CN115482487A - A video sequence sorting method, device, electronic equipment and storage medium - Google Patents
A video sequence sorting method, device, electronic equipment and storage mediumDownload PDFInfo
- Publication number
- CN115482487A CN115482487ACN202211122318.8ACN202211122318ACN115482487ACN 115482487 ACN115482487 ACN 115482487ACN 202211122318 ACN202211122318 ACN 202211122318ACN 115482487 ACN115482487 ACN 115482487A
- Authority
- CN
- China
- Prior art keywords
- frequency domain
- video
- video sequence
- frame
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本申请涉及图像处理技术领域，尤其是涉及一种视频序列的排序方法、装置、电子设备及存储介质。The present application relates to the technical field of image processing, and in particular to a video sequence sorting method, device, electronic equipment and storage medium.
背景技术Background technique
视频序列是有时空联系的多个视频图像按照拍摄时间顺序的排列，例如冠脉造影序列，是诊断冠状动脉粥样硬化性心脏病(冠心病)的一种常用而且有效的方法，通过摄入含原子序数高的元素的物质，然后在预诊断的体内部位摄取多张放射照片以供医学诊断，具体是使用导管向冠脉注射显影剂，通过X光拍摄得到2D冠脉造影图像。Video sequence is the arrangement of multiple video images linked by time and space according to the order of shooting time, such as coronary angiography sequence, which is a common and effective method for diagnosing coronary atherosclerotic heart disease (coronary heart disease). Substances containing elements with a high atomic number, and then take multiple radiographs at pre-diagnosed internal parts for medical diagnosis. Specifically, a catheter is used to inject a contrast agent into the coronary artery, and 2D coronary angiography images are obtained by taking X-rays.
目前，在针对同一个分析目标的多个视频序列中，例如针对同一血管部位的多个冠脉造影序列，并不是每个视频序列都适合进行分析诊断，所以需要由经验丰富的医生对每个冠脉造影序列中的多张造影图像的质量进行人为主观评估，确定出质量较好的视频序列，从而对该视频序列中的造影图像进行分析，但是人工评估的方式需要耗费大量的人力与时间，增大了医生和患者的手术负担。因此，如何提高分析视频序列的效率，以减轻医生负担，成为了亟待解决的问题。At present, among multiple video sequences for the same analysis target, such as multiple coronary angiography sequences for the same vascular site, not every video sequence is suitable for analysis and diagnosis, so it is necessary for experienced doctors to analyze each The quality of multiple angiographic images in the coronary angiography sequence is subjectively evaluated by humans, and a video sequence with better quality is determined, so as to analyze the angiographic images in the video sequence, but manual evaluation requires a lot of manpower and time , increasing the surgical burden on doctors and patients. Therefore, how to improve the efficiency of analyzing video sequences to reduce the burden on doctors has become an urgent problem to be solved.
发明内容Contents of the invention
有鉴于此，本申请的目的在于提供一种视频序列的排序方法、装置、电子设备及存储介质，能够通过每个视频序列中的前景帧和背景帧，确定出每个视频序列的质量，根据每个视频序列的质量对多个视频序列进行排序，可以按照排序后的视频序列优先对质量较好的视频序列中的分析目标进行分析，提高了分析视频序列的效率，减轻了医生负担。In view of this, the purpose of this application is to provide a video sequence sorting method, device, electronic equipment and storage medium, which can determine the quality of each video sequence through the foreground frame and background frame in each video sequence, according to The quality of each video sequence sorts multiple video sequences, and the analysis targets in the video sequences with better quality can be analyzed according to the sorted video sequences, which improves the efficiency of analyzing video sequences and reduces the burden on doctors.
本申请主要包括以下几个方面：This application mainly includes the following aspects:
第一方面，本申请实施例提供了一种视频序列的排序方法，所述排序方法包括：In the first aspect, the embodiment of the present application provides a video sequence sorting method, the sorting method comprising:
获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；Acquiring a plurality of video frames of each video sequence in the plurality of video sequences shot for the analysis target;
针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；For each video sequence, in a plurality of video frames of the video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target;
基于所述前景帧和所述背景帧，确定该视频序列的质量；determining the quality of the video sequence based on the foreground frame and the background frame;
按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。The plurality of video sequences are sorted according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequences.
进一步的，所述基于所述前景帧和所述背景帧，确定该视频序列的质量的步骤，包括：Further, the step of determining the quality of the video sequence based on the foreground frame and the background frame includes:
基于所述前景帧，将所述前景帧经过频域转换后，得到前景频域图，并基于所述背景帧，将所述背景帧经过频域转换后，得到背景频域图；Based on the foreground frame, after the foreground frame is subjected to frequency domain conversion, a foreground frequency domain map is obtained, and based on the background frame, after the background frame is subjected to frequency domain conversion, a background frequency domain map is obtained;
基于所述前景频域图和所述背景频域图，得到仅具有所述分析目标的目标频域图；Based on the foreground frequency domain diagram and the background frequency domain diagram, a target frequency domain diagram having only the analysis target is obtained;
将所述目标频域图根据预设去除区域分割为多个目标频域子区域，并将所述背景频域图根据预设去除区域分割为多个背景频域子区域；The target frequency domain image is divided into a plurality of target frequency domain sub-areas according to the preset removal area, and the background frequency domain image is divided into a plurality of background frequency domain sub-areas according to the preset removal area;
根据所述多个目标频域子区域，确定所述目标频域图的图像质量，并根据所述多个背景频域子区域，确定所述背景频域图的图像质量；determining the image quality of the target frequency domain image according to the plurality of target frequency domain subregions, and determining the image quality of the background frequency domain image according to the plurality of background frequency domain subregions;
基于所述目标频域图的图像质量和所述背景频域图的图像质量，确定该视频序列的质量。The quality of the video sequence is determined based on the image quality of the target frequency domain map and the image quality of the background frequency domain map.
进一步的，所述在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧的步骤，包括：Further, the step of determining a foreground frame with the analysis target and a background frame without the analysis target among the multiple video frames of the video sequence includes:
在该视频序列的多个视频帧中，针对每个视频帧，获取该视频帧的每个像素点对应的灰度值和该视频帧中包括的像素点的个数；In a plurality of video frames of the video sequence, for each video frame, the gray value corresponding to each pixel of the video frame and the number of pixels included in the video frame are obtained;
将该视频帧的每个像素点对应的灰度值相加，得到该视频帧对应的灰度值总和；Adding the gray value corresponding to each pixel of the video frame to obtain the sum of the gray value corresponding to the video frame;
将该视频帧对应的灰度值总和与该视频帧中包括的像素点的个数的商，确定为该视频帧对应的灰度均值；The quotient of the grayscale value sum corresponding to the video frame and the number of pixels included in the video frame is determined as the grayscale mean value corresponding to the video frame;
基于该视频序列的所述多个视频帧中的每个视频帧对应的灰度均值，将数值最大的灰度均值对应的视频帧确定为不具有分析目标的背景帧，并将数值最小的灰度均值对应的视频帧确定为具有分析目标的前景帧。Based on the grayscale mean value corresponding to each video frame in the plurality of video frames of the video sequence, the video frame corresponding to the grayscale mean value with the largest value is determined as a background frame without an analysis target, and the grayscale value with the smallest value The video frame corresponding to the degree mean value is determined as the foreground frame with the analysis target.
进一步的，所述基于所述前景频域图和所述背景频域图，得到仅具有所述分析目标的目标频域图的步骤，包括：Further, the step of obtaining the target frequency domain map with only the analysis target based on the foreground frequency domain map and the background frequency domain map includes:
基于所述前景频域图，获取所述前景频域图中每个像素点的像素值；Based on the foreground frequency domain image, obtain the pixel value of each pixel in the foreground frequency domain image;
基于所述背景频域图，获取所述背景频域图中每个像素点的像素值；Based on the background frequency domain image, obtain the pixel value of each pixel in the background frequency domain image;
将所述前景频域图中每个像素点的像素值与所述背景频域图中对应位置的像素点的像素值相减，得到仅具有所述分析目标的目标频域图。Subtracting the pixel value of each pixel in the foreground frequency domain image from the pixel value of a corresponding pixel in the background frequency domain image to obtain a target frequency domain image with only the analysis target.
进一步的，所述根据所述多个目标频域子区域，确定所述目标频域图的图像质量的步骤，包括：Further, the step of determining the image quality of the target frequency domain image according to the multiple target frequency domain sub-regions includes:
根据所述多个目标频域子区域，获取预先确定的每个目标频域子区域的最大像素值和每个目标频域子区域的平均方差；Acquiring a predetermined maximum pixel value of each target frequency domain subregion and an average variance of each target frequency domain subregion according to the plurality of target frequency domain subregions;
针对每个目标频域子区域，基于该目标频域子区域中的最大像素值和平均方差，确定该目标频域子区域的质量；For each target frequency domain sub-region, based on the maximum pixel value and average variance in the target frequency domain sub-region, determine the quality of the target frequency domain sub-region;
基于每个目标频域子区域的质量，将每个目标频域子区域的质量的加和与目标频域子区域的个数的商，确定为所述目标频域图的图像质量。Based on the quality of each target frequency domain sub-region, the quotient of the sum of the qualities of each target frequency domain sub-region and the number of target frequency domain sub-regions is determined as the image quality of the target frequency domain image.
进一步的，通过以下步骤确定每个目标频域子区域的最大像素值：Further, the maximum pixel value of each target frequency domain sub-region is determined by the following steps:
获取所述多个目标频域子区域中每个目标频域子区域中的每个像素点的像素值；Acquiring the pixel value of each pixel in each target frequency domain sub-area among the plurality of target frequency domain sub-areas;
针对每个目标频域子区域，在该目标频域子区域中所有像素点的每个像素点的像素值中，将数值最大的像素值确定为该目标频域子区域中的最大像素值。For each target frequency domain sub-region, among the pixel values of all pixels in the target frequency domain sub-region, the pixel value with the largest value is determined as the maximum pixel value in the target frequency-domain sub-region.
进一步的，所述基于所述目标频域图的图像质量和所述背景频域图的图像质量，确定该视频序列的质量的步骤，包括：Further, the step of determining the quality of the video sequence based on the image quality of the target frequency domain image and the image quality of the background frequency domain image includes:
基于所述目标频域图的图像质量，将所述目标频域图的图像质量和第一预设权重的乘积，确定为该视频序列的第一质量分量；Based on the image quality of the target frequency domain image, determining the product of the image quality of the target frequency domain image and a first preset weight as the first quality component of the video sequence;
基于所述背景频域图的图像质量，将所述背景频域图的图像质量和第二预设权重的乘积，确定为该视频序列的第二质量分量；其中，所述第二预设权重是数字一与所述第一预设权重的差值；Based on the image quality of the background frequency domain image, the product of the image quality of the background frequency domain image and a second preset weight is determined as the second quality component of the video sequence; wherein, the second preset weight is the difference between number one and the first preset weight;
将该视频序列的第一质量分量与该视频序列的第二质量分量的加和，确定为该视频序列的质量。The sum of the first quality component of the video sequence and the second quality component of the video sequence is determined as the quality of the video sequence.
第二方面，本申请实施例还提供了一种视频序列的排序装置，所述排序装置包括：In the second aspect, the embodiment of the present application also provides a sorting device for video sequences, and the sorting device includes:
获取模块，用于获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；An acquisition module, configured to acquire a plurality of video frames of each video sequence in a plurality of video sequences taken for the analysis target;
第一确定模块，用于针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；The first determining module is configured to, for each video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target among multiple video frames of the video sequence;
第二确定模块，用于基于所述前景帧和所述背景帧，确定该视频序列的质量；A second determining module, configured to determine the quality of the video sequence based on the foreground frame and the background frame;
排序模块，用于按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。A sorting module, configured to sort the plurality of video sequences according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequences.
第三方面，本申请实施例还提供一种电子设备，包括：处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器与所述存储器之间通过总线通信，所述机器可读指令被所述处理器执行时执行如上述的视频序列的排序方法的步骤。In the third aspect, the embodiment of the present application also provides an electronic device, including: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processing The processor communicates with the memory through a bus, and when the machine-readable instructions are executed by the processor, the steps of the video sequence sorting method described above are executed.
第四方面，本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器运行时执行如上述的视频序列的排序方法的步骤。In the fourth aspect, the embodiment of the present application also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the above-mentioned method for sorting video sequences is executed. step.
本申请实施例提供的一种视频序列的排序方法、装置、电子设备及存储介质，所述排序方法包括：获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；基于所述前景帧和所述背景帧，确定该视频序列的质量；按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。A method, device, electronic device, and storage medium for sorting video sequences provided in an embodiment of the present application, the sorting method includes: acquiring multiple video frames of each of multiple video sequences shot for the analysis target; For each video sequence, in a plurality of video frames of the video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target; based on the foreground frame and the background frame, determine The quality of the video sequence: sorting the plurality of video sequences according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequence.
这样，采用本申请提供的技术方案能够通过每个视频序列中的前景帧和背景帧，确定出每个视频序列的质量，根据每个视频序列的质量对多个视频序列进行排序，可以按照排序后的视频序列优先对质量较好的视频序列中的分析目标进行分析，提高了分析视频序列的效率，减轻了医生负担。In this way, the technical solution provided by this application can determine the quality of each video sequence through the foreground frame and background frame in each video sequence, and sort multiple video sequences according to the quality of each video sequence. The final video sequence first analyzes the analysis target in the video sequence with better quality, which improves the efficiency of analyzing the video sequence and reduces the burden on doctors.
为使本申请的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。In order to make the above-mentioned purpose, features and advantages of the present application more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.
附图说明Description of drawings
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, so It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.
图1示出了本申请实施例所提供的一种视频序列的排序方法的流程图；Fig. 1 shows a flow chart of a method for sorting video sequences provided by an embodiment of the present application;
图2示出了本申请实施例所提供的另一种视频序列的排序方法的流程图；FIG. 2 shows a flow chart of another video sequence sorting method provided by the embodiment of the present application;
图3示出了本申请实施例所提供的一种背景频域图分割的示意图；FIG. 3 shows a schematic diagram of a background frequency-domain image segmentation provided by an embodiment of the present application;
图4示出了本申请实施例所提供的一种目标频域图分割的示意图；FIG. 4 shows a schematic diagram of a target frequency-domain image segmentation provided by an embodiment of the present application;
图5示出了本申请实施例所提供的一种视频序列的排序装置的结构图；FIG. 5 shows a structural diagram of an apparatus for sorting video sequences provided by an embodiment of the present application;
图6示出了本申请实施例所提供的一种电子设备的结构示意图。FIG. 6 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.
具体实施方式detailed description
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，应当理解，本申请中的附图仅起到说明和描述的目的，并不用于限定本申请的保护范围。另外，应当理解，示意性的附图并未按实物比例绘制。本申请中使用的流程图示出了根据本申请的一些实施例实现的操作。应当理解，流程图的操作可以不按顺序实现，没有逻辑的上下文关系的步骤可以反转顺序或者同时实施。此外，本领域技术人员在本申请内容的指引下，可以向流程图添加一个或多个其他操作，也可以从流程图中移除一个或多个操作。In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the technical solutions in the embodiments of the present application The drawings are only for the purpose of illustration and description, and are not used to limit the protection scope of the present application. Additionally, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented in accordance with some embodiments of the application. It should be understood that the operations of the flowcharts may be performed out of order, and steps that do not have a logical context may be performed in reverse order or simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.
另外，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的全部其他实施例，都属于本申请保护的范围。In addition, the described embodiments are only some of the embodiments of the application, not all of the embodiments. The components of the embodiments of the application generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present application.
为了使得本领域技术人员能够使用本申请内容，结合特定应用场景“视频序列的排序”，给出以下实施方式，对于本领域技术人员来说，在不脱离本申请的精神和范围的情况下，可以将这里定义的一般原理应用于其他实施例和应用场景。In order to enable those skilled in the art to use the content of this application, in combination with the specific application scenario "Video Sequence Sorting", the following implementation methods are given. For those skilled in the art, without departing from the spirit and scope of this application, The general principles defined here can be applied to other embodiments and application scenarios.
本申请实施例下述方法、装置、电子设备或计算机可读存储介质可以应用于任何需要排序视频序列的场景，本申请实施例并不对具体的应用场景作限制，任何使用本申请实施例提供的一种视频序列的排序方法、装置、电子设备及存储介质的方案均在本申请保护范围内。The following methods, devices, electronic devices, or computer-readable storage media in the embodiments of the present application can be applied to any scene where video sequences need to be sorted. The embodiments of the present application are not limited to specific application scenarios. A video sequence sorting method, device, electronic equipment, and storage medium solutions are all within the protection scope of the present application.
值得注意的是，视频序列是有时空联系的多个视频图像按照拍摄时间顺序的排列，例如冠脉造影序列，是诊断冠状动脉粥样硬化性心脏病(冠心病)的一种常用而且有效的方法，通过摄入含原子序数高的元素的物质，然后在预诊断的体内部位摄取多张放射照片以供医学诊断，具体是使用导管向冠脉注射显影剂，通过X光拍摄得到2D冠脉造影图像。It is worth noting that a video sequence is the arrangement of multiple video images connected in time and space according to the order of shooting time, such as a coronary angiography sequence, which is a commonly used and effective method for diagnosing coronary atherosclerotic heart disease (coronary heart disease). Method, by ingesting substances containing elements with a high atomic number, and then taking multiple radiographs at pre-diagnosed internal body parts for medical diagnosis, specifically injecting a contrast agent into the coronary arteries using a catheter, and obtaining 2D coronary arteries through X-ray photography Contrast image.
目前，在针对同一个分析目标的多个视频序列中，例如针对同一血管部位的多个冠脉造影序列，并不是每个视频序列都适合进行分析诊断，所以需要由经验丰富的医生对每个冠脉造影序列中的多张造影图像的质量进行人为主观评估，确定出质量较好的视频序列，从而对该视频序列中的造影图像进行分析，但是人工评估的方式需要耗费大量的人力与时间，增大了医生和患者的手术负担。因此，如何提高分析视频序列的效率，以减轻医生负担，成为了亟待解决的问题。At present, among multiple video sequences for the same analysis target, such as multiple coronary angiography sequences for the same vascular site, not every video sequence is suitable for analysis and diagnosis, so it is necessary for experienced doctors to analyze each The quality of multiple angiographic images in the coronary angiography sequence is subjectively evaluated by humans, and a video sequence with better quality is determined, so as to analyze the angiographic images in the video sequence, but manual evaluation requires a lot of manpower and time , increasing the surgical burden on doctors and patients. Therefore, how to improve the efficiency of analyzing video sequences to reduce the burden on doctors has become an urgent problem to be solved.
基于此，本申请提出了一种视频序列的排序方法、装置、电子设备及存储介质，所述排序方法包括：获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；基于所述前景帧和所述背景帧，确定该视频序列的质量；按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。Based on this, the present application proposes a video sequence sorting method, device, electronic equipment, and storage medium, the sorting method includes: acquiring multiple video frames of each video sequence in multiple video sequences shot for the analysis target ; For each video sequence, in a plurality of video frames of the video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target; based on the foreground frame and the background frame, determining the quality of the video sequence; sorting the plurality of video sequences according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequence.
这样，采用本申请提供的技术方案能够通过每个视频序列中的前景帧和背景帧，确定出每个视频序列的质量，根据每个视频序列的质量对多个视频序列进行排序，可以按照排序后的视频序列优先对质量较好的视频序列中的分析目标进行分析，提高了分析视频序列的效率，减轻了医生负担。In this way, the technical solution provided by this application can determine the quality of each video sequence through the foreground frame and background frame in each video sequence, and sort multiple video sequences according to the quality of each video sequence. The final video sequence first analyzes the analysis target in the video sequence with better quality, which improves the efficiency of analyzing the video sequence and reduces the burden on doctors.
为便于对本申请进行理解，下面将结合具体实施例对本申请提供的技术方案进行详细说明。In order to facilitate the understanding of the present application, the technical solution provided by the present application will be described in detail below in conjunction with specific embodiments.
请参阅图1，图1为本申请实施例所提供的一种视频序列的排序方法的流程图，如图1中所示，所述排序方法包括：Please refer to FIG. 1. FIG. 1 is a flow chart of a sorting method for a video sequence provided in an embodiment of the present application. As shown in FIG. 1, the sorting method includes:
S101、获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；S101. Obtain multiple video frames of each video sequence in multiple video sequences shot for the analysis target;
该步骤中，分析目标可以是血管，也可以是输卵管，视频序列可以是冠脉造影序列，也可以是输卵管造影序列；目前冠脉造影序列中的血管造影图像(视频帧)的质量一般由经验丰富的医生进行认为主观评估，或是利用一些基本的统计学指标，比如均值，方差，以至于信噪比等粗略计算图像的质量评分。但是，人工评估的方式需要耗费大量的人力与时间，有限的医疗资源(医生)与不断增大的造影数量形成明显的矛盾。对于造影的分析，将那些质量好的自动筛选出来能大大加快分析速度，特别是在手术中，时间异常宝贵，人工分析这时候成为一个巨大的瓶颈，这无疑增大了医生和患者的手术负担。而且，用一些基本的统计学指标进行质量评分，太过于片面，太过于全局化。一般来讲，方差小的数据(一维二维等信号)表示其稳定性好，但在血管造影图像中，首先要保证有血管显影在里面，比如无血管显影的造影图像，方差很低，但造影剂还没流入血管，看不到血管，这是不可分析的图像。再比如信噪比，其计算的是整体图像的情况，比如说，背景噪声特别低，而前景高，也可能导致整体的信噪比降低。因此这些硬性指标基于全局计算，很容易忽略造影图像中的前景(血管)重要性。In this step, the analysis target can be a blood vessel or a fallopian tube, and the video sequence can be a coronary angiography sequence or a fallopian tube angiography sequence; currently, the quality of angiography images (video frames) in a coronary angiography sequence is generally determined by experience. Rich doctors make subjective evaluations, or use some basic statistical indicators, such as mean, variance, and even signal-to-noise ratio to roughly calculate the quality score of the image. However, manual assessment requires a lot of manpower and time, and there is an obvious contradiction between limited medical resources (doctors) and the increasing number of angiography. For the analysis of radiography, automatic screening of those with good quality can greatly speed up the analysis, especially in surgery, where time is extremely precious, and manual analysis becomes a huge bottleneck at this time, which undoubtedly increases the surgical burden on doctors and patients . Moreover, using some basic statistical indicators for quality scoring is too one-sided and too global. Generally speaking, data with small variance (one-dimensional, two-dimensional, etc. signals) means that its stability is good, but in angiography images, it is first necessary to ensure that there are blood vessels in it, such as angiography images without blood vessel development, the variance is very low, But the contrast agent has not yet flowed into the blood vessels, and the blood vessels cannot be seen. This is an unanalyzable image. Another example is the signal-to-noise ratio, which calculates the overall image. For example, the background noise is particularly low, while the foreground is high, which may also lead to a decrease in the overall signal-to-noise ratio. Therefore, these hard indicators are based on global calculations, and it is easy to ignore the importance of foreground (vessels) in contrast images.
示例性的，在诊断冠状动脉粥样硬化性心脏病(冠心病)时，需要通过冠状动脉造影进行诊断。每个患者一般会拍摄多个序列的造影图像(二维的动态序列)，例如，针对患者的某个血管部位从不同角度拍摄视频，得到了多个造影序列(视频序列)，每个造影序列中具有多个造影图像(视频帧)，但有些造影图像由于造影剂还没有流入血管，导致造影图像中看不到血管，使该造影图像不能用于病症分析，所以并不是每个造影序列都能够分析，或者都适合进行后续分析。如何快速地将这些图像按照质量进行正确的排序，是一个目前存在的问题。解决这一问题，能节省医生不必要的找图，看图时间，而将时间放在正真的患者病情，血管形态学功能学等这些重要的分析上，能减轻医生负担，缩短手术时间或术后的分析时间，为广大医生和患者带来福音。Exemplarily, when diagnosing coronary atherosclerotic heart disease (coronary heart disease), it needs to be diagnosed by coronary angiography. Each patient generally takes multiple sequences of contrast images (two-dimensional dynamic sequences). There are multiple contrast images (video frames), but some contrast images have no blood vessels because the contrast agent has not flowed into the blood vessels, so that the contrast images cannot be used for disease analysis, so not every contrast sequence capable of analysis, or both are suitable for subsequent analysis. How to quickly and correctly sort these images according to quality is a current problem. Solving this problem can save doctors unnecessary time for looking for pictures and looking at pictures, and spend time on important analysis such as the real patient's condition, vascular morphology and function, which can reduce the burden on doctors, shorten operation time or The postoperative analysis time brings good news to doctors and patients.
S102、针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；S102. For each video sequence, among multiple video frames of the video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target;
需要说明的是，在该视频序列的多个视频帧中，确定出具有分析目标的前景帧和不具有分析目标的背景帧的步骤，包括：It should be noted that, among the multiple video frames of the video sequence, the step of determining the foreground frame with the analysis target and the background frame without the analysis target includes:
S1021、在该视频序列的多个视频帧中，针对每个视频帧，获取该视频帧的每个像素点对应的灰度值和该视频帧中包括的像素点的个数；S1021. In a plurality of video frames of the video sequence, for each video frame, obtain the gray value corresponding to each pixel of the video frame and the number of pixels included in the video frame;
S1022、将该视频帧的每个像素点对应的灰度值相加，得到该视频帧对应的灰度值总和；S1022. Add the gray value corresponding to each pixel of the video frame to obtain the sum of the gray value corresponding to the video frame;
S1023、将该视频帧对应的灰度值总和与该视频帧中包括的像素点的个数的商，确定为该视频帧对应的灰度均值；S1023. Determine the quotient of the sum of the grayscale values corresponding to the video frame and the number of pixels included in the video frame as the grayscale mean value corresponding to the video frame;
S1024、基于该视频序列的所述多个视频帧中的每个视频帧对应的灰度均值，将数值最大的灰度均值对应的视频帧确定为不具有分析目标的背景帧，并将数值最小的灰度均值对应的视频帧确定为具有分析目标的前景帧。S1024. Based on the grayscale mean value corresponding to each video frame in the plurality of video frames of the video sequence, determine the video frame corresponding to the grayscale mean value with the largest value as a background frame without an analysis target, and set the value to be the smallest The video frame corresponding to the gray mean value of is determined as the foreground frame with the analysis target.
示例性的，上述步骤S1021-S1024的目的在于自动准确地筛选出血管造影充盈的前景帧(具有分析目标的前景帧)和造影剂未注入时的背景帧(不具有分析目标的背景帧)。首先计算造影序列中每个视频帧的灰度均值，这里，针对每个视频帧，该视频帧的灰度均值的计算方式是：将该视频帧的每个像素点的灰度值的加和与该视频帧包括的像素点的个数的商，确定为该视频帧的灰度均值；基于该造影序列中包括的所有视频帧的灰度均值，沿着拍摄时间画出灰度均值的变化曲线，并将变化曲线中灰度均值最大的视频帧作为背景帧，灰度均值最小的视频帧作为血管帧(前景帧)；这里，因为造影剂在图像上显示暗色，所以灰度均值小的才是血管帧。Exemplarily, the purpose of the above steps S1021-S1024 is to automatically and accurately screen out foreground frames of angiographic filling (foreground frames with analysis targets) and background frames without contrast agent injection (background frames without analysis targets). First calculate the grayscale mean value of each video frame in the contrast sequence. Here, for each video frame, the calculation method of the grayscale mean value of the video frame is: the sum of the grayscale values of each pixel of the video frame The quotient with the number of pixels included in the video frame is determined as the average gray value of the video frame; based on the average gray values of all video frames included in the contrast sequence, the change in the average gray value is drawn along the shooting time curve, and the video frame with the largest average gray value in the change curve is used as the background frame, and the video frame with the smallest average gray value is used as the blood vessel frame (foreground frame); here, because the contrast agent displays dark colors on the image, the image with the smallest average gray value It is the blood vessel frame.
S103、基于所述前景帧和所述背景帧，确定该视频序列的质量；S103. Determine the quality of the video sequence based on the foreground frame and the background frame;
需要说明的是，基于前景帧和背景帧，确定该视频序列的质量的步骤请参阅图2，图2为本申请实施例所提供另一种视频序列的排序方法的流程图，如图2中所示，基于前景帧和背景帧，确定该视频序列的质量的步骤，包括：It should be noted that, based on the foreground frame and the background frame, please refer to FIG. 2 for the steps of determining the quality of the video sequence. FIG. As shown, based on the foreground frame and the background frame, the steps of determining the quality of the video sequence include:
S201、基于所述前景帧，将所述前景帧经过频域转换后，得到前景频域图，并基于所述背景帧，将所述背景帧经过频域转换后，得到背景频域图；S201. Based on the foreground frame, perform frequency domain conversion on the foreground frame to obtain a foreground frequency domain map, and based on the background frame, perform frequency domain conversion on the background frame to obtain a background frequency domain map;
该步骤中，频域转换可以采用离散快速傅里叶变换(FFT)，通过FFT将前景帧和背景帧进行时域到频域的变换，具体公式如下：In this step, the frequency domain conversion can adopt the discrete fast Fourier transform (FFT), and the foreground frame and the background frame are transformed from the time domain to the frequency domain through the FFT, and the specific formula is as follows:
其中，m和n分别表示二维图像(即前景帧和背景帧)的横纵坐标，p和q表示转换后的频域图(即前景频域图和背景频域图)中的空间坐标，M和N分别表示二维图像的长和宽。Among them, m and n represent the horizontal and vertical coordinates of the two-dimensional image (ie, the foreground frame and the background frame), respectively, and p and q represent the spatial coordinates in the converted frequency domain image (ie, the foreground frequency domain image and the background frequency domain image), M and N represent the length and width of the two-dimensional image, respectively.
这里，频域图的特点是四周部分为高频信息，包含了图像的噪声，而中间为低频信息，包含了大量的图像重要特征。示例性的，血管频域图(前景频域图)的中间丰富，而背景帧其四周信息较为贫乏。Here, the characteristic of the frequency domain map is that the surrounding part is high-frequency information, which contains the noise of the image, while the middle part is low-frequency information, which contains a large number of important features of the image. Exemplarily, the center of the blood vessel frequency domain image (foreground frequency domain image) is rich, while the surrounding information of the background frame is relatively poor.
S202、基于所述前景频域图和所述背景频域图，得到仅具有所述分析目标的目标频域图；S202. Based on the foreground frequency domain diagram and the background frequency domain diagram, obtain a target frequency domain diagram having only the analysis target;
需要说明的是，基于前景频域图和背景频域图，得到仅具有分析目标的目标频域图的步骤，包括：It should be noted that, based on the foreground frequency domain diagram and the background frequency domain diagram, the steps of obtaining the target frequency domain diagram with only the analysis target include:
S2021、基于所述前景频域图，获取所述前景频域图中每个像素点的像素值；S2021. Based on the foreground frequency domain image, obtain the pixel value of each pixel in the foreground frequency domain image;
S2022、基于所述背景频域图，获取所述背景频域图中每个像素点的像素值；S2022. Acquire the pixel value of each pixel in the background frequency domain image based on the background frequency domain image;
S2023、将所述前景频域图中每个像素点的像素值与所述背景频域图中对应位置的像素点的像素值相减，得到仅具有所述分析目标的目标频域图。S2023. Subtract the pixel value of each pixel in the foreground frequency domain image from the pixel value of the corresponding pixel in the background frequency domain image to obtain a target frequency domain image with only the analysis target.
该步骤中，目的是为了独立评估背景质量与前景质量，那么就需要将前景和背景分开。示例性的，一般来讲可用图像分割技术将前景帧中的分析目标与背景分开，而在分析目标是血管的前景帧中，考虑到本实施例不需要非常精确的前景背景区域(无需精确到每一个像素)，所以不需要采用精确而复杂的图像分割区域，由于心脏的跳动，血管与导管在图像序列中呈现运动状态，因此如果在时域中相减的话，会因为错位而导致相减结果不可用。因此，本实施例采用频域相减的方式得到前景频域图，即将前景频域图与背景频域图相减，可将前景频域图中的背景区域减去，得到前景区域(分析目标，例如血管)；这种方式避免了图像因为空间错位的问题，在频域中相减后，原本噪声的区域被弱化，而且逆变换回时域后能保留血管重要前景信息，这说明通过频域相减取前景的方式具有有效性。In this step, the purpose is to independently evaluate the quality of the background and the quality of the foreground, then the foreground and the background need to be separated. Exemplarily, in general, image segmentation technology can be used to separate the analysis target in the foreground frame from the background, and in the foreground frame in which the analysis target is a blood vessel, considering that this embodiment does not require very accurate foreground and background regions (no need to be accurate to Each pixel), so there is no need to use accurate and complex image segmentation regions. Due to the beating of the heart, blood vessels and catheters are in motion in the image sequence, so if they are subtracted in the time domain, they will be subtracted due to misalignment Results are not available. Therefore, this embodiment adopts the method of frequency domain subtraction to obtain the foreground frequency domain map, that is, to subtract the foreground frequency domain map from the background frequency domain map, and subtract the background area in the foreground frequency domain map to obtain the foreground area (the analysis target , such as blood vessels); this method avoids the problem of spatial misalignment of the image. After subtraction in the frequency domain, the original noise area is weakened, and the important foreground information of blood vessels can be preserved after inverse transformation back to the time domain. This shows that by The method of subtracting the foreground in the frequency domain is effective.
S203、将所述目标频域图根据预设去除区域分割为多个目标频域子区域，并将所述背景频域图根据预设去除区域分割为多个背景频域子区域；S203. Divide the target frequency domain map into multiple target frequency domain sub-regions according to the preset removal area, and divide the background frequency domain map into multiple background frequency domain sub-regions according to the preset removal area;
示例性的，当得到目标频域图和背景频域图后，可对其分别进行质量评估。首先，需要分别对目标频域图和背景频域图进行区域分割，请参阅图3和图4，图3为本申请实施例所提供的一种背景频域图分割的示意图，图4为本申请实施例所提供的一种目标频域图分割的示意图。如图3所示，预设去除区域为背景频域图中的十字区域，通过十字区域将背景频域图分为了四个背景频域子区域，分别为图3中的x11、x12、x21和x22；如图4所示，预设去除区域为目标频域图中的十字区域，通过十字区域将目标频域图分为了四个目标频域子区域，分别为图4中的y11、y12、y21和y22；这里的预设去除区域可以是根据历史经验或者实验数据预先确定的区域。Exemplarily, after the target frequency-domain image and the background frequency-domain image are obtained, quality evaluation can be performed on them respectively. First of all, it is necessary to segment the target frequency domain image and the background frequency domain image respectively, please refer to Figure 3 and Figure 4, Figure 3 is a schematic diagram of a background frequency domain image segmentation provided by the embodiment of the present application, and Figure 4 is the basic A schematic diagram of target frequency domain image segmentation provided in the embodiment of the application. As shown in Figure 3, the preset removal area is the cross area in the background frequency domain image, and the background frequency domain image is divided into four background frequency domain sub-areas through the cross area, which are x11 , x12 , x21 and x22 ; as shown in Figure 4, the preset removal area is the cross area in the target frequency domain map, and the target frequency domain map is divided into four target frequency domain sub-areas by the cross area, which are respectively the y11 , y12 , y21 and y22 ; the preset removal area here may be an area predetermined according to historical experience or experimental data.
S204、根据所述多个目标频域子区域，确定所述目标频域图的图像质量，并根据所述多个背景频域子区域，确定所述背景频域图的图像质量；S204. Determine the image quality of the target frequency domain map according to the multiple target frequency domain subregions, and determine the image quality of the background frequency domain map according to the multiple background frequency domain subregions;
需要说明的是，根据多个目标频域子区域，确定目标频域图的图像质量的步骤，包括：It should be noted that, according to multiple target frequency domain sub-regions, the step of determining the image quality of the target frequency domain map includes:
S2041、根据所述多个目标频域子区域，获取预先确定的每个目标频域子区域的最大像素值和每个目标频域子区域的平均方差；S2041. Acquire a predetermined maximum pixel value of each target frequency domain subregion and an average variance of each target frequency domain subregion according to the plurality of target frequency domain subregions;
需要说明的是，通过以下步骤确定每个目标频域子区域的最大像素值：It should be noted that the maximum pixel value of each target frequency domain sub-region is determined by the following steps:
1)、获取所述多个目标频域子区域中每个目标频域子区域中的每个像素点的像素值；1), acquiring the pixel value of each pixel in each target frequency domain sub-region in the plurality of target frequency domain sub-regions;
2)、针对每个目标频域子区域，在该目标频域子区域中所有像素点的每个像素点的像素值中，将数值最大的像素值确定为该目标频域子区域中的最大像素值。2), for each target frequency domain sub-region, among the pixel values of each pixel of all pixels in the target frequency domain sub-region, determine the pixel value with the largest value as the maximum value in the target frequency domain sub-region Pixel values.
该步骤中，需要确定出目标频域图中的每个目标频域子区域的最大像素值和平均方差；这里，针对每个目标频域子区域，确定该目标频域子区域的平均方差的步骤，包括：In this step, it is necessary to determine the maximum pixel value and average variance of each target frequency domain sub-region in the target frequency domain diagram; here, for each target frequency domain sub-region, determine the average variance of the target frequency domain sub-region steps, including:
一、将获取到的该目标频域子区域中的每个像素点的像素值的加和与该目标频域子区域中包括的像素点的个数的商，确定为该目标频域子区域的平均像素值；1. Determine the quotient of the sum of the obtained pixel values of each pixel in the target frequency domain sub-area and the number of pixels included in the target frequency domain sub-area as the target frequency domain sub-area The average pixel value of ;
二、将该目标频域子区域中的每个像素点的像素值与该目标频域子区域的平均像素值的差值的平方和，确定为该目标频域子区域的方差；2. The square sum of the difference between the pixel value of each pixel in the target frequency domain sub-region and the average pixel value of the target frequency domain sub-region is determined as the variance of the target frequency domain sub-region;
三、将该目标频域子区域的方差与该目标频域子区域中包括的像素点的个数的商，确定为该目标频域子区域的平均方差。3. Determine the quotient of the variance of the target frequency-domain sub-area and the number of pixels included in the target frequency-domain sub-area as the average variance of the target frequency-domain sub-area.
这里，还需要根据所述多个背景频域子区域，获取预先确定的每个背景频域子区域的最大像素值和每个目标频域子区域的平均方差；通过以下步骤确定每个目标频域子区域的最大像素值：Here, it is also necessary to obtain the predetermined maximum pixel value of each background frequency domain subregion and the average variance of each target frequency domain subregion according to the plurality of background frequency domain subregions; Maximum pixel value for a domain subregion:
1)、获取所述多个背景频域子区域中每个背景频域子区域中的每个像素点的像素值；1), obtaining the pixel value of each pixel in each background frequency domain sub-area in the plurality of background frequency domain sub-areas;
2)、针对每个背景频域子区域，在该背景频域子区域中所有像素点的每个像素点的像素值中，将数值最大的像素值确定为该背景频域子区域中的最大像素值。2), for each background frequency domain sub-region, among the pixel values of each pixel of all pixels in the background frequency domain sub-region, the pixel value with the largest value is determined as the maximum value in the background frequency domain sub-region Pixel values.
这里，针对每个背景频域子区域，确定该背景频域子区域的平均方差的步骤，包括：Here, for each background frequency domain sub-region, the step of determining the average variance of the background frequency domain sub-region includes:
一、将获取到的该背景频域子区域中的每个像素点的像素值的加和与该背景频域子区域中包括的像素点的个数的商，确定为该背景频域子区域的平均像素值；1. Determine the quotient of the sum of the pixel values of each pixel in the background frequency domain sub-area obtained and the number of pixels included in the background frequency domain sub-area as the background frequency domain sub-area The average pixel value of ;
二、将该背景频域子区域中的每个像素点的像素值与该背景频域子区域的平均像素值的差值的平方和，确定为该背景频域子区域的方差；2. The sum of the squares of the difference between the pixel value of each pixel in the background frequency-domain sub-region and the average pixel value of the background frequency-domain sub-region is determined as the variance of the background frequency-domain sub-region;
三、将该背景频域子区域的方差与该背景频域子区域中包括的像素点的个数的商，确定为该背景频域子区域的平均方差。3. Determine the quotient of the variance of the background frequency domain sub-area and the number of pixels included in the background frequency domain sub-area as the average variance of the background frequency domain sub-area.
S2042、针对每个目标频域子区域，基于该目标频域子区域中的最大像素值和平均方差，确定该目标频域子区域的质量；S2042. For each target frequency domain sub-region, determine the quality of the target frequency domain sub-region based on the maximum pixel value and average variance in the target frequency domain sub-region;
S2043、基于每个目标频域子区域的质量，将每个目标频域子区域的质量的加和与目标频域子区域的个数的商，确定为所述目标频域图的图像质量。S2043. Based on the quality of each target frequency-domain sub-region, determine the quotient of the sum of the qualities of each target frequency-domain sub-region and the number of target frequency-domain sub-regions as the image quality of the target frequency-domain image.
该步骤中，确定为目标频域图的图像质量的公式如下：In this step, the formula determined as the image quality of the target frequency domain map is as follows:
其中，y_MSEij为目标频域图y中第i行第j列的目标频域子区域的平均方差，
这里，背景频域图的图像质量的确定方法与目标频域图的图像质量的确定方法相同，背景频域图的图像质量的确定方法，包括：Here, the method for determining the image quality of the background frequency domain image is the same as the method for determining the image quality of the target frequency domain image, and the method for determining the image quality of the background frequency domain image includes:
(1)、针对每个背景频域子区域，基于该背景频域子区域中的最大像素值和平均方差，确定该背景频域子区域的质量；(1), for each background frequency domain sub-region, determine the quality of the background frequency domain sub-region based on the maximum pixel value and average variance in the background frequency domain sub-region;
(2)、基于每个背景频域子区域的质量，将每个背景频域子区域的质量的加和与背景频域子区域的个数的商，确定为所述背景频域图的图像质量。(2), based on the quality of each background frequency domain subregion, the quotient of the sum of the quality of each background frequency domain subregion and the number of background frequency domain subregions is determined as the image of the background frequency domain map quality.
该步骤中，确定为背景频域图的图像质量的公式如下：In this step, the formula for determining the image quality of the background frequency domain map is as follows:
其中，x_MSEij为背景频域图x中第i行第j列的背景频域子区域的平均方差，
S205、基于所述目标频域图的图像质量和所述背景频域图的图像质量，确定该视频序列的质量。S205. Determine the quality of the video sequence based on the image quality of the target frequency domain image and the image quality of the background frequency domain image.
需要说明的是，基于目标频域图的图像质量和背景频域图的图像质量，确定该视频序列的质量的步骤，包括：It should be noted that, based on the image quality of the target frequency domain image and the image quality of the background frequency domain image, the step of determining the quality of the video sequence includes:
S2051、基于所述目标频域图的图像质量，将所述目标频域图的图像质量和第一预设权重的乘积，确定为该视频序列的第一质量分量；S2051. Based on the image quality of the target frequency domain image, determine the product of the image quality of the target frequency domain image and a first preset weight as the first quality component of the video sequence;
S2052、基于所述背景频域图的图像质量，将所述背景频域图的图像质量和第二预设权重的乘积，确定为该视频序列的第二质量分量；S2052. Based on the image quality of the background frequency domain image, determine the product of the image quality of the background frequency domain image and a second preset weight as the second quality component of the video sequence;
该步骤中，第二预设权重是数字一与第一预设权重的差值。In this step, the second preset weight is the difference between the number one and the first preset weight.
S2053、将该视频序列的第一质量分量与该视频序列的第二质量分量的加和，确定为该视频序列的质量。S2053. Determine the sum of the first quality component of the video sequence and the second quality component of the video sequence as the quality of the video sequence.
该步骤中，第一预设权重是根据历史经验或实验数据预先设置的，针对每个视频序列，确定该视频序列的质量的公式如下：In this step, the first preset weight is preset according to historical experience or experimental data. For each video sequence, the formula for determining the quality of the video sequence is as follows:
PSNR＝αPSNRx+(1-α)PSNRy；PSNR = αPSNRx + (1-α)PSNRy ;
其中，α为权重系数(第二预设权重)，PSNRx为背景频域图的峰值信噪比(背景频域图的图像质量)，αPSNRx为该视频序列的第二质量分量，(1-α)为第一预设权重，PSNRy为目标频域图的峰值信噪比(目标频域图的图像质量)，(1-α)PSNRy为该视频序列的第一质量分量，PSNR为该视频序列的质量。Wherein, α is a weight coefficient (the second preset weight), PSNRx is the peak signal-to-noise ratio (image quality of the background frequency domain map) of the background frequency domain map, and αPSNRx is the second quality component of the video sequence, (1 -α) is the first preset weight, PSNRy is the peak signal-to-noise ratio of the target frequency domain map (the image quality of the target frequency domain map), (1-α)PSNRy is the first quality component of the video sequence, PSNR is the quality of the video sequence.
示例性的，α用于控制目标频域图和背景频域图对于最终质量评分的比重，可取α＝0.3；至此完成了自动化的造影图像质量评分，PSNR越大表示图像质量越高。Exemplarily, α is used to control the proportion of the target frequency domain map and the background frequency domain map to the final quality score, and α=0.3 is desirable; so far, the automatic contrast image quality score has been completed, and the larger the PSNR, the higher the image quality.
S104、按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。S104. Sort the multiple video sequences according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequences.
该步骤中，将每个视频序列按照质量进行排序，可以按照质量从高到低进行排序，本实施例无需进行精确度要求高、复杂的图像分割技术区分视频帧的前景和背景，利用频域空间能更好地反映噪声这一优势，将视频帧映射到频域空间中进行噪声分析，通过适合表达高低频信息的图像频域，进行高低频剥离，区分前景和背景，得到目标频域图和背景频域图，同时考虑到图像质量的全局性和局部性，分别计算背景和前景的噪声程度并进行加权，自动得到最终的图像质量评分。本实施例不再对图像的时域/空域进行分析，而是从频域角度出发，结合造影的不同帧，判别其噪声程度，以此来判断图像的质量，可以实现对大量血管造影的图像质量进行自动化评分，快速将质量最好的图像优先展示给医生。In this step, each video sequence is sorted according to the quality, which can be sorted according to the quality from high to low. This embodiment does not need to perform high-accuracy and complex image segmentation technology to distinguish the foreground and background of the video frame. The space can better reflect the advantage of noise. The video frame is mapped to the frequency domain space for noise analysis. Through the frequency domain of the image suitable for expressing high and low frequency information, the high and low frequencies are stripped, and the foreground and background are distinguished to obtain the target frequency domain map. And the background frequency domain map, taking into account the globality and locality of the image quality at the same time, calculate the noise level of the background and foreground respectively and weight them, and automatically get the final image quality score. This embodiment no longer analyzes the time domain/space domain of the image, but proceeds from the perspective of the frequency domain, combined with different frames of angiography, to determine the degree of noise, so as to judge the quality of the image, and can achieve a large number of angiographic images The quality is automatically scored, and the best quality images are quickly displayed to doctors first.
本申请实施例提供的一种视频序列的排序方法，所述排序方法包括：获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；基于所述前景帧和所述背景帧，确定该视频序列的质量；按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。A method for sorting video sequences provided in an embodiment of the present application, the sorting method includes: acquiring multiple video frames of each video sequence in multiple video sequences shot for the analysis target; for each video sequence, in the In a plurality of video frames of the video sequence, a foreground frame with the analysis target and a background frame without the analysis target are determined; based on the foreground frame and the background frame, the quality of the video sequence is determined; according to the sorting the plurality of video sequences according to the quality of each video sequence, so as to analyze the analysis target according to the sorted video sequences.
这样，采用本申请提供的技术方案能够通过每个视频序列中的前景帧和背景帧，确定出每个视频序列的质量，根据每个视频序列的质量对多个视频序列进行排序，可以按照排序后的视频序列优先对质量较好的视频序列中的分析目标进行分析，提高了分析视频序列的效率，减轻了医生负担。In this way, the technical solution provided by this application can determine the quality of each video sequence through the foreground frame and background frame in each video sequence, and sort multiple video sequences according to the quality of each video sequence. The final video sequence first analyzes the analysis target in the video sequence with better quality, which improves the efficiency of analyzing the video sequence and reduces the burden on doctors.
基于同一申请构思，本申请实施例中还提供了与上述实施例提供一种视频序列的排序方法对应的一种视频序列的排序装置，由于本申请实施例中的装置解决问题的原理与本申请上述实施例一种视频序列的排序方法相似，因此装置的实施可以参见方法的实施，重复之处不再赘述。Based on the same application idea, the embodiment of the present application also provides a video sequence sorting device corresponding to the video sequence sorting method provided in the above embodiment, because the problem-solving principle of the device in the embodiment of the present application is the same The method for sorting a video sequence in the above-mentioned embodiment is similar, so the implementation of the device can refer to the implementation of the method, and repeated descriptions will not be repeated.
请参阅图5，图5为本申请实施例所提供的一种视频序列的排序装置的结构图。如图5中所示，所述排序装置510包括：Please refer to FIG. 5 . FIG. 5 is a structural diagram of an apparatus for sorting video sequences provided by an embodiment of the present application. As shown in Figure 5, the
获取模块511，用于获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；An
第一确定模块512，用于针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；The first determining
第二确定模块513，用于基于所述前景帧和所述背景帧，确定该视频序列的质量；The
排序模块514，用于按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。The
可选的，所述第二确定模块513在用于基于所述前景帧和所述背景帧，确定该视频序列的质量时，所述第二确定模块513具体用于：Optionally, when the second determining
基于所述前景帧，将所述前景帧经过频域转换后，得到前景频域图，并基于所述背景帧，将所述背景帧经过频域转换后，得到背景频域图；Based on the foreground frame, after the foreground frame is subjected to frequency domain conversion, a foreground frequency domain map is obtained, and based on the background frame, after the background frame is subjected to frequency domain conversion, a background frequency domain map is obtained;
基于所述前景频域图和所述背景频域图，得到仅具有所述分析目标的目标频域图；Based on the foreground frequency domain diagram and the background frequency domain diagram, a target frequency domain diagram having only the analysis target is obtained;
将所述目标频域图根据预设去除区域分割为多个目标频域子区域，并将所述背景频域图根据预设去除区域分割为多个背景频域子区域；The target frequency domain image is divided into a plurality of target frequency domain sub-areas according to the preset removal area, and the background frequency domain image is divided into a plurality of background frequency domain sub-areas according to the preset removal area;
根据所述多个目标频域子区域，确定所述目标频域图的图像质量，并根据所述多个背景频域子区域，确定所述背景频域图的图像质量；determining the image quality of the target frequency domain image according to the plurality of target frequency domain subregions, and determining the image quality of the background frequency domain image according to the plurality of background frequency domain subregions;
基于所述目标频域图的图像质量和所述背景频域图的图像质量，确定该视频序列的质量。The quality of the video sequence is determined based on the image quality of the target frequency domain map and the image quality of the background frequency domain map.
可选的，所述第一确定模块512在用于在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧时，所述第一确定模块512具体用于：Optionally, when the first determining
在该视频序列的多个视频帧中，针对每个视频帧，获取该视频帧的每个像素点对应的灰度值和该视频帧中包括的像素点的个数；In a plurality of video frames of the video sequence, for each video frame, the gray value corresponding to each pixel of the video frame and the number of pixels included in the video frame are obtained;
将该视频帧的每个像素点对应的灰度值相加，得到该视频帧对应的灰度值总和；Adding the gray value corresponding to each pixel of the video frame to obtain the sum of the gray value corresponding to the video frame;
将该视频帧对应的灰度值总和与该视频帧中包括的像素点的个数的商，确定为该视频帧对应的灰度均值；The quotient of the grayscale value sum corresponding to the video frame and the number of pixels included in the video frame is determined as the grayscale mean value corresponding to the video frame;
基于该视频序列的所述多个视频帧中的每个视频帧对应的灰度均值，将数值最大的灰度均值对应的视频帧确定为不具有分析目标的背景帧，并将数值最小的灰度均值对应的视频帧确定为具有分析目标的前景帧。Based on the grayscale mean value corresponding to each video frame in the plurality of video frames of the video sequence, the video frame corresponding to the grayscale mean value with the largest value is determined as a background frame without an analysis target, and the grayscale value with the smallest value The video frame corresponding to the degree mean value is determined as the foreground frame with the analysis target.
可选的，所述第二确定模块513在用于基于所述前景频域图和所述背景频域图，得到仅具有所述分析目标的目标频域图时，所述第二确定模块513具体用于：Optionally, when the
基于所述前景频域图，获取所述前景频域图中每个像素点的像素值；Based on the foreground frequency domain image, obtain the pixel value of each pixel in the foreground frequency domain image;
基于所述背景频域图，获取所述背景频域图中每个像素点的像素值；Based on the background frequency domain image, obtain the pixel value of each pixel in the background frequency domain image;
将所述前景频域图中每个像素点的像素值与所述背景频域图中对应位置的像素点的像素值相减，得到仅具有所述分析目标的目标频域图。Subtracting the pixel value of each pixel in the foreground frequency domain image from the pixel value of a corresponding pixel in the background frequency domain image to obtain a target frequency domain image with only the analysis target.
可选的，所述第二确定模块513在用于根据所述多个目标频域子区域，确定所述目标频域图的图像质量时，所述第二确定模块513具体用于：Optionally, when the second determining
根据所述多个目标频域子区域，获取预先确定的每个目标频域子区域的最大像素值和每个目标频域子区域的平均方差；Acquiring a predetermined maximum pixel value of each target frequency domain subregion and an average variance of each target frequency domain subregion according to the plurality of target frequency domain subregions;
针对每个目标频域子区域，基于该目标频域子区域中的最大像素值和平均方差，确定该目标频域子区域的质量；For each target frequency domain sub-region, based on the maximum pixel value and average variance in the target frequency domain sub-region, determine the quality of the target frequency domain sub-region;
基于每个目标频域子区域的质量，将每个目标频域子区域的质量的加和与目标频域子区域的个数的商，确定为所述目标频域图的图像质量。Based on the quality of each target frequency domain sub-region, the quotient of the sum of the qualities of each target frequency domain sub-region and the number of target frequency domain sub-regions is determined as the image quality of the target frequency domain image.
可选的，所述第二确定模块513还用于：Optionally, the second determining
获取所述多个目标频域子区域中每个目标频域子区域中的每个像素点的像素值；Acquiring the pixel value of each pixel in each target frequency domain sub-area among the plurality of target frequency domain sub-areas;
针对每个目标频域子区域，在该目标频域子区域中所有像素点的每个像素点的像素值中，将数值最大的像素值确定为该目标频域子区域中的最大像素值。For each target frequency domain sub-region, among the pixel values of all pixels in the target frequency domain sub-region, the pixel value with the largest value is determined as the maximum pixel value in the target frequency-domain sub-region.
可选的，所述第二确定模块513在用于基于所述目标频域图的图像质量和所述背景频域图的图像质量，确定该视频序列的质量时，所述第二确定模块513具体用于：Optionally, when the second determining
基于所述目标频域图的图像质量，将所述目标频域图的图像质量和第一预设权重的乘积，确定为该视频序列的第一质量分量；Based on the image quality of the target frequency domain image, determining the product of the image quality of the target frequency domain image and a first preset weight as the first quality component of the video sequence;
基于所述背景频域图的图像质量，将所述背景频域图的图像质量和第二预设权重的乘积，确定为该视频序列的第二质量分量；其中，所述第二预设权重是数字一与所述第一预设权重的差值；Based on the image quality of the background frequency domain image, the product of the image quality of the background frequency domain image and a second preset weight is determined as the second quality component of the video sequence; wherein, the second preset weight is the difference between number one and the first preset weight;
将该视频序列的第一质量分量与该视频序列的第二质量分量的加和，确定为该视频序列的质量。The sum of the first quality component of the video sequence and the second quality component of the video sequence is determined as the quality of the video sequence.
本申请实施例提供的一种视频序列的排序装置，所述排序装置包括：获取模块，用于获取针对分析目标所拍摄的多个视频序列中每个视频序列的多个视频帧；第一确定模块，用于针对每个视频序列，在该视频序列的多个视频帧中，确定出具有所述分析目标的前景帧和不具有所述分析目标的背景帧；第二确定模块，用于基于所述前景帧和所述背景帧，确定该视频序列的质量；排序模块，用于按照所述每个视频序列的质量将所述多个视频序列进行排序，以按照所述排序后的视频序列对所述分析目标进行分析。An apparatus for sorting video sequences provided in an embodiment of the present application, the sorting apparatus includes: an acquisition module configured to acquire multiple video frames of each video sequence in multiple video sequences shot for the analysis target; the first determination A module, for each video sequence, in a plurality of video frames of the video sequence, determine a foreground frame with the analysis target and a background frame without the analysis target; a second determination module, for based on The foreground frame and the background frame determine the quality of the video sequence; the sorting module is configured to sort the plurality of video sequences according to the quality of each video sequence, so as to sort the sorted video sequence Analyze the analysis target.
这样，采用本申请提供的技术方案能够通过每个视频序列中的前景帧和背景帧，确定出每个视频序列的质量，根据每个视频序列的质量对多个视频序列进行排序，可以按照排序后的视频序列优先对质量较好的视频序列中的分析目标进行分析，提高了分析视频序列的效率，减轻了医生负担。In this way, the technical solution provided by this application can determine the quality of each video sequence through the foreground frame and background frame in each video sequence, and sort multiple video sequences according to the quality of each video sequence. The final video sequence first analyzes the analysis target in the video sequence with better quality, which improves the efficiency of analyzing the video sequence and reduces the burden on doctors.
请参阅图6，图6为本申请实施例所提供的一种电子设备的结构示意图。如图6中所示，所述电子设备600包括处理器610、存储器620和总线630。Please refer to FIG. 6 . FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As shown in FIG. 6 , the
所述存储器620存储有所述处理器610可执行的机器可读指令，当电子设备600运行时，所述处理器610与所述存储器620之间通过总线630通信，所述机器可读指令被所述处理器610执行时，可以执行如上述图1以及图2所示方法实施例中的视频序列的排序方法的步骤，具体实现方式可参见方法实施例，在此不再赘述。The
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时可以执行如上述图1以及图2所示方法实施例中的视频序列的排序方法的步骤，具体实现方式可参见方法实施例，在此不再赘述。The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, it can execute the method in the above-mentioned embodiments shown in FIG. 1 and FIG. 2 . For the steps of the video sequence sorting method, the specific implementation may refer to the method embodiments, and will not be repeated here.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-OnlyMemory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, and other media that can store program codes.
最后应说明的是：以上所述实施例，仅为本申请的具体实施方式，用以说明本申请的技术方案，而非对其限制，本申请的保护范围并不局限于此，尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本申请实施例技术方案的精神和范围，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。Finally, it should be noted that: the above-described embodiments are only specific implementations of the application, used to illustrate the technical solutions of the application, rather than limiting it, and the scope of protection of the application is not limited thereto, although referring to the aforementioned The embodiment has described this application in detail, and those of ordinary skill in the art should understand that any person familiar with this technical field can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed in this application Changes can be easily imagined, or equivalent replacements can be made to some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be covered by this application. within the scope of protection. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211122318.8ACN115482487A (en) | 2022-09-15 | 2022-09-15 | A video sequence sorting method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211122318.8ACN115482487A (en) | 2022-09-15 | 2022-09-15 | A video sequence sorting method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115482487Atrue CN115482487A (en) | 2022-12-16 |
Family
ID=84392888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211122318.8APendingCN115482487A (en) | 2022-09-15 | 2022-09-15 | A video sequence sorting method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115482487A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118840641A (en)* | 2024-09-23 | 2024-10-25 | 之江实验室 | Multi-band image fusion method, device, storage medium and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102014240A (en)* | 2010-12-01 | 2011-04-13 | 深圳市蓝韵实业有限公司 | Real-time medical video image denoising method |
| CN105915892A (en)* | 2016-05-06 | 2016-08-31 | 乐视控股（北京）有限公司 | Panoramic video quality determination method and system |
| US20190130554A1 (en)* | 2017-10-27 | 2019-05-02 | Alex Rothberg | Quality indicators for collection of and automated measurement on ultrasound images |
| CN111134686A (en)* | 2019-12-19 | 2020-05-12 | 南京酷派软件技术有限公司 | Human body disease determination method and device, storage medium and terminal |
| CN113794815A (en)* | 2021-08-25 | 2021-12-14 | 中科云谷科技有限公司 | Method, device and controller for extracting video key frame |
| CN113891069A (en)* | 2021-10-21 | 2022-01-04 | 咪咕文化科技有限公司 | Video quality assessment method, device and equipment |
- 2022
- 2022-09-15CNCN202211122318.8Apatent/CN115482487A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102014240A (en)* | 2010-12-01 | 2011-04-13 | 深圳市蓝韵实业有限公司 | Real-time medical video image denoising method |
| CN105915892A (en)* | 2016-05-06 | 2016-08-31 | 乐视控股（北京）有限公司 | Panoramic video quality determination method and system |
| US20190130554A1 (en)* | 2017-10-27 | 2019-05-02 | Alex Rothberg | Quality indicators for collection of and automated measurement on ultrasound images |
| CN111134686A (en)* | 2019-12-19 | 2020-05-12 | 南京酷派软件技术有限公司 | Human body disease determination method and device, storage medium and terminal |
| CN113794815A (en)* | 2021-08-25 | 2021-12-14 | 中科云谷科技有限公司 | Method, device and controller for extracting video key frame |
| CN113891069A (en)* | 2021-10-21 | 2022-01-04 | 咪咕文化科技有限公司 | Video quality assessment method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| MIRKO AGARLA ET AL.: "An Efficient method for no-reference video quality assessment", 《J.IMAGING》, 13 March 2022 (2022-03-13)* |
| 宋巍;刘诗梦;黄冬梅;王文娟;王建;: "适用小样本的无参考水下视频质量评价方法", 中国图象图形学报, no. 09, 16 September 2020 (2020-09-16)* |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118840641A (en)* | 2024-09-23 | 2024-10-25 | 之江实验室 | Multi-band image fusion method, device, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230113721A1 (en) | Functional measurements of vessels using a temporal feature | |
| US10867375B2 (en) | Forecasting images for image processing | |
| US11468570B2 (en) | Method and system for acquiring status of strain and stress of a vessel wall | |
| KR101902883B1 (en) | A method for analyzing plaque in a computed tomography image and an apparatus thereof | |
| CA3095408A1 (en) | Systems and methods for automated detection and segmentation of vertebral centrum(s) in 3d images | |
| CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
| CN115511995A (en) | Angiography image processing method and system | |
| TWI788629B (en) | Image processing method, device and system, electronic apparatus, and computer readable storage medium | |
| US10002428B2 (en) | Method and system for identifying bleeding | |
| CN113940698B (en) | Ultrasound-based processing method, ultrasound device and computer storage medium | |
| CN115482487A (en) | A video sequence sorting method, device, electronic equipment and storage medium | |
| CN115147360B (en) | Plaque segmentation method and device, electronic equipment and readable storage medium | |
| US20220138936A1 (en) | Systems and methods for calcium-free computed tomography angiography | |
| US8848998B1 (en) | Automated method for contrast media arrival detection for dynamic contrast enhanced MRI | |
| CN114693641B (en) | Blood vessel image extraction method, device, equipment and storage medium | |
| CN117523014A (en) | Endoscopic SS-OCT image layering method, device and storage medium | |
| CN114913133B (en) | Lung medical image processing method and device, storage medium and computer equipment | |
| JP2008514317A (en) | Vascular structure segmentation system and method | |
| CN117422874A (en) | Abdominal fat segmentation method and device and computer equipment | |
| EP4285825A1 (en) | Improving the image quality of medical images | |
| CN117059263A (en) | Method and system for determining occurrence probability of pulmonary artery high pressure based on double-view chest radiography | |
| CN112184632B (en) | Image processing method, device and computer storage medium | |
| CN115222665A (en) | Plaque detection method and device, electronic equipment and readable storage medium | |
| CN113989171A (en) | Subtraction map generation method and device, storage medium and computer equipment | |
| CN113989157B (en) | Image denoising method, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |