CN113569911A - Vehicle identification method, device, electronic device and storage medium - Google Patents
Vehicle identification method, device, electronic device and storage mediumDownload PDFInfo
- Publication number
- CN113569911A CN113569911ACN202110722566.5ACN202110722566ACN113569911ACN 113569911 ACN113569911 ACN 113569911ACN 202110722566 ACN202110722566 ACN 202110722566ACN 113569911 ACN113569911 ACN 113569911A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- feature information
- candidate
- similarity
- image
- 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
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本公开涉及人工智能领域，尤其涉及计算机视觉、深度学习等技术领域，具体可用于智慧城市和智能交通的场景下。The present disclosure relates to the field of artificial intelligence, in particular to the technical fields of computer vision, deep learning and the like, and can be specifically used in scenarios of smart cities and smart transportation.
背景技术Background technique
相关技术中，车辆图片中的车辆姿态会随拍摄角度的变化而变化，因此，通过车辆的外观特征进行车辆识别时，往往倾向于认定两个姿态相近的车辆是同一车辆。因此，如何准确识别车辆，已经成为重要的研究方向之一。In the related art, the posture of the vehicle in the vehicle picture changes with the change of the shooting angle. Therefore, when vehicle identification is performed based on the appearance features of the vehicle, it is often inclined to determine that two vehicles with similar postures are the same vehicle. Therefore, how to accurately identify vehicles has become one of the important research directions.
发明内容SUMMARY OF THE INVENTION
本公开提供了一种车辆识别方法、装置、电子设备及存储介质。The present disclosure provides a vehicle identification method, device, electronic device and storage medium.
根据本公开的一方面，提供了一种车辆识别方法，包括：According to an aspect of the present disclosure, there is provided a vehicle identification method, comprising:
获取待识别车辆的图像，并提取图像的第一全局特征信息；acquiring an image of the vehicle to be recognized, and extracting the first global feature information of the image;
基于第一全局特征信息获取至少一个候选车辆；acquiring at least one candidate vehicle based on the first global feature information;
从图像中提取待识别车辆的第一姿态特征信息；extracting the first posture feature information of the vehicle to be recognized from the image;
从至少一个候选车辆中，基于第一姿态特征信息获取与待识别车辆匹配的目标车辆。本公开实施例中基于全局特征和姿态特征，对待识别车辆进行精准识别，从而能够从外观和/或姿态上筛选出相似性高的车辆作为目标车辆，提高车辆识别的准确性。From the at least one candidate vehicle, a target vehicle matching the vehicle to be identified is acquired based on the first posture feature information. In the embodiment of the present disclosure, based on the global feature and the posture feature, the vehicle to be recognized is accurately identified, so that the vehicle with high similarity can be selected as the target vehicle from the appearance and/or posture, and the accuracy of the vehicle identification can be improved.
根据本公开的另一方面，提供了一种车辆识别装置，包括：According to another aspect of the present disclosure, a vehicle identification device is provided, comprising:
全局特征提取模块，用于获取待识别车辆的图像，并提取图像的第一全局特征信息；a global feature extraction module, used for acquiring the image of the vehicle to be recognized, and extracting the first global feature information of the image;
候选车辆获取模块，用于基于第一全局特征信息获取至少一个候选车辆；a candidate vehicle acquisition module, configured to acquire at least one candidate vehicle based on the first global feature information;
姿态特征提取模块，用于从图像中提取待识别车辆的第一姿态特征信息；an attitude feature extraction module, used for extracting the first attitude feature information of the vehicle to be recognized from the image;
目标车辆获取模块，用于从至少一个候选车辆中，基于第一姿态特征信息获取与待识别车辆匹配的目标车辆。The target vehicle obtaining module is configured to obtain, from at least one candidate vehicle, a target vehicle matching the vehicle to be identified based on the first posture feature information.
根据本公开的另一方面，提供了一种电子设备，包括至少一个处理器，以及According to another aspect of the present disclosure, there is provided an electronic device including at least one processor, and
与至少一个处理器通信连接的存储器；其中，a memory communicatively coupled to the at least one processor; wherein,
存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行本公开第一个方面实施例的车辆识别方法。The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle identification method of the embodiment of the first aspect of the present disclosure.
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，计算机指令用于使计算机执行本公开第一个方面实施例的车辆识别方法。According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the vehicle identification method of the embodiment of the first aspect of the present disclosure.
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行时实现本公开第一个方面实施例的车辆识别方法。According to another aspect of the present disclosure, there is provided a computer program product including a computer program, which when executed by a processor implements the vehicle identification method of the embodiment of the first aspect of the present disclosure.
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.
附图说明Description of drawings
附图用于更好地理解本方案，不构成对本公开的限定。其中：The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:
图1是根据本公开一个实施例的车辆识别方法的流程图；FIG. 1 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure;
图2是根据本公开一个实施例的车辆识别方法的流程图；FIG. 2 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure;
图3是根据本公开一个实施例的车辆识别方法的流程图；3 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure;
图4是根据本公开一个实施例的车辆识别方法的示意图；4 is a schematic diagram of a vehicle identification method according to an embodiment of the present disclosure;
图5是根据本公开一个实施例的车辆识别方法的示意图；FIG. 5 is a schematic diagram of a vehicle identification method according to an embodiment of the present disclosure;
图6是根据本公开一个实施例的车辆识别方法的流程图；6 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure;
图7是根据本公开一个实施例的车辆识别装置的结构图；FIG. 7 is a structural diagram of a vehicle identification device according to an embodiment of the present disclosure;
图8是用来实现本公开实施例的车辆识别方法的电子设备的框图。FIG. 8 is a block diagram of an electronic device used to implement the vehicle identification method of the embodiment of the present disclosure.
具体实施方式Detailed ways
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
为了方便对本公开的理解，下面首先对本公开涉及的技术领域进行简单解释说明书。In order to facilitate the understanding of the present disclosure, a brief description of the technical field to which the present disclosure relates will be briefly explained below.
人工智能是研究使计算机来模拟人的某些思维过程和智能行为(如学习、推理、思考、规划等)的学科，既有硬件层面的技术也有软件层面的技术。人工智能硬件技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理等技术；人工智能软件技术主要包括计算机视觉技术、语音识别技术、自然语言处理技术以及机器学习、深度学习、大数据处理技术、知识图谱技术等几大方向。Artificial intelligence is the study of making computers to simulate certain thinking processes and intelligent behaviors of people (such as learning, reasoning, thinking, planning, etc.), both hardware-level technology and software-level technology. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning, deep Learning, big data processing technology, knowledge graph technology and other major directions.
深度学习是学习样本数据的内在规律和表示层次，这些学习过程中获得的信息对诸如文字，图像和声音等数据的解释有很大的帮助。它的最终目标是让机器能够像人一样具有分析学习能力，能够识别文字、图像和声音等数据。深度学习是一个复杂的机器学习算法，在语音和图像识别方面取得的效果，远远超过先前相关技术。Deep learning is to learn the inherent laws and representation levels of sample data, and the information obtained during these learning processes is of great help to the interpretation of data such as text, images, and sounds. Its ultimate goal is to enable machines to have the ability to analyze and learn like humans, and to recognize data such as words, images, and sounds. Deep learning is a complex machine learning algorithm that has achieved results in speech and image recognition far exceeding previous related technologies.
智能交通是将先进的信息技术、数据通讯传输技术、电子传感技术、控制技术及计算机技术等有效地集成运用于整个地面交通管理系统而建立的一种在大范围内、全方位发挥作用的，实时、准确、高效的综合交通运输管理技术。Intelligent transportation is a large-scale and all-round function established by effectively integrating advanced information technology, data communication transmission technology, electronic sensing technology, control technology and computer technology into the entire ground traffic management system. , real-time, accurate and efficient integrated transportation management technology.
计算机视觉是一个跨学科的科学领域，研究如何让计算机从数字图像或视频中获得高水平的理解。从工程学的角度来看，它寻求人类视觉系统能够完成的自动化任务。计算机视觉任务包括获取、处理、分析和理解数字图像的方法，以及从现实世界中提取高维数据以便例如以决策的形式产生数字或符号信息的方法。Computer vision is an interdisciplinary scientific field that studies how computers can gain a high level of understanding from digital images or videos. From an engineering standpoint, it seeks to automate tasks that the human visual system can accomplish. Computer vision tasks include methods of acquiring, processing, analyzing, and understanding digital images, as well as methods of extracting high-dimensional data from the real world in order to produce numerical or symbolic information, for example, in the form of decisions.
下面结合参考附图描述本公开的车辆识别方法、装置、电子设备及存储介质。The vehicle identification method, apparatus, electronic device, and storage medium of the present disclosure will be described below with reference to the accompanying drawings.
图1是根据本公开一个实施例的车辆识别方法的流程图，如图1所示，该方法包括以下步骤：FIG. 1 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure. As shown in FIG. 1 , the method includes the following steps:
S101，获取待识别车辆的图像，并提取图像的第一全局特征信息。S101: Acquire an image of the vehicle to be recognized, and extract first global feature information of the image.
从某个角度对待识别车辆进行图像采集，获取待识别车辆的图像。本公开实施例中，待识别车辆的图像可以是包含待识别车辆的一部分的图像，也可以是包含整个待识别车辆的图像。可选地，待识别车辆的图像可以是拍摄的静态图像，也可以是视频帧序列中的视频图像或合成图像等。The image of the vehicle to be recognized is acquired from a certain angle, and the image of the vehicle to be recognized is obtained. In the embodiment of the present disclosure, the image of the vehicle to be identified may be an image including a part of the vehicle to be identified, or an image including the entire vehicle to be identified. Optionally, the image of the vehicle to be identified may be a captured still image, or may be a video image or a composite image in a video frame sequence.
对待识别车辆的图像中进行全局特征提取，提取第一全局特征信息，可选地，可以将待识别车辆的图像输入神经网络中，提取图像的第一全局特征信息，其中，第一全局特征信息可以是向量表示的全局特征。例如，利用神经网络的特征提取层对待识别车辆的图像进行卷积操作和池化操作，从而获取第一全局特征信息。Perform global feature extraction in the image of the vehicle to be recognized to extract the first global feature information, optionally, the image of the vehicle to be recognized can be input into a neural network to extract the first global feature information of the image, wherein the first global feature information Can be a vector-represented global feature. For example, a feature extraction layer of a neural network is used to perform a convolution operation and a pooling operation on the image of the vehicle to be recognized, so as to obtain the first global feature information.
可选地，神经网络可以是任意适当的可以提取全局特征信息的神经网络，包括但不限于全局的卷积神经网络等。Optionally, the neural network can be any suitable neural network that can extract global feature information, including but not limited to a global convolutional neural network and the like.
S102，基于第一全局特征信息获取至少一个候选车辆。S102, at least one candidate vehicle is acquired based on the first global feature information.
本公开中预先采集不同车辆的图像，并将不同车辆的图像存储在数据库中。在获取到第一全局特征信息，可以基于第一全局特征信息获取与待识别车辆的图像相似的至少一张车辆图像，进而将车辆图像对应的车辆作为候选车辆。In the present disclosure, images of different vehicles are pre-collected and stored in a database. After the first global feature information is acquired, at least one vehicle image similar to the image of the vehicle to be recognized may be acquired based on the first global feature information, and then the vehicle corresponding to the vehicle image is used as a candidate vehicle.
在一些实现中，提取数据库中已有的车辆图像的第二全局特征信息，并与第一全局特征信息进行匹配，根据匹配结果获取至少一个候选车辆。其中，提取第二全局特征信息的过程可以参见步骤S101中提取第一全局特征信息的相关介绍，此处不再赘述。In some implementations, the second global feature information of an existing vehicle image in the database is extracted and matched with the first global feature information, and at least one candidate vehicle is obtained according to the matching result. Wherein, for the process of extracting the second global feature information, reference may be made to the relevant introduction of extracting the first global feature information in step S101 , which will not be repeated here.
S103，从图像中提取待识别车辆的第一姿态特征信息。S103: Extract first posture feature information of the vehicle to be recognized from the image.
由于待识别车辆的行驶方向的不同，待识别车辆的图像所包含的车辆姿态及车辆部件也不相同。例如，在一些实现中，待识别车辆的行驶方向与拍摄方向相同，则获取的待识别车辆的图像中可能包含后转向灯、后备箱等；在一些实现中，待识别车辆的行驶方向与拍摄方向相反，则获取的待识别车辆的图像中可能包含保险杠、车标、两侧后视镜、两侧前大灯等。Due to the different driving directions of the vehicles to be identified, the vehicle postures and vehicle components included in the images of the vehicles to be identified are also different. For example, in some implementations, the driving direction of the vehicle to be recognized is the same as the shooting direction, the acquired image of the vehicle to be recognized may include rear turn signals, trunks, etc.; in some implementations, the driving direction of the vehicle to be recognized is the same as the shooting direction. If the direction is opposite, the acquired image of the vehicle to be identified may include bumpers, vehicle logos, side mirrors, headlights on both sides, etc.
为了提高车辆识别的准确率，本公开实施例根据图像中的车辆部件进一步对候选车辆进行筛选，从候选车辆中获取目标车辆。在一些实现中，对图像中的待识别车辆的姿态进行识别，获取车辆行驶方向，对图像中的待识别车辆的部件进行识别，获取车辆部件区域的图像，进而从车辆部件区域的图像中提取车辆部件的局部特征信息，进而将行驶方向及局部特征信息作为第一姿态特征信息。可选地，可以利用神经网络从图像中提取待识别车辆的局部特征信息。In order to improve the accuracy of vehicle identification, the embodiments of the present disclosure further screen candidate vehicles according to vehicle components in the image, and obtain the target vehicle from the candidate vehicles. In some implementations, the posture of the vehicle to be recognized in the image is recognized, the driving direction of the vehicle is obtained, the parts of the vehicle to be recognized in the image are recognized, the image of the vehicle part area is obtained, and then the image is extracted from the image of the vehicle part area. Local feature information of vehicle components, and further use the driving direction and local feature information as the first posture feature information. Optionally, a neural network can be used to extract local feature information of the vehicle to be identified from the image.
S104，从至少一个候选车辆中，基于第一姿态特征信息获取与待识别车辆匹配的目标车辆。S104, from at least one candidate vehicle, obtain a target vehicle matching the vehicle to be identified based on the first posture feature information.
在获取到第一姿态特征信息后，可以基于第一姿态特征信息获取与待识别车辆的图像在姿态特征上相似的至少一张车辆图像，进而实现对候选车辆的进一步筛选。作为一种可能的实现方式，可以从候选车辆的图片中提取第二姿态特征信息，确定待识别车辆的第一姿态特征信息与候选车辆的第二姿态特征信息的相似度，根据相似度，将与待识别车辆匹配的候选车辆作为目标车辆。After acquiring the first posture feature information, at least one vehicle image that is similar in posture feature to the image of the vehicle to be recognized may be acquired based on the first posture feature information, thereby further screening candidate vehicles. As a possible implementation, the second posture feature information can be extracted from the picture of the candidate vehicle, the similarity between the first posture feature information of the vehicle to be recognized and the second posture feature information of the candidate vehicle can be determined, and according to the similarity, the The candidate vehicle that matches the vehicle to be identified is used as the target vehicle.
本公开实施例中，获取待识别车辆的图像，并提取图像的第一全局特征信息；基于第一全局特征信息获取至少一个候选车辆；从图像中提取待识别车辆的第一姿态特征信息；从至少一个候选车辆中，基于第一姿态特征信息获取与待识别车辆匹配的目标车辆。本公开实施例中基于全局特征和姿态特征，对待识别车辆进行精准识别，从而能够从外观和/或姿态上筛选出相似性高的车辆作为目标车辆，提高车辆识别的准确性。In the embodiment of the present disclosure, an image of the vehicle to be recognized is acquired, and first global feature information of the image is extracted; at least one candidate vehicle is acquired based on the first global feature information; first posture feature information of the vehicle to be recognized is extracted from the image; In at least one candidate vehicle, a target vehicle matching the vehicle to be recognized is acquired based on the first posture feature information. In the embodiment of the present disclosure, based on the global feature and the posture feature, the vehicle to be recognized is accurately identified, so that the vehicle with high similarity can be selected as the target vehicle from the appearance and/or posture, and the accuracy of the vehicle identification can be improved.
图2是根据本公开另一个实施例的车辆识别方法的流程图，如图2所示，在上述实施例的基础上，基于第一全局特征信息获取至少一个候选车辆，包括以下步骤：FIG. 2 is a flowchart of a vehicle identification method according to another embodiment of the present disclosure. As shown in FIG. 2 , on the basis of the above embodiment, acquiring at least one candidate vehicle based on the first global feature information includes the following steps:
S201，获取第一全局特征信息与数据库中每个车辆的第二全局特征信息的相似度。S201: Obtain the similarity between the first global feature information and the second global feature information of each vehicle in the database.
提取数据库中的车辆的图像的第二全局特征信息，并与第一全局特征信息进行匹配，获取第一全局特征信息与第二全局特征信息的相似度，作为待识别车辆与数据库中的每个车辆的相似度。可选地，可以获取第一全局特征信息与第二全局特征信息的余弦距离，作为待识别车辆与数据库中的每个车辆的相似度。Extract the second global feature information of the image of the vehicle in the database, and match it with the first global feature information, and obtain the similarity between the first global feature information and the second global feature information, as the vehicle to be identified and each in the database. similarity of vehicles. Optionally, the cosine distance between the first global feature information and the second global feature information may be obtained as the similarity between the vehicle to be identified and each vehicle in the database.
S202，根据相似度，对数据库内所有车辆进行排序，并按照排序筛选至少一个候选车辆。S202, according to the similarity, sort all vehicles in the database, and filter at least one candidate vehicle according to the sorting.
将数据库内所有车辆按照相似度进行排序，可选地，可以将相似度大于预设阈值的车辆作为候选车辆，也可以将相似度最大的N个车辆作为候选车辆；其中，N为预先设定的大于0的正整数，也可以将排序后排序在前N位的车辆作为候选车辆。Sort all the vehicles in the database according to their similarity. Optionally, vehicles with a similarity greater than a preset threshold can be used as candidate vehicles, or N vehicles with the largest similarity can be used as candidate vehicles; where N is a preset is a positive integer greater than 0, and the vehicles ranked in the top N positions after sorting can also be used as candidate vehicles.
本公开实施例中，获取第一全局特征信息与数据库中每个车辆的第二全局特征信息的相似度；根据相似度，对数据库内所有车辆进行排序，并按照排序筛选至少一个候选车辆。本公开实施例有效利用第一全局特征信息从数据库中初步筛选出候选车辆，减小了后续筛选过程的计算量，便于提高后续对目标车辆进行识别的效率。In the embodiment of the present disclosure, the similarity between the first global feature information and the second global feature information of each vehicle in the database is obtained; according to the similarity, all vehicles in the database are sorted, and at least one candidate vehicle is screened according to the sorting. The embodiment of the present disclosure effectively utilizes the first global feature information to preliminarily screen candidate vehicles from the database, which reduces the amount of calculation in the subsequent screening process and facilitates the improvement of the efficiency of subsequent identification of target vehicles.
图3是根据本公开一个实施例的车辆识别方法的流程图，如图3所示，该方法包括以下步骤：FIG. 3 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure. As shown in FIG. 3 , the method includes the following steps:
S301，从图像中获取待识别车辆的行驶方向。S301 , acquiring the driving direction of the vehicle to be identified from the image.
对图像提取待识别车辆的位置，基于位置确定待识别车辆与图像的基准线之间的夹角。将夹角与多个候选行驶方向的角度范围进行比对，确定夹角所处的目标角度范围。将目标角度范围对应的候选行驶方向，确定为待识别车辆的行驶方向。举例说明，若拍摄角度为自南向北拍摄，则图像的基准线即为东西方向的直线，以车辆所在区域的外接矩形作为车辆的检测框，取车辆的检测框的中心点作为车辆的位置，将车辆位置与预设点进行连线，获取该直线与基准线之间的夹角，并将夹角与多个候选行驶方向的角度范围进行比对。可选地，如图4所示，本申请实施例中由8个候选行驶方向，其中，正东方向对应的角度范围为(-22.5°，22.5°]，东南方向对应的角度范围为(22.5°，67.5°]，正南方向对应的角度范围为(67.5°，112.5°]，以此类推，可以确定所有方向的角度范围，进而根据夹角所处的目标角度范围，将目标角度范围对应的候选行驶方向，确定为待识别车辆的行驶方向。例如，如图5所示，在一些实现中，若拍摄角度为自南向北拍摄，则图像的基准线即为东西方向的直线，基于位置确定待识别车辆与图像的基准线之间的夹角为90°，则确定待识别车辆的行驶方向为向南行驶。The position of the vehicle to be recognized is extracted from the image, and the angle between the vehicle to be recognized and the reference line of the image is determined based on the position. The included angle is compared with the angular ranges of multiple candidate driving directions to determine the target angle range in which the included angle is located. The candidate driving direction corresponding to the target angle range is determined as the driving direction of the vehicle to be identified. For example, if the shooting angle is from south to north, the reference line of the image is the straight line in the east-west direction, the circumscribed rectangle of the area where the vehicle is located is used as the detection frame of the vehicle, and the center point of the detection frame of the vehicle is taken as the position of the vehicle. , connect the vehicle position with the preset point, obtain the included angle between the straight line and the reference line, and compare the included angle with the angular ranges of multiple candidate driving directions. Optionally, as shown in FIG. 4 , in the embodiment of the present application, there are 8 candidate driving directions, wherein the angle range corresponding to the due east direction is (-22.5°, 22.5°], and the angle range corresponding to the southeast direction is (22.5°). °, 67.5°], the angle range corresponding to the south direction is (67.5°, 112.5°], and so on, the angle range of all directions can be determined, and then according to the target angle range where the included angle is located, the target angle range corresponds to The candidate driving direction is determined as the driving direction of the vehicle to be identified. For example, as shown in Figure 5, in some implementations, if the shooting angle is from south to north, the reference line of the image is the straight line in the east-west direction, based on It is determined that the included angle between the vehicle to be recognized and the reference line of the image is 90°, and then it is determined that the driving direction of the vehicle to be recognized is southward.
S302，从图像中获取待识别车辆的可见车辆部件的局部特征信息。S302: Obtain local feature information of visible vehicle components of the vehicle to be identified from the image.
对图像进行部件分类检测，以获取可见车辆部件的检测框。在一些实现中，可以将待识别车辆的图像输入分类检测网络，输出车辆部件的类别、位置及区域，将车辆部件区域的外接矩形作为车辆部件的检测框。Component classification detection is performed on the image to obtain detection frames for visible vehicle components. In some implementations, the image of the vehicle to be recognized may be input into the classification detection network, the category, location and area of the vehicle component may be output, and the circumscribing rectangle of the vehicle component area may be used as the detection frame of the vehicle component.
提取检测框对应位置上的局部特征信息。在一些实现中，将检测框对应的图像片区域输入感兴趣区域对齐层，由感兴趣对齐层提取局部特征信息，也就是说，将检测框包含的图像区域分割成若干个单元，在每个单元中计算固定四个坐标位置，用双线性内插的方法计算出这四个位置的值，然后进行最大池化操作，获取检测框对应位置上的局部特征信息。Extract the local feature information at the corresponding position of the detection frame. In some implementations, the image patch area corresponding to the detection frame is input into the region of interest alignment layer, and the local feature information is extracted by the alignment layer of interest, that is, the image area contained in the detection frame is divided into several units, in each Four fixed coordinate positions are calculated in the unit, and the values of these four positions are calculated by the method of bilinear interpolation, and then the maximum pooling operation is performed to obtain the local feature information at the corresponding position of the detection frame.
S303，将行驶方向和局部特征信息，作为待识别车辆的第一姿态特征信息。S303, taking the driving direction and the local feature information as the first posture feature information of the vehicle to be recognized.
在一些实现中，待识别车辆的第一姿态特征信息包括待识别车辆的行驶方向和局部特征信息。In some implementations, the first posture feature information of the vehicle to be recognized includes the driving direction and local feature information of the vehicle to be recognized.
在一些实现中，将行驶方向和局部特征信息输入全连接层，进行特征融合，获取第一姿态特征信息。In some implementations, the driving direction and local feature information are input into the fully connected layer, and feature fusion is performed to obtain the first pose feature information.
可选地，还可以根据检测框的大小和可见车辆部件的实际大小，确定可见车辆部件的可见比例参数，将可见比例参数，作为第一姿态特征信息中的一个特征信息，从而丰富第一姿态特征信息，进一步提高车辆识别的准确率。例如，将可见车辆部件的面积与检测框的面积的比值作为可见比例参数，进而将可见比例参数作为第一姿态特征信息中的一个特征信息。Optionally, the visible scale parameter of the visible vehicle component can also be determined according to the size of the detection frame and the actual size of the visible vehicle component, and the visible scale parameter is used as a feature information in the first posture feature information, thereby enriching the first posture. feature information to further improve the accuracy of vehicle identification. For example, the ratio of the area of the visible vehicle component to the area of the detection frame is used as the visible scale parameter, and then the visible scale parameter is used as one feature information in the first pose feature information.
本公开实施例中，从图像中获取待识别车辆的行驶方向，从图像中获取待识别车辆的可见车辆部件的局部特征信息，将行驶方向和局部特征信息，作为待识别车辆的第一姿态特征信息。本公开实施例将基于图像获取的行驶方向和局部特征信息作为待识别车辆的第一姿态特征信息，便于后续从候选车辆中确定目标车辆，提高了车辆识别的准确率。In the embodiment of the present disclosure, the driving direction of the vehicle to be recognized is obtained from the image, the local feature information of the visible vehicle components of the vehicle to be recognized is obtained from the image, and the driving direction and the local feature information are used as the first posture feature of the vehicle to be recognized. information. The embodiment of the present disclosure uses the driving direction and local feature information obtained based on the image as the first posture feature information of the vehicle to be identified, which facilitates subsequent determination of the target vehicle from the candidate vehicles, and improves the accuracy of vehicle identification.
图6是根据本公开一个实施例的车辆识别方法的流程图，如图4所示，该方法包括以下步骤：FIG. 6 is a flowchart of a vehicle identification method according to an embodiment of the present disclosure. As shown in FIG. 4 , the method includes the following steps:
S601，获取每个候选车辆的第二姿态特征信息。S601: Obtain second pose feature information of each candidate vehicle.
步骤S601中获取候选车辆的第二姿态特征信息的相关内容可以参见上述实施例中获取第一姿态特征信息的相关介绍，此处不再赘述。For the relevant content of acquiring the second posture feature information of the candidate vehicle in step S601, reference may be made to the relevant introduction of acquiring the first posture feature information in the above-mentioned embodiment, which will not be repeated here.
S602，获取第一姿态特征信息与每个第二姿态特征信息之间的姿态相似度。S602: Obtain the posture similarity between the first posture feature information and each second posture feature information.
针对每个候选车辆，将任一车辆部件的第一姿态特征信息与任一车辆部件的第二姿态特征信息进行匹配，获取车辆部件的相似度。在一些实现中，姿态相似度包括行驶方向上的第一相似度和可见车辆部件上的第二相似度；在一些实现中，可以将行驶方向上的第一相似度和可见车辆部件上的第二相似度取平均值，作为姿态相似度；在一些实现中，可以将行驶方向上的第一相似度和可见车辆部件上的第二相似度取加权平均值，作为姿态相似度；For each candidate vehicle, the first posture feature information of any vehicle component is matched with the second posture feature information of any vehicle component to obtain the similarity of the vehicle components. In some implementations, the pose similarity includes a first similarity in the direction of travel and a second similarity in the visible vehicle part; in some implementations, the first similarity in the direction of travel and the first similarity in the visible vehicle part may be combined Take the average of the two degrees of similarity as the posture similarity; in some implementations, a weighted average of the first similarity in the driving direction and the second similarity on the visible vehicle components can be taken as the posture similarity;
S603，根据姿态相似度，从至少一个候选车辆中识别出目标车辆。S603: Identify a target vehicle from at least one candidate vehicle according to the gesture similarity.
在一些实现中，姿态相似度包括行驶方向上的第一相似度和可见车辆部件上的第二相似度，从至少一个候选车辆中，获取第一相似度和第二相似度均满足各自的相似度阈值的目标候选车辆。获取目标候选车辆的数量，响应于数量大于设定数值，升高相似度阈值，重新选取目标候选车辆，直至数量未大于设定数量。例如，在一些实现中，待识别车辆的图像中包含保险杠、右侧后视镜、右侧前大灯等车辆部件，将第一相似度满足第一相似度阈值且第二相似度满足第二相似度阈值的的候选车辆作为目标候选车辆，若目标候选车辆的数量满足设定数值，则判定目标候选车辆为目标车辆，否则提高第一、第二相似度阈值，按照更新后的第一、第二相似度阈值重新选取目标候选车辆，直至数量未大于设定数量，得到目标车辆。可选地，设定数量可以为1。In some implementations, the pose similarity includes a first similarity in a driving direction and a second similarity in visible vehicle components, and from at least one candidate vehicle, the first similarity and the second similarity are obtained from the at least one candidate vehicle and both satisfy the respective similarity degree threshold of the target candidate vehicle. The number of target candidate vehicles is acquired, and in response to the number being greater than the set value, the similarity threshold is raised, and the target candidate vehicles are reselected until the number is not greater than the set number. For example, in some implementations, the image of the vehicle to be identified includes vehicle components such as a bumper, a right side mirror, and a right headlight, and the first similarity degree satisfies the first similarity degree threshold and the second similarity degree satisfies the first similarity degree threshold. Candidate vehicles with two similarity thresholds are used as target candidate vehicles. If the number of target candidate vehicles meets the set value, the target candidate vehicle is determined to be the target vehicle. Otherwise, the first and second similarity thresholds are increased. , and the second similarity threshold is re-selected target candidate vehicles until the number is not greater than the set number, and the target vehicle is obtained. Optionally, the set number may be one.
在一些实现中，姿态相似度为行驶方向上的第一相似度和可见车辆部件上的第二相似度的平均值或加权平均值，则从至少一个候选车辆中，选取姿态相似度中最大的候选车辆作为目标车辆。In some implementations, the gesture similarity is an average or weighted average of the first similarity in the driving direction and the second similarity in the visible vehicle components, then from the at least one candidate vehicle, the highest gesture similarity is selected from the at least one candidate vehicle. The candidate vehicle is used as the target vehicle.
本公开实施例中，获取每个候选车辆的第二姿态特征信息，获取第一姿态特征信息与每个第二姿态特征信息之间的姿态相似度，根据姿态相似度，从至少一个候选车辆中识别出目标车辆。本公开实施例中，根据第一姿态特征信息与第二姿态特征信息从候选车辆中确定目标车辆，可以降低候选车辆中与待识别车辆相似的非目标车辆的影响，对待识别车辆进行精准识别，从而能够从外观和/或姿态上筛选出相似性高的车辆作为目标车辆，提高车辆识别的准确率。In the embodiment of the present disclosure, the second posture feature information of each candidate vehicle is obtained, the posture similarity between the first posture feature information and each second posture feature information is obtained, and according to the posture similarity, from at least one candidate vehicle The target vehicle is identified. In the embodiment of the present disclosure, determining the target vehicle from the candidate vehicles according to the first posture feature information and the second posture feature information can reduce the influence of non-target vehicles that are similar to the vehicle to be recognized in the candidate vehicle, and accurately identify the vehicle to be recognized. Therefore, vehicles with high similarity can be screened out as target vehicles from the appearance and/or posture, and the accuracy of vehicle identification can be improved.
图7是根据本公开一个实施例的车辆识别装置的结构图，如图7所示，车辆识别装置700包括：FIG. 7 is a structural diagram of a vehicle identification device according to an embodiment of the present disclosure. As shown in FIG. 7 , the
全局特征提取模块710，用于获取待识别车辆的图像，并提取图像的第一全局特征信息；a global
候选车辆获取模块720，用于基于第一全局特征信息获取至少一个候选车辆；a candidate
姿态特征提取模块730，用于从图像中提取待识别车辆的第一姿态特征信息；an attitude
目标车辆获取模块740，用于从至少一个候选车辆中，基于第一姿态特征信息获取与待识别车辆匹配的目标车辆。The target
本公开实施例中基于全局特征和姿态特征，对待识别车辆进行精准识别，从而能够从外观和/或姿态上筛选出相似性高的车辆作为目标车辆，提高车辆识别的准确性。In the embodiment of the present disclosure, based on the global feature and the posture feature, the vehicle to be recognized is accurately identified, so that the vehicle with high similarity can be selected as the target vehicle from the appearance and/or posture, and the accuracy of the vehicle identification can be improved.
需要说明的是，前述对车辆识别方法实施例的解释说明也适用于该实施例的车辆识别装置，此处不再赘述。It should be noted that, the foregoing explanations on the embodiment of the vehicle identification method are also applicable to the vehicle identification device of this embodiment, which will not be repeated here.
进一步的，在本公开实施例一种可能的实现方式中，候选车辆获取模块720，还用于：获取第一全局特征信息与数据库中每个车辆的第二全局特征信息的相似度；根据相似度，对数据库内所有车辆进行排序，并按照排序筛选至少一个候选车辆。Further, in a possible implementation manner of the embodiment of the present disclosure, the candidate
进一步的，在本公开实施例一种可能的实现方式中，姿态特征提取模块730，还用于：从图像中获取待识别车辆的行驶方向；从图像中获取待识别车辆的可见车辆部件的局部特征信息将行驶方向和局部特征信息，作为待识别车辆的第一姿态特征信息。Further, in a possible implementation manner of the embodiment of the present disclosure, the posture
进一步的，在本公开实施例一种可能的实现方式中，姿态特征提取模块730，还用于：对图像进行部件分类检测，以获取可见车辆部件的检测框；提取检测框对应位置上的局部特征信息。Further, in a possible implementation manner of the embodiment of the present disclosure, the posture
进一步的，在本公开实施例一种可能的实现方式中，姿态特征提取模块730，还用于：对图像提取待识别车辆的位置，基于位置确定待识别车辆与图像的基准线之间的夹角；将夹角与多个候选行驶方向的角度范围进行比对，确定夹角所处的目标角度范围；将目标角度范围对应的候选行驶方向，确定为待识别车辆的行驶方向。Further, in a possible implementation manner of the embodiment of the present disclosure, the posture
进一步的，在本公开实施例一种可能的实现方式中，目标车辆获取模块740，还用于：获取每个候选车辆的第二姿态特征信息；获取第一姿态特征信息与每个第二姿态特征信息之间的姿态相似度；根据姿态相似度，从至少一个候选车辆中识别出目标车辆。Further, in a possible implementation manner of the embodiment of the present disclosure, the target
进一步的，在本公开实施例一种可能的实现方式中，姿态相似度包括行驶方向上的第一相似度和可见车辆部件上的第二相似度，其中目标车辆获取模块740，还用于：从至少一个候选车辆中，获取第一相似度和第二相似度均满足各自的相似度阈值的目标候选车辆；获取目标候选车辆的数量，响应于数量大于设定数值，升高相似度阈值，重新选取目标候选车辆，直至数量未大于设定数量。Further, in a possible implementation manner of the embodiment of the present disclosure, the posture similarity includes the first similarity in the driving direction and the second similarity in the visible vehicle components, wherein the target
进一步的，在本公开实施例一种可能的实现方式中，目标车辆获取模块740，还用于：从至少一个候选车辆中，选取姿态相似度中最大的候选车辆作为目标车辆。Further, in a possible implementation manner of the embodiment of the present disclosure, the target
进一步的，在本公开实施例一种可能的实现方式中，姿态特征提取模块730，还用于：根据检测框的大小和可见车辆部件的实际大小，确定可见车辆部件的可见比例参数；将可见比例参数，作为第一姿态特征信息中的一个特征信息。Further, in a possible implementation manner of the embodiment of the present disclosure, the posture
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
图8示出了可以用来实施本公开的实施例的示例电子设备800的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。FIG. 8 shows a schematic block diagram of an example
如图8所示，设备800包括计算单元801，其可以根据存储在只读存储器(ROM)802中的计算机程序或者从存储单元808加载到随机访问存储器(RAM)803中的计算机程序，来执行各种适当的动作和处理。在RAM 803中，还可存储设备800操作所需的各种程序和数据。计算单元801、ROM 802以及RAM 803通过总线804彼此相连。输入/输出(I/O)接口805也连接至总线804。As shown in FIG. 8 , the
设备800中的多个部件连接至I/O接口805，包括：输入单元806，例如键盘、鼠标等；输出单元807，例如各种类型的显示器、扬声器等；存储单元808，例如磁盘、光盘等；以及通信单元809，例如网卡、调制解调器、无线通信收发机等。通信单元809允许设备800通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。Various components in the
计算单元801可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元801的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元801执行上文所描述的各个方法和处理，例如车辆识别方法。例如，在一些实施例中，车辆识别方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元808。在一些实施例中，计算机程序的部分或者全部可以经由ROM 802和/或通信单元809而被载入和/或安装到设备800上。当计算机程序加载到RAM 803并由计算单元801执行时，可以执行上文描述的车辆识别方法的一个或多个步骤。备选地，在其他实施例中，计算单元801可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行车辆识别方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a distributed system server, or a server combined with blockchain.
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders. As long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, there is no limitation herein.
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.
Claims (21)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110722566.5ACN113569911A (en) | 2021-06-28 | 2021-06-28 | Vehicle identification method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110722566.5ACN113569911A (en) | 2021-06-28 | 2021-06-28 | Vehicle identification method, device, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113569911Atrue CN113569911A (en) | 2021-10-29 |
Family
ID=78162858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110722566.5APendingCN113569911A (en) | 2021-06-28 | 2021-06-28 | Vehicle identification method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113569911A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297534A (en)* | 2022-02-28 | 2022-04-08 | 京东方科技集团股份有限公司 | Method, system and storage medium for interactively finding target objects |
| CN114510996A (en)* | 2021-12-30 | 2022-05-17 | 北京精英路通科技有限公司 | Video-based vehicle matching method and device, electronic equipment and storage medium |
| CN114581525A (en)* | 2022-03-11 | 2022-06-03 | 浙江商汤科技开发有限公司 | Attitude determination method and device, electronic device and storage medium |
| CN115205555A (en)* | 2022-07-12 | 2022-10-18 | 北京百度网讯科技有限公司 | Method, training method, information determination method and device for determining similar images |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229468A (en)* | 2017-06-28 | 2018-06-29 | 北京市商汤科技开发有限公司 | Vehicle appearance feature recognition and vehicle retrieval method, apparatus, storage medium, electronic equipment |
| CN108596277A (en)* | 2018-05-10 | 2018-09-28 | 腾讯科技（深圳）有限公司 | A kind of testing vehicle register identification method, apparatus and storage medium |
| CN109145898A (en)* | 2018-07-26 | 2019-01-04 | 清华大学深圳研究生院 | A kind of object detecting method based on convolutional neural networks and iterator mechanism |
| CN109508623A (en)* | 2018-08-31 | 2019-03-22 | 杭州千讯智能科技有限公司 | Item identification method and device based on image procossing |
| CN109584300A (en)* | 2018-11-20 | 2019-04-05 | 浙江大华技术股份有限公司 | A kind of method and device of determining headstock towards angle |
| CN110458086A (en)* | 2019-08-07 | 2019-11-15 | 北京百度网讯科技有限公司 | Vehicle re-identification method and device |
| CN111242088A (en)* | 2020-01-22 | 2020-06-05 | 上海商汤临港智能科技有限公司 | Target detection method and device, electronic equipment and storage medium |
| CN111611414A (en)* | 2019-02-22 | 2020-09-01 | 杭州海康威视数字技术股份有限公司 | Vehicle retrieval method, device and storage medium |
| CN111931627A (en)* | 2020-08-05 | 2020-11-13 | 智慧互通科技有限公司 | Vehicle re-identification method and device based on multi-mode information fusion |
| CN112990217A (en)* | 2021-03-24 | 2021-06-18 | 北京百度网讯科技有限公司 | Image recognition method and device for vehicle, electronic equipment and medium |
- 2021
- 2021-06-28CNCN202110722566.5Apatent/CN113569911A/enactivePending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229468A (en)* | 2017-06-28 | 2018-06-29 | 北京市商汤科技开发有限公司 | Vehicle appearance feature recognition and vehicle retrieval method, apparatus, storage medium, electronic equipment |
| CN108596277A (en)* | 2018-05-10 | 2018-09-28 | 腾讯科技（深圳）有限公司 | A kind of testing vehicle register identification method, apparatus and storage medium |
| CN109145898A (en)* | 2018-07-26 | 2019-01-04 | 清华大学深圳研究生院 | A kind of object detecting method based on convolutional neural networks and iterator mechanism |
| CN109508623A (en)* | 2018-08-31 | 2019-03-22 | 杭州千讯智能科技有限公司 | Item identification method and device based on image procossing |
| CN109584300A (en)* | 2018-11-20 | 2019-04-05 | 浙江大华技术股份有限公司 | A kind of method and device of determining headstock towards angle |
| CN111611414A (en)* | 2019-02-22 | 2020-09-01 | 杭州海康威视数字技术股份有限公司 | Vehicle retrieval method, device and storage medium |
| CN110458086A (en)* | 2019-08-07 | 2019-11-15 | 北京百度网讯科技有限公司 | Vehicle re-identification method and device |
| CN111242088A (en)* | 2020-01-22 | 2020-06-05 | 上海商汤临港智能科技有限公司 | Target detection method and device, electronic equipment and storage medium |
| CN111931627A (en)* | 2020-08-05 | 2020-11-13 | 智慧互通科技有限公司 | Vehicle re-identification method and device based on multi-mode information fusion |
| CN112990217A (en)* | 2021-03-24 | 2021-06-18 | 北京百度网讯科技有限公司 | Image recognition method and device for vehicle, electronic equipment and medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114510996A (en)* | 2021-12-30 | 2022-05-17 | 北京精英路通科技有限公司 | Video-based vehicle matching method and device, electronic equipment and storage medium |
| CN114297534A (en)* | 2022-02-28 | 2022-04-08 | 京东方科技集团股份有限公司 | Method, system and storage medium for interactively finding target objects |
| CN114581525A (en)* | 2022-03-11 | 2022-06-03 | 浙江商汤科技开发有限公司 | Attitude determination method and device, electronic device and storage medium |
| CN114581525B (en)* | 2022-03-11 | 2025-06-27 | 浙江商汤科技开发有限公司 | Attitude determination method and device, electronic device and storage medium |
| CN115205555A (en)* | 2022-07-12 | 2022-10-18 | 北京百度网讯科技有限公司 | Method, training method, information determination method and device for determining similar images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Pedestrian detection method based on Faster R-CNN | |
| CN113936256A (en) | An image target detection method, device, device and storage medium | |
| US12196572B2 (en) | Method for automatically producing map data, and related apparatus | |
| KR20220113829A (en) | Vehicle tracking methods, devices and electronic devices | |
| CN113569911A (en) | Vehicle identification method, device, electronic device and storage medium | |
| CN113971751A (en) | Training feature extraction model, and method and device for detecting similar images | |
| CN112966742A (en) | Model training method, target detection method and device and electronic equipment | |
| CN113569912A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
| WO2022227770A1 (en) | Method for training target object detection model, target object detection method, and device | |
| CN113344121B (en) | Methods for training signboard classification models and signboard classification | |
| CN107169421A (en) | A kind of car steering scene objects detection method based on depth convolutional neural networks | |
| CN117456389B (en) | YOLOv5 s-based improved unmanned aerial vehicle aerial image dense and small target identification method, system, equipment and medium | |
| Yang et al. | HCNN-PSI: A hybrid CNN with partial semantic information for space target recognition | |
| CN113378770A (en) | Gesture recognition method, device, equipment, storage medium and program product | |
| CN115240035A (en) | Semi-supervised target detection model training method, device, equipment and storage medium | |
| CN113065523A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN114332977A (en) | Key point detection method, device, electronic device and storage medium | |
| CN116958027A (en) | Three-dimensional industrial abnormality detection method and device, storage medium and electronic equipment | |
| CN117203678A (en) | Target detection method and device | |
| CN115147809A (en) | Obstacle detection method, device, equipment and storage medium | |
| CN115205806A (en) | Method and device for generating target detection model and automatic driving vehicle | |
| CN113705381A (en) | Target detection method and device in foggy days, electronic equipment and storage medium | |
| CN114998678A (en) | Model training method, target tracking method and device | |
| CN114842541A (en) | Model training and face recognition method, device, equipment and storage medium | |
| CN113989300A (en) | Method, device, electronic device and storage medium for lane line segmentation |
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 |