CN112084963B - A monitoring and early warning method, system and storage medium - Google Patents
A monitoring and early warning method, system and storage mediumDownload PDFInfo
- Publication number
- CN112084963B CN112084963BCN202010955424.9ACN202010955424ACN112084963BCN 112084963 BCN112084963 BCN 112084963BCN 202010955424 ACN202010955424 ACN 202010955424ACN 112084963 BCN112084963 BCN 112084963B
- Authority
- CN
- China
- Prior art keywords
- abnormal event
- early warning
- module
- video stream
- monitoring
- 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.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
- 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
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及视频处理技术领域，特别涉及一种监控预警方法、系统及存储介质。The invention relates to the technical field of video processing, in particular to a monitoring and early warning method, system and storage medium.
背景技术Background technique
监控系统是安防系统中应用最多的系统之一，传统的监控系统需要监控员在监控室中通过多个独立的监控窗口实现对复杂场景中的不同监控点的异常情况进行实时的监控。The monitoring system is one of the most widely used systems in the security system. The traditional monitoring system requires the monitor to monitor the abnormal conditions of different monitoring points in complex scenes in real time through multiple independent monitoring windows in the monitoring room.
此种监控方式中监控画面彼此相互孤立不具有关联性，且由于摄像头监控的视角有限，无法得到完整全面的图像画面信息及视域内清晰的视觉特征信息，一旦监控区域内出现异常事件，则监控人员无法通过零散的视频画面对异常事件当前呈现的实际状况或视觉特征进行有效识别、对发生异常事件的实际地理位置进行有效的定位以及对异常事件视频进行的快速回溯，大幅地影响专业人员对异常事件的处理效率及对处理该异常事件的人员的安排和调度，进而会引发严重的后果。In this monitoring method, the monitoring screens are isolated from each other and have no correlation, and due to the limited viewing angle of the camera monitoring, it is impossible to obtain complete and comprehensive image information and clear visual feature information in the field of view. Once an abnormal event occurs in the monitoring area, the monitoring Personnel cannot effectively identify the actual situation or visual features currently presented by the abnormal event through scattered video images, effectively locate the actual geographic location where the abnormal event occurred, and quickly trace back the video of the abnormal event, which greatly affects the professional understanding of the abnormal event. The processing efficiency of abnormal events and the arrangement and scheduling of personnel handling the abnormal events will lead to serious consequences.
上述公开于该背景技术部分的信息仅仅旨在增加对本发明的总体背景的理解，而不应当被视为承认或以任何形式暗示该信息构成已为本领域一般技术人员所公知的现有技术。The above information disclosed in this Background section is only intended to increase the understanding of the general background of the present invention, and should not be considered as an acknowledgment or any form of suggestion that the information constitutes the prior art that is already known to those skilled in the art.
发明内容Contents of the invention
为解决背景技术中的技术问题，本发明提供一种监控预警方法、系统及存储介质。In order to solve the technical problems in the background technology, the present invention provides a monitoring and early warning method, system and storage medium.
根据本发明提供的一种监控预警方法，其特征在于，包含下列步骤：According to a monitoring and early warning method provided by the present invention, it is characterized in that it comprises the following steps:
S1：获取视频流，对视频流进行预处理；S1: Obtain the video stream and preprocess the video stream;
S2：获取经预处理后的视频流的目标特征；S2: Obtain the target features of the preprocessed video stream;
S3：构建异常事件识别判据；S3: Construct abnormal event identification criteria;
S4：依据异常事件识别判据对视频流中是否出现异常事件进行识别；S4: Identify whether an abnormal event occurs in the video stream according to the abnormal event identification criterion;
S5：当检测到异常事件的发生，对异常事件进行响应。S5: When an abnormal event is detected, respond to the abnormal event.
优选地，上述技术方案中，S1中对视频流进行预处理具体包括：Preferably, in the above technical solution, the preprocessing of the video stream in S1 specifically includes:
S11：对视频流进行解码并提取关键帧；S11: Decoding the video stream and extracting key frames;
S12：对关键帧进行预处理；S12: Preprocessing the key frame;
S13：对经过预处理的关键帧进行图像优化。S13: Perform image optimization on the preprocessed key frames.
优选地，上述技术方案中，S2的具体步骤包含：Preferably, in the above technical solution, the specific steps of S2 include:
S21：计算视频流中每一帧目标特征的兴趣点特征坐标集；S21: Calculate the point-of-interest feature coordinate set of each frame target feature in the video stream;
S22：对兴趣点特征坐标集进行计算，得到目标特征矢量集。S22: Calculate the feature coordinate set of the interest point to obtain the target feature vector set.
优选地，上述技术方案中，步骤S3还包含：Preferably, in the above technical solution, step S3 also includes:
S31：结合目标特征矢量集，计算出目标特征参数；S31: Combining with the target feature vector set, calculate the target feature parameters;
S32：将目标特征参数输入到异常事件识别模型中进行训练。S32: Input the target feature parameters into the abnormal event recognition model for training.
优选地，上述技术方案中，目标特征参数包括有：运动矢量动能、运动方向信息熵、相邻目标信息量。Preferably, in the above technical solution, the target feature parameters include: motion vector kinetic energy, motion direction information entropy, and adjacent target information volume.
优选地，上述技术方案中，步骤S5还包括有：在检测到异常事件后，自动对异常事件进行预警及记录。Preferably, in the above technical solution, step S5 further includes: after the abnormal event is detected, automatically warn and record the abnormal event.
优选地，上述技术方案中，所述步骤S5还包括，在检测到异常事件后，对所述异常事件发生方位进行定位。Preferably, in the above technical solution, the step S5 further includes, after detecting the abnormal event, locating the location where the abnormal event occurs.
根据本发明提供的一种监控预警系统，包括采集及预处理模块、异常事件识别模块、预警及信息回溯模块、显示模块及通信模块；A monitoring and early warning system provided by the present invention includes a collection and preprocessing module, an abnormal event identification module, an early warning and information backtracking module, a display module and a communication module;
采集及预处理模块，用获取及存储视频流，以及对视频流进行预处理；The acquisition and preprocessing module is used to acquire and store video streams, and preprocess video streams;
异常事件识别模块，用于对经预处理的视频流中是否出现异常事件进行判别；An abnormal event identification module is used to judge whether an abnormal event occurs in the preprocessed video stream;
预警及信息回溯模块，用于在异常事件发生时，启动预警机制，以及将异常事件信息回传至监控中心；The early warning and information backtracking module is used to start the early warning mechanism when an abnormal event occurs, and return the abnormal event information to the monitoring center;
显示模块，用于对视频流采用网格化排布或者单点排布中任一种显示方法进行显示；The display module is used to display the video stream by using any display method in grid arrangement or single-point arrangement;
通信模块，用于各模块间的通信连接。The communication module is used for communication connection between modules.
一种计算机存储介质，计算机存储介质存储有一个或者多个程序，一个或者多个程序可被一个或者多个处理器执行，以实现上述监控预警方法。A computer storage medium, where one or more programs are stored in the computer storage medium, and the one or more programs can be executed by one or more processors, so as to realize the above monitoring and early warning method.
与现有技术相比，本发明具有如下有益效果：本发明提供的一种监控预警方法、系统及存储介质，系统能够自行依据其内设置的异常事件识别算法对监控区域内是否发生异常事件进行识别，并将异常事件视频图像进行截取保存以及自动获取异常事件发生的地理位置坐标，将上述信息回传至监控中心，工作人员可依据回传的信息启动应急预案。Compared with the prior art, the present invention has the following beneficial effects: a monitoring and early warning method, system and storage medium provided by the present invention, the system can automatically check whether an abnormal event occurs in the monitoring area according to the abnormal event identification algorithm set in it. Identify, intercept and save the video images of abnormal events and automatically obtain the geographic location coordinates of the abnormal events, and send the above information back to the monitoring center, and the staff can start the emergency plan based on the returned information.
附图说明Description of drawings
图1是本发明一种监控预警方法的流程图；Fig. 1 is the flowchart of a kind of monitoring early warning method of the present invention;
图2是本发明一实施例对视频流进行预处理的方法流程图；Fig. 2 is a flow chart of a method for preprocessing a video stream according to an embodiment of the present invention;
图3是本发明一实施例对异常事件判断识别的方法流程图；Fig. 3 is a flowchart of a method for judging and identifying abnormal events according to an embodiment of the present invention;
图4是本发明一种监控预警系统的原理框图；Fig. 4 is a functional block diagram of a monitoring and early warning system of the present invention;
图5是本发明一种监控预警系统的另一种原理框图。Fig. 5 is another functional block diagram of a monitoring and early warning system of the present invention.
100-采集及预处理模块，200-显示模块，300-异常事件识别模快，310-异常事件判别模块，320-异常信息定位模块，400-预警及信息回溯模块，500-通信模块。100-acquisition and preprocessing module, 200-display module, 300-abnormal event identification module, 310-abnormal event discrimination module, 320-abnormal information positioning module, 400-early warning and information backtracking module, 500-communication module.
具体实施方式Detailed ways
下面结合附图，对本发明的具体实施方式进行详细描述，但应当理解本发明的保护范围并不受具体实施方式的限制。The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific embodiments.
除非另有其它明确表示，否则在整个说明书和权利要求书中，术语“包括”或其变换如“包含”或“包括有”等等将被理解为包括所陈述的元件或组成部分，而并未排除其它元件或其它组成部分。Unless expressly stated otherwise, throughout the specification and claims, the term "comprise" or variations thereof such as "includes" or "includes" and the like will be understood to include the stated elements or constituents, and not Other elements or other components are not excluded.
实施例1Example 1
根据本发明提供的一种监控预警方法，包括下列步骤：A monitoring and early warning method provided according to the present invention comprises the following steps:
步骤S1：获取视频流，对视频流进行预处理；Step S1: Obtain a video stream, and preprocess the video stream;
获取视频流包含一切可以获得视频流的方法及手段，对视频流进行预处理具体方法为：Obtaining video streams includes all methods and means to obtain video streams. The specific methods for preprocessing video streams are:
S11对视频流进行解码及提取关键帧；S11 decodes the video stream and extracts key frames;
将视频流解析成视频帧图像，筛选有运动目标的视频帧图像并将其标注为关键帧；Parse the video stream into video frame images, filter video frame images with moving objects and mark them as key frames;
S12对关键帧进行预处理；S12 preprocesses the key frame;
分别利用中值滤波和均值滤波的图像处理方式针对关键帧图像中的椒盐噪声以及高斯噪声进行降噪处理；The salt and pepper noise and Gaussian noise in the key frame image are denoised by using the image processing methods of median filter and mean filter respectively;
S13对经过预处理的关键帧进行图像优化；S13 performs image optimization on the preprocessed key frame;
利用基于EM算法的高斯混合模型对降噪后的关键帧突显进行前景检测，并利用RCB颜色模型进行阴影去除；利用二值形态学算法进行图像优化，即对初步得到的图像进行去噪操作即分别进行腐蚀、膨胀、开运算和闭运算，最终得到二值化关键帧前景图即运动目标的二值图像。Use the Gaussian mixture model based on the EM algorithm to perform foreground detection on the highlighted key frame after noise reduction, and use the RCB color model to remove the shadow; use the binary morphology algorithm to optimize the image, that is, to perform denoising operation on the preliminary image. Carry out erosion, dilation, opening operation and closing operation respectively, and finally obtain the binary image of the foreground image of the binarized key frame, that is, the moving target.
需要说明的是进行视频流采集时，需要实时回传采集模块的属性信息，即采集模块对应的地理位置信息(ID)以及角度偏转信息等(即球幕相机ID对应的属性信息至少包括摄像头GPS位置、滚动角、倾斜角和偏航角)，以便后续可以通过GPS定位将采集模块定位到监控中的对应该位置，并回传对应地理位置信息。It should be noted that when collecting video streams, it is necessary to return the attribute information of the acquisition module in real time, that is, the geographic location information (ID) and angle deflection information corresponding to the acquisition module (that is, the attribute information corresponding to the dome camera ID includes at least the camera GPS Position, roll angle, tilt angle and yaw angle), so that the acquisition module can be positioned to the corresponding position in the monitoring through GPS positioning, and the corresponding geographic location information can be returned.
步骤S2：获取经预处理后的视频流的目标特征；具体方法为：Step S2: Obtain the target features of the preprocessed video stream; the specific method is:
S21：计算所述视频流中每一帧所述目标特征的兴趣点特征坐标集；S21: Calculate the feature coordinate set of the point of interest of the target feature in each frame of the video stream;
构建关键帧掩膜模板，通过结合特征提取算法计算每一帧以得到目标特征的兴趣点特征坐标集，即基于S1中得到的运动目标二值图像作为二值化掩膜模板，利用特征提取算法实现对每一帧视频图像的兴趣点特征的检测及提取，并得到目标特征即运动目标的兴趣点特征坐标集。Construct the key frame mask template, calculate each frame by combining the feature extraction algorithm to obtain the feature coordinate set of the point of interest of the target feature, that is, based on the binary image of the moving target obtained in S1 as the binary mask template, use the feature extraction algorithm Realize the detection and extraction of the interest point features of each frame of video image, and obtain the target feature, that is, the interest point feature coordinate set of the moving target.
S22：对兴趣点特征坐标集进行计算，构建目标特征矢量集S22: Calculate the feature coordinate set of the point of interest, and construct the target feature vector set
利用LK光流法，对运动目标的兴趣点特征坐标集中的运动目标兴趣点特征进行光流计算，得到运动目标特征的光流矢量集，作为后续构建异常事件识别判据的计算基础。Using the LK optical flow method, the optical flow calculation is performed on the interest point features of the moving target in the feature coordinate set of the moving target points of interest, and the optical flow vector set of the moving target features is obtained, which is used as the calculation basis for the subsequent construction of abnormal event recognition criteria.
需要说明的是：本发明中的兴趣点特征即为角点特征；本发明中特征提取算法优选为Shi-Tomasi算法；本发明中光流矢量即为运动目标的运动矢量。It should be noted that: the interest point feature in the present invention is the corner point feature; the feature extraction algorithm in the present invention is preferably the Shi-Tomasi algorithm; the optical flow vector in the present invention is the motion vector of the moving object.
步骤S3：构建异常事件识别判据；具体方法为：Step S3: Construct abnormal event identification criteria; the specific method is:
S31：结合目标特征矢量集，计算出目标特征参数；S31: Combining with the target feature vector set, calculate the target feature parameters;
利用多源动态信息融合算法，结合运动目标的运动矢量集，计算出运动目标的特征参数；以此实现视频流中异常事件识别判据的构建。Using the multi-source dynamic information fusion algorithm, combined with the motion vector set of the moving object, the characteristic parameters of the moving object are calculated; in this way, the construction of the abnormal event identification criterion in the video stream is realized.
本发明中通过利用运动矢量动能即光流矢量动能、运动方向信息熵以及相邻视频帧互信息量三个特征构建异常事件识别判据，具体步骤如下：In the present invention, the abnormal event identification criterion is constructed by using three characteristics of the kinetic energy of the motion vector, that is, the kinetic energy of the optical flow vector, the information entropy of the motion direction, and the mutual information of adjacent video frames. The specific steps are as follows:
S311计算运动目标的运动矢量的平均动能，作为视频图像中动态目标的运动剧烈程度的评判指标；S311 calculates the average kinetic energy of the motion vector of the moving object as an index for judging the intensity of motion of the moving object in the video image;
S312计算运动目标的运动方向信息熵；S312 calculates the moving direction information entropy of the moving target;
利用公式(1)计算运动目标的运动方向信息熵，作为视频中前景动态目标的运动方向的分散性，即混乱程度。Use the formula (1) to calculate the moving direction information entropy of the moving target, as the dispersion of the moving direction of the foreground dynamic target in the video, that is, the degree of confusion.
其中，p(xi)为事件发生的概率分布p(xi)＝w(xi)/m，0＜i＜n，m是每帧图像中运动矢量总数。w(xi)＝{qi，0＜i＜n}为某帧图像的运动矢量方向直方图，其中n代表直方条数量，qi表示第i条对应某一方向运动矢量数量。Wherein, p(xi ) is the probability distribution of event occurrence p(xi )=w(xi )/m, 0<i<n, and m is the total number of motion vectors in each frame of image. w(xi )={qi , 0<i<n} is the motion vector direction histogram of a certain frame image, where n represents the number of histogram bars, and qi represents the number of motion vectors corresponding to the i-th bar in a certain direction.
S313计算相邻视频帧信息量；S313 calculates the amount of information of adjacent video frames;
利用公式(2)计算相邻视频帧信息量，作为视频图像中运动模式突变特征。Use the formula (2) to calculate the information amount of adjacent video frames, and use it as the abrupt change feature of the motion pattern in the video image.
需要说明的是，互信息量的提出依据的是信息论中的交互信息相似性准则，可以用来描述两幅图像运动矢量场之间的相似程度。It should be noted that the mutual information is proposed based on the mutual information similarity criterion in information theory, which can be used to describe the similarity between the motion vector fields of two images.
S32：将目标特征参数输入到异常事件识别模型中进行训练；S32: Input the target feature parameters into the abnormal event recognition model for training;
利用步骤S311、S312、S313分别计算正常视频帧以及异常视频帧对应的运动目标运动特征参数即运动目标的平均运动矢量动能、运动方向信息熵以及相邻视频帧互信息量，将计算的到的正常运动特征参数及异常特征参数作为输入，传输至异常事件识别模型中进行训练，用于针对视频流中异常事件的分类及识别。Utilize steps S311, S312, S313 to calculate the normal video frame and the moving target motion characteristic parameter corresponding to the abnormal video frame, namely the average motion vector kinetic energy, motion direction information entropy and adjacent video frame mutual information of the moving target, and the calculated The normal motion feature parameters and abnormal feature parameters are used as input, and are transmitted to the abnormal event recognition model for training, which is used for classification and identification of abnormal events in the video stream.
需要说明的是，本发明中利用InceptionV4网络对异常事件识别模型进行训练。It should be noted that in the present invention, the InceptionV4 network is used to train the abnormal event recognition model.
S4：根据异常事件识别判据对视频流中是否出现异常事件进行识别。S4: Identify whether an abnormal event occurs in the video stream according to the abnormal event identification criterion.
需要说明的是，平均运动矢量动能用于表征视频中动态目标运动的剧烈程度，运动方向信息熵用于表征视频中动态目标运动方向的分散性，即混乱程度；相邻视频帧互信息量用于表征视频图像中运动模式突变特征。It should be noted that the average motion vector kinetic energy is used to characterize the intensity of the dynamic target motion in the video, and the motion direction information entropy is used to characterize the dispersion of the dynamic target motion direction in the video, that is, the degree of confusion; the mutual information of adjacent video frames is represented by It is used to characterize the mutation characteristics of motion patterns in video images.
S5，当检测到异常事件的发生，对异常事件进行响应。S5, responding to the abnormal event when the occurrence of the abnormal event is detected.
在检测到异常事件发生后，可进一步启动预警以及纪录异常事件的发生信息，例如将异常事件发生信号回传至监控中心，由工作人员同步启动应急预案。After an abnormal event is detected, an early warning can be further activated and information on the occurrence of the abnormal event can be recorded, for example, the signal of the abnormal event can be sent back to the monitoring center, and the emergency plan can be activated by the staff simultaneously.
此外，通过上述异常事件识别算法对视频内容进行监控时，一旦检测到异常事件的发生可自动截取异常事件视频图像显示到监控屏幕上，以及将自动获取的异常事件发生地的地理位置信息、摄像头角度信息、时间信息等各类参数回传至监控中心，并根据异常事件发生的时间，自动保存事件发生前及发生后一段时间的视频影像，完整记录整个异常事件发生过程，更进一步的还可以将异常事件发生的图像进行放大。In addition, when monitoring video content through the above-mentioned abnormal event recognition algorithm, once the occurrence of an abnormal event is detected, the video image of the abnormal event can be automatically intercepted and displayed on the monitoring screen, and the geographical location information of the place where the abnormal event occurred, the camera Various parameters such as angle information and time information are sent back to the monitoring center, and according to the time when the abnormal event occurs, the video images before and after the event are automatically saved, and the entire process of the abnormal event is fully recorded. Zoom in on images of abnormal events occurring.
实施例2Example 2
本实施例提供的一种监控预警系统，本系统需要应用实施例1中所提及的方法及算法，在本实施例中不再论述，包括采集及预处理模块100、显示模块200、异常事件识别模块300、预警及信息回溯模块400、通信模块500；A monitoring and early warning system provided in this embodiment. This system needs to apply the method and algorithm mentioned in Embodiment 1, which will not be discussed in this embodiment. It includes a collection and
采集及预处理模块100，用于获取及存储视频流，以及对视频流进行预处理；Acquisition and
异常事件识别模块300，用于对视频流中是否出现异常事件进行判别；An abnormal
异常事件识别模块300包括异常事件判别模块310及异常信息定位模块320；The abnormal
异常事件判别模块310，用于构建所述异常事件识别依据，对经预处理的视频流中是否出现异常事件进行判别；An abnormal
异常信息定位模块320，用于回传异常事件发生地理位置信息。The abnormality
预警及信息回溯模块400，用于在异常事件发生时，启动预警机制，以及将异常事件信息回传至监控中心；The early warning and
显示模块200，用于对视频流采用网格化排布或单点排布中任一种显示方法进行显示；A
通信模块500，用于各模块间的通信连接。The
实施例3Example 3
本实施例提供了一种计算机存储介质，计算机存储介质存储有一个或者多个程序，其中一个或者多个程序可被一个或者多个处理器执行，以实现实施例1中所述的监控预警方法，此外还可在计算机存储介质中安装有如实施例2所述的监控预警系统。This embodiment provides a computer storage medium, and the computer storage medium stores one or more programs, wherein one or more programs can be executed by one or more processors to implement the monitoring and early warning method described in Embodiment 1 , In addition, the monitoring and early warning system as described in Embodiment 2 can also be installed in the computer storage medium.
前述对本发明的具体示例性实施方案的描述是为了说明和例证的目的。这些描述并非想将本发明限定为所公开的精确形式，并且很显然，根据上述教导，可以进行很多改变和变化。对示例性实施例进行选择和描述的目的在于解释本发明的特定原理及其实际应用，从而使得本领域的技术人员能够实现并利用本发明的各种不同的示例性实施方案以及各种不同的选择和改变。本发明的范围意在由权利要求书及其等同形式所限定。The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. These descriptions are not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling others skilled in the art to make and use various exemplary embodiments of the invention, as well as various Choose and change. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (8)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010955424.9ACN112084963B (en) | 2020-09-11 | 2020-09-11 | A monitoring and early warning method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010955424.9ACN112084963B (en) | 2020-09-11 | 2020-09-11 | A monitoring and early warning method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112084963A CN112084963A (en) | 2020-12-15 |
| CN112084963Btrue CN112084963B (en) | 2022-11-01 |
Family
ID=73737642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010955424.9AActiveCN112084963B (en) | 2020-09-11 | 2020-09-11 | A monitoring and early warning method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084963B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112530021B (en)* | 2020-12-24 | 2023-06-23 | 北京百度网讯科技有限公司 | Method, device, device and storage medium for processing data |
| CN113673311B (en)* | 2021-07-05 | 2025-05-30 | 浙江大华技术股份有限公司 | A method, device and computer storage medium for detecting abnormal traffic events |
| CN113673406B (en)* | 2021-08-16 | 2024-07-23 | 杭州图灵视频科技有限公司 | Curtain wall glass burst detection method, system, electronic equipment and storage medium |
| CN113992896A (en)* | 2021-10-28 | 2022-01-28 | 南京奥拓电子科技有限公司 | Safety monitoring and early warning management method, system and storage medium |
| CN114220049A (en)* | 2021-12-03 | 2022-03-22 | 深圳市震有智联科技有限公司 | Video data processing method, device and storage medium |
| CN114328127A (en)* | 2022-01-05 | 2022-04-12 | 北京航空航天大学 | Software performance abnormality detection method and detection device |
| CN114554153B (en)* | 2022-02-24 | 2024-11-29 | 西安健尚智能科技有限公司 | Video stream transmission control method for monitoring system and monitoring system |
| CN115035436A (en)* | 2022-05-18 | 2022-09-09 | 佳源科技股份有限公司 | A smart gateway wake-up method, device, computer equipment and storage medium |
| CN116017038A (en)* | 2022-11-24 | 2023-04-25 | 杭州华橙软件技术有限公司 | A video data transmission method, system and computer-readable storage medium |
| CN116524427A (en)* | 2023-03-23 | 2023-08-01 | 福建新大陆通信科技股份有限公司 | Monitoring and managing method for emergency media-melting system |
| CN118447457B (en)* | 2024-07-02 | 2025-09-09 | 西安华盛通信有限公司 | Fusion type intelligent AI visual monitoring method and system |
| CN118569617A (en)* | 2024-08-05 | 2024-08-30 | 济南奔腾时代电力科技有限公司 | A smart power plant control system and control method based on computer vision target detection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180229A (en)* | 2017-05-04 | 2017-09-19 | 南京邮电大学 | Anomaly detection method based on the direction of motion in a kind of monitor video |
| CN111062281A (en)* | 2019-12-05 | 2020-04-24 | 亿利生态大数据有限公司 | Abnormal event monitoring method and device, storage medium and electronic equipment |
| CN111601074A (en)* | 2020-04-24 | 2020-08-28 | 平安科技（深圳）有限公司 | Security monitoring method, device, robot and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629316A (en)* | 2018-05-08 | 2018-10-09 | 东北师范大学人文学院 | A kind of video accident detection method of various visual angles |
- 2020
- 2020-09-11CNCN202010955424.9Apatent/CN112084963B/enactiveActive
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180229A (en)* | 2017-05-04 | 2017-09-19 | 南京邮电大学 | Anomaly detection method based on the direction of motion in a kind of monitor video |
| CN111062281A (en)* | 2019-12-05 | 2020-04-24 | 亿利生态大数据有限公司 | Abnormal event monitoring method and device, storage medium and electronic equipment |
| CN111601074A (en)* | 2020-04-24 | 2020-08-28 | 平安科技（深圳）有限公司 | Security monitoring method, device, robot and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于Vibe改进算法的中高密度人群异常检测方法研究;李丹丹;《中国优秀硕士学位论文全文数据库社会科学Ⅰ辑》;20180215;第14-60页* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112084963A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112084963B (en) | A monitoring and early warning method, system and storage medium | |
| CN113516076B (en) | An improved lightweight YOLO v4 security protection detection method based on attention mechanism | |
| CN108062349B (en) | Video surveillance method and system based on video structured data and deep learning | |
| CN106128022B (en) | A kind of wisdom gold eyeball identification violent action alarm method | |
| CN111242025B (en) | A real-time motion monitoring method based on YOLO | |
| CN110321780B (en) | Detection method of abnormal fall behavior based on spatiotemporal motion characteristics | |
| CN112053391B (en) | Monitoring and early warning method and system based on dynamic three-dimensional model and storage medium | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN110826538A (en) | An abnormal departure recognition system for electric power business halls | |
| CN113963301B (en) | A video fire smoke detection method and system based on spatiotemporal feature fusion | |
| CN106128053A (en) | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device | |
| CN112819068B (en) | Ship operation violation behavior real-time detection method based on deep learning | |
| KR102149832B1 (en) | Automated Violence Detecting System based on Deep Learning | |
| CN108053427A (en) | A kind of modified multi-object tracking method, system and device based on KCF and Kalman | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN111814638B (en) | Security scene flame detection method based on deep learning | |
| CN111325048B (en) | Personnel gathering detection method and device | |
| CN113743256B (en) | Intelligent early warning method and device for site safety | |
| CN108376246A (en) | A kind of identification of plurality of human faces and tracking system and method | |
| CN111091098A (en) | Training method and detection method of detection model and related device | |
| CN101883261A (en) | Method and system for abnormal target detection and relay tracking in large-scale monitoring scenarios | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| CN105426820A (en) | Multi-person abnormal behavior detection method based on security monitoring video data | |
| CN110070055A (en) | A kind of capital construction scene safety detecting system and method based on deep learning | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right | Effective date of registration:20250513 Address after:100020 Room 707, 7th Floor, Building A, Xingdi Center, No. 1 Building, Yard 10, JiuXianQiao North Road, Jiangtai Township, Chaoyang District, Beijing Patentee after:Four Dimensional View (Beijing) Data Technology Co.,Ltd. Country or region after:China Address before:519080 Guangdong Province Zhuhai City Gaoxin District Tangjia Bay Town Jin Tang Road No. 1 Harbor One Science and Technology Park Building 2 2-101/2-201/2-501 Patentee before:CHINA-GERMANY (ZHUHAI) ARTIFICIAL INTELLIGENCE INSTITUTE Co.,Ltd. Country or region before:China Patentee before:ZHUHAI 4DAGE NETWORK TECHNOLOGY Co.,Ltd. |