WO2019105342A1 - 车辆套牌检测方法、装置、可读存储介质及电子设备 - Google Patents
车辆套牌检测方法、装置、可读存储介质及电子设备 Download PDFInfo
- Publication number
- WO2019105342A1 WO2019105342A1 PCT/CN2018/117685 CN2018117685W WO2019105342A1 WO 2019105342 A1 WO2019105342 A1 WO 2019105342A1 CN 2018117685 W CN2018117685 W CN 2018117685W WO 2019105342 A1 WO2019105342 A1 WO 2019105342A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- current
- vehicle
- license plate
- driver
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Definitions
- the present invention relates to the field of vehicle inspection technology, and in particular, to a vehicle deck detection method, apparatus, readable storage medium, and electronic device.
- the present invention provides a vehicle deck detection method that solves the problem that the vehicle capture system of the prior art cannot recognize the vehicle deck.
- the vehicle deck detection method of the invention comprises:
- the current vehicle is marked as a deck vehicle.
- the vehicle deck detection method based on the face recognition technology and the vehicle identification technology, the relationship between the captured current vehicle and the driver driving the current vehicle is mainly analyzed, and the captured current vehicle image is first performed.
- the vehicle identification analysis and the face recognition analysis obtain the current vehicle information of the current vehicle and the current face information of the current vehicle, and then compare and analyze the current vehicle information and the current face information respectively, according to the current license plate in the current vehicle information.
- the information acquires the owner information corresponding to the current license plate information, and obtains corresponding driver information according to the current face information.
- Vehicle capture system does not have the ability to identify vehicle decks The problem, can reduce the workload of manual reconnaissance car deck.
- vehicle deck detecting method according to the present invention described above may further have the following additional technical features:
- the vehicle owner information corresponding to the determined current license plate information is acquired according to the determined current license plate information
- the current face information corresponding to the determined current face information is acquired according to the determined current face information.
- the driver information, and determining whether the acquired owner information is consistent with the obtained driver information includes:
- the driver information including identity information of the driver
- the step of acquiring vehicle information of all vehicles under the driver name corresponding to the driver information includes:
- the vehicle information of all the vehicles under the driver name corresponding to the current driver information is determined, and the vehicle information of all the vehicles includes brand information, model information, color information, and license plate information of each vehicle.
- the current vehicle structure information includes current brand information, current model information, and current color information of the current vehicle;
- the comparing the current vehicle information with the vehicle information of the all vehicles to determine whether there is a vehicle in the all vehicles that is consistent with the current vehicle structure information, but the vehicle that is inconsistent with the current license plate information includes :
- the method further includes:
- the vehicle corresponding to the current license plate is inspected according to the vehicle record information in the preset time in the license plate information database, and the vehicle record information includes license plate information, a capture time corresponding to the license plate information, and a capture location;
- the current lane bayonet capture unit includes at least one fill light for assisting the license plate fill light, and at least one fill light for assisting in capturing a human face;
- the steps of performing vehicle identification analysis and face recognition analysis on the current vehicle picture captured by the current lane bayonet capture unit include:
- the current vehicle picture is processed by ISP imaging control, and the processed vehicle map is subjected to vehicle recognition analysis and face recognition analysis.
- the step of performing vehicle identification analysis on the current vehicle picture captured by the current lane bayonet capture unit comprises:
- the current vehicle structure information includes at least current brand information, current model information, and current color information of the current vehicle;
- the current vehicle structure information and the current license plate information are aggregated to generate the current vehicle information.
- the step of performing face recognition analysis on the current vehicle picture captured by the current lane bayonet capture unit comprises:
- the face position is determined in the area where the face is located, and the face feature extraction, the face size, and the position information of each face organ are obtained to obtain the current face information.
- the invention also provides a vehicle deck detecting device, which solves the problem that the vehicle capturing system of the prior art cannot recognize the vehicle deck, and the device comprises:
- the capture analysis module is configured to perform vehicle identification analysis and face recognition analysis on the current vehicle image captured by the current lane bayonet capture unit to acquire current vehicle information and current face information corresponding to the current vehicle, the current vehicle information. Includes current license plate information and current vehicle structure information;
- the obtaining judgment module is configured to acquire, according to the determined current license plate information, vehicle owner information corresponding to the determined current license plate information, and obtain driver information corresponding to the determined current face information according to the determined current face information, and determine the acquisition Whether the owner information is consistent with the obtained driver information;
- a comparison judging module configured to acquire vehicle information of all vehicles under the driver name corresponding to the driver information when the lookup judgment module determines that the owner information and the driver information are inconsistent, and The current vehicle information is compared with the vehicle information of all the vehicles under the driver name to determine whether all vehicles under the driver name are consistent with the current vehicle structure information, but are inconsistent with the current license plate information.
- a marking module configured to determine the current vehicle when the comparison judgment module determines that there is a vehicle in the vehicle under the driver name that is consistent with the current vehicle structure information but is inconsistent with the current license plate information For the deck car.
- the present invention also provides a readable storage medium having stored thereon a computer program that, when executed by a processor, implements the steps of the above method.
- the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, further comprising a lane bayonet capture unit, wherein the processor implements the method when the program is executed A step of.
- the vehicle deck detection method of the invention is based on the face recognition technology and the vehicle identification technology, and mainly analyzes the relationship between the captured current vehicle and the driver driving the current vehicle, and first performs vehicle identification on the captured current vehicle image.
- the analysis and the face recognition analysis obtain the current vehicle information of the current vehicle and the current face information of the current vehicle, and then compare and analyze the current vehicle information and the current face information respectively, and obtain according to the current license plate information in the current vehicle information.
- the owner information corresponding to the current license plate information, and the corresponding driver information is obtained according to the current face information.
- the two are inconsistent, continue to query all the vehicle information under the driver name and compare with the current vehicle information, and finally when the driver When there are vehicles in the name that are consistent with the current vehicle structure information but are inconsistent with the current license plate information, it can be determined that the captured current vehicle is a deck vehicle and marked, and the method can solve the prior art vehicle capture
- the system does not have the problem of recognizing the vehicle deck function People can reduce the workload of workers reconnaissance car deck.
- FIG. 1 is a flow chart of a vehicle deck detecting method according to a first embodiment of the present invention
- Figure 2 is a flow chart of the vehicle identification analysis of Figure 1;
- Figure 3 is a flow chart of the face recognition analysis of Figure 1;
- FIG. 4 is a flow chart of a vehicle deck detecting method according to a second embodiment of the present invention.
- FIG. 5 is a block diagram showing the structure of a vehicle deck detecting device in accordance with a third embodiment of the present invention.
- a vehicle deck detection method includes:
- S101 Perform vehicle identification analysis and face recognition analysis on the current vehicle image captured by the current lane bayonet capture unit to acquire current vehicle information and current face information corresponding to the current vehicle, where the current vehicle information includes current license plate information. And current vehicle structure information.
- the current face information is driver face information of the current vehicle.
- the current camera capture unit usually uses a camera.
- the camera can be installed at the main road, the city bayonet, the high-speed entrance and exit, etc.
- the camera uses a 7-megapixel high-definition camera.
- the server for example, adopts a computer, and can receive an image captured by the camera, and perform data analysis and processing on the captured image.
- the method execution body provided in this embodiment is the server.
- the current lane bayonet capture unit further includes at least one fill light for assisting the license plate fill light, and at least one fill light for assisting the capture of the face to enhance the camera to the vehicle and The driver's ability to capture.
- the video virtual coil trigger and the fill light linkage signal output may be used to enable the current lane bayonet capture unit to capture the current vehicle image, that is, to set a virtual coil at a corresponding position from the road bayonet, when the vehicle passes the virtual coil, Causing the video virtual coil to trigger, at the same time, with the fill light linkage signal output, that is, the fill light for assisting the license plate fill light and the fill light for assisting the capture of the face simultaneously open, so that the corresponding camera captures , get the current vehicle picture.
- the current vehicle picture has both the current vehicle and an image of the driver driving the current vehicle.
- the current vehicle image can be processed by ISP (Image Signal Processing) imaging control to improve the image quality, specifically by adopting an autofocus algorithm, an automatic exposure algorithm, and an automatic white balance algorithm.
- ISP Image Signal Processing
- the picture is processed, and the processed vehicle image is analyzed for vehicle recognition analysis and face recognition.
- vehicle identification analysis and face recognition analysis are required for the current vehicle map.
- S1011a performing structural extraction of vehicle information on the current vehicle image to obtain current vehicle structure information, where the current vehicle structure information includes at least current brand information, current model information, and current color information of the current vehicle;
- the vehicle identification technology may be used to obtain the current vehicle structure information
- the current vehicle structure information may further include information such as the total mass of the current vehicle and the collision situation.
- the current brand information and the current model information may be searched in the vehicle model database.
- the total quality information of the current vehicle can be obtained by comparing the current vehicle in the current vehicle picture with the vehicle picture recorded in the vehicle type database to obtain the collision information of the current vehicle.
- S1012a performing license plate detection and identification on the current vehicle image to obtain license plate information of the current vehicle
- the license plate number identification technology can be used to detect and recognize the license plate of the current vehicle image. It should be pointed out that since the license plate number recognition technology is relatively mature, the license plate number recognition technology can also be integrated into the current lane bayonet capture unit, that is, Integrated in the camera.
- S1013a summarizing the current vehicle structure information and the license plate information of the current vehicle to generate the current vehicle information.
- S1011b performing face detection on the current vehicle image to determine whether a face exists
- the driver's area that is, the pixel range near the driver's seat
- the face detection algorithm based on the depth neural network performs face detection to determine whether there is a face. If yes, the facial feature extraction is further performed on the area where the face is located, the position and size of the face, and the position information of each facial organ are determined, and finally the current face information is obtained.
- the vehicle information database stores license plate information and vehicle owner information corresponding to the license plate information.
- Driver's face information and driver information corresponding to face information are stored in the driver database.
- the vehicle information base and the driver database can also be integrated.
- vehicle owner information corresponding to the determined license plate information according to the determined current license plate information, where the vehicle owner information includes identity information of the vehicle owner;
- the driver information including identity information of the driver
- the identity information may include related information on the resident ID card.
- Vehicle information can be carried out in the following ways:
- the vehicle information of all the vehicles under the driver name corresponding to the current driver information is determined, and the vehicle information of all the vehicles includes brand information, model information, color information, and license plate information of each vehicle.
- the brand information, the model information, the color information, and the license plate information of the current vehicle are respectively obtained, and the acquired brand information, model information, and color information of each vehicle in the vehicle information of all the vehicles.
- the license plate information is compared to determine whether there is a vehicle in the vehicle under the driver name that is consistent with the current vehicle structure information but is inconsistent with the current license plate information.
- relevant information of the current vehicle and the driver driving the current vehicle may be stored, so that the police can conduct forensic analysis and may also actively push the police to the police. Message.
- the vehicle deck detecting method mainly analyzes the relationship between the captured current vehicle and the driver driving the current vehicle based on the face recognition technology and the vehicle identification technology, and firstly captures the captured current vehicle picture. Performing vehicle identification analysis and face recognition analysis, obtaining current vehicle information of the current vehicle and driving current face information of the current vehicle, and then performing comparative analysis on the current vehicle information and the current face information respectively, according to current current information in the current vehicle information
- the license plate information obtains the owner information corresponding to the current license plate information, and obtains corresponding driver information according to the current face information.
- a vehicle deck detecting method includes:
- S201 Perform vehicle identification analysis on the current vehicle image captured by the current lane bayonet capture unit to acquire current vehicle information corresponding to the current vehicle, where the current vehicle information includes current license plate information;
- the method and implementation process of the bayonet capture unit, the vehicle identification analysis, and the like in this step are the same as those in the first embodiment.
- This embodiment focuses on the differences from the previous embodiment, and the embodiments are similar. Some are not repeated and can be referred to each other.
- the vehicle corresponding to the current license plate is checked according to the vehicle record information in the preset time in the license plate information database, and the vehicle record information includes license plate information, a capture time corresponding to the license plate information, and a capture location (;
- the license plate information database may be pre-stored in the server, and the license plate information database uses a big data processing technology to store and analyze all the vehicles captured by the bayonet.
- a certain range of bayonet for example, storing and analyzing vehicle images captured by all the bayonet ports of a certain province or a certain city, extracting and recording the corresponding license plate information, and recording the capture time and the capture time when the fear is captured.
- the time range of the comparison can be limited. For example, the current license plate is compared with the vehicle record information in the license information database for nearly one hour.
- the time and place when the current license plate appears in the second bayonet is first obtained, and then according to the current bayonet and the first
- the position information of the two bayonet, the road condition information between the two, the vehicle speed information, and the time interval information of the current license plate appearing at the current bayonet and the second bayonet, determining that the same car appears in the two bayonet at the time interval can be calculated by the corresponding calculation formula or by the discharge method.
- the current bayonet is separated from the second bayonet by 200 km, and the current license plate appears at the current second bayonet for 10: 00am, and the current license plate appears at the current bayonet at 10:20am on the same day. It is impossible for the same car to appear on the two bayonets according to the above two time points, so it can be determined that the current vehicle and the second card There is a deck car in the vehicle corresponding to the current license plate captured by the mouth, and the analysis result can be pushed to the police for further analysis. As a supplement to the first embodiment, the embodiment reduces the detection range of the deck vehicle, thereby improving the efficiency of the detection of the deck vehicle and further reducing the workload of the manual reconnaissance deck truck.
- the current owner information is consistent with the current driver information
- the driver driving the current vehicle has no driver's license, that is, there is no driver's information in the vehicle/driver database;
- the driver has a driver's license, but there is no vehicle under his name
- the method provided by the embodiment can be used for supplementary detection to improve the efficiency of the detection of the deck vehicle, and the workload of the manual reconnaissance deck vehicle can be reduced.
- a vehicle deck detecting device includes:
- the capture analysis module 10 is configured to perform vehicle identification analysis and face recognition analysis on the current vehicle image captured by the current lane bayonet capture unit to acquire current vehicle information and current face information corresponding to the current vehicle, the current vehicle.
- the information includes current license plate information and current vehicle structure information;
- the obtaining judgment module 20 is configured to acquire, according to the determined current license plate information, vehicle owner information corresponding to the determined current license plate information, and obtain driver information corresponding to the determined current face information according to the determined current face information, and determine Whether the obtained owner information is consistent with the obtained driver information;
- the comparison judging module 30 is configured to acquire vehicle information of all vehicles under the driver name corresponding to the driver information when the search judging module determines that the owner information and the driver information are inconsistent, and Comparing the current vehicle information with the vehicle information of all the vehicles to determine whether there is a vehicle in the all vehicles that is consistent with the current vehicle structure information but is inconsistent with the current license plate information;
- the marking module 40 is configured to: when the comparison judgment module determines that there is a vehicle in the vehicle under the driver name that is consistent with the current vehicle structure information but is inconsistent with the current license plate information, the current The vehicle is marked as a deck car.
- the obtaining determining module 20 includes:
- the first obtaining unit 201 is configured to acquire, according to the determined current license plate information, vehicle owner information corresponding to the determined license plate information in the vehicle information base, where the vehicle owner information includes identity information of the vehicle owner;
- the second obtaining unit 202 is configured to acquire driver information corresponding to current face information in the driver according to the current face information, where the driver information includes identity information of the driver;
- the determining unit 203 is configured to determine whether the identity information of the owner and the identity information of the driver are consistent.
- the comparison determining module 30 is specifically configured to:
- the vehicle information of all the vehicles under the driver name corresponding to the current driver information is determined, and the vehicle information of all the vehicles includes brand information, model information, color information, and license plate information of each vehicle.
- the current vehicle structure information includes current brand information, current model information, and current color information of the current vehicle;
- the comparison judgment module 30 is further configured to:
- the vehicle deck detecting device further includes:
- the troubleshooting module 50 performs a check on the vehicle corresponding to the current license plate according to the vehicle record information in the preset time in the license plate information database, where the vehicle record information includes license plate information, a capture time corresponding to the license plate information, and a capture location;
- the judging module 60 is configured to, when the current license plate corresponding to the current license plate information is found in the license plate information database, appears in the second bayonet in a preset time, according to the current bayonet and the second bayonet Position information, road condition information between the two, vehicle speed information of the current license plate, and time interval information of the current license plate appearing at the current bayonet and the second bayonet, determining the current vehicle or the first Whether the vehicle corresponding to the current license plate captured by the two bayonet has a deck vehicle.
- the current lane bayonet capture unit includes at least one fill light for assisting the license plate fill light, and at least one fill light for assisting in capturing the face;
- the capture analysis module 10 is specifically configured to:
- the current vehicle picture is processed by ISP imaging control, and the processed vehicle map is subjected to vehicle recognition analysis and face recognition analysis.
- the snapshot analysis module 10 is further configured to:
- the current vehicle structure information includes at least current brand information, current model information, and current color information of the current vehicle;
- the current vehicle structure information and the current license plate information are aggregated to generate the current vehicle information.
- the snapshot analysis module 10 is further configured to:
- the face position is determined in the area where the face is located, and the face feature extraction, the face size, and the position information of each face organ are obtained to obtain the current face information.
- embodiments of the present invention also provide a readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the steps of the above methods.
- embodiments of the present invention also provide an electronic device including a memory, a processor, and a computer program stored on the memory and operable on the processor, further including a lane bayonet capture unit, the processor executing the The steps of the above method are implemented when the program is executed.
- a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with such an instruction execution system, apparatus, or device.
- computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
- the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
- portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
- multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
- a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
Abstract
一种车辆套牌检测方法、装置、可读存储介质及电子设备，包括：对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，当前车辆信息包括当前车牌信息和当前车辆结构信息（S101）；根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致（S102）；若不一致，则获取驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将当前车辆信息与所有车辆的车辆信息进行对比，以判断所有车辆中是否存在与当前车辆结构信息一致，但与当前车牌信息不一致的车辆（S103）；若存在，则将当前车辆标记为套牌车（S104）。
Description
本申请要求于2017年12月1日提交中国专利局，申请号为201711248759.1、发明名称为“车辆套牌检测方法、装置、可读存储介质及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及车辆检验技术领域，特别是涉及一种车辆套牌检测方法、装置、可读存储介质及电子设备。
随着国民经济水平的提升，越来越多的家庭购买了机动车辆，极大提高了日常出行的便捷性。但随着车辆的增多，违法现象也日渐攀升，一些心存侥幸心理的人们，为了能够违反道路交通法规而不用接受处罚，便使用套牌。与此同时，车主从网络购物平台或其他途径就能够轻易的获取仿造的套牌，导致目前仅依靠人工侦察的技术手段，执法部门很难查出套牌车辆。目前使用套牌的违法行为日益猖獗，严重的危害了国家的经济利益、合法车牌车主的权益，同时也将严重破坏道路交通管理秩序，社会危害性不容小觑。
目前在城市的主要道路、市际卡口、高速出入口等都安装的有车辆抓拍系统，在现有的技术条件下能够在各种复杂场景下完成对所有经过的车辆抓拍，进而准确的识别出车牌、车型、颜色、是否有年检标识、前排司乘人员是否有系安全带、有无接打电话等等。但通过以上识别出的信息还是无法判断出车辆是否为套牌车辆。
发明内容
为此，本发明提出一种车辆套牌检测方法，解决现有技术的车辆抓拍系统无法识别出车辆套牌的问题。
本发明车辆套牌检测方法，包括：
对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息；
根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；
若不一致，则获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；
若存在，则将所述当前车辆标记为套牌车。
根据本发明提供的车辆套牌检测方法，基于人脸识别技术和车辆识别技术，主要分析抓拍到的当前车辆与驾驶该当前车辆的驾驶员之间的关系，首先对抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，获得当前车辆的当前车辆信息以及驾驶该当前车辆的当前人脸信息，然后分别对当前车辆信息和当前人脸信息进行对比分析，根据当前车辆信息中的当前车牌信息获取当前车牌信息对应的车主信息，同时根据当前人脸信息获取对应的驾驶员信息，若两者不一致，继续查询该驾驶员名下的所有车辆信息并与当前车辆信息进行对比，最后当在驾驶员名下的所有车辆中存在与当前车辆结构信息一致，但与当前车牌信息不一致的车辆时，可以确定抓拍到的当前车辆是套牌车，并进行标记，该方法能够解决现有技术中车辆抓拍系统不具备识别车辆套牌功能的问题，能够减轻人工侦察套牌车的工作量。
另外，根据本发明上述的车辆套牌检测方法，还可以具有如下附加的技术特征：
进一步地，在本发明的一个实施例中，所述根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶 员信息是否一致的步骤包括：
根据确定的当前车牌信息在车辆信息库中获取与确定的车牌信息对应的车主信息，所述车主信息包括车主的身份信息；
根据所述当前人脸信息在驾驶员数据库中获取与当前人脸信息对应的驾驶员信息，所述驾驶员信息包括驾驶员的身份信息；
判断所述车主的身份信息和所述驾驶员的身份信息是否一致。
进一步地，在本发明的一个实施例中，所述获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息的步骤包括：
判断所述当前驾驶员信息对应的驾驶员名下是否有车辆；
若是，则确定所述当前驾驶员信息对应的驾驶员名下所有车辆的车辆信息，所述所有车辆的车辆信息包括每台车辆的品牌信息、型号信息、颜色信息、车牌信息。
进一步地，在本发明的一个实施例中，所述当前车辆结构信息包括当前车辆的当前品牌信息、当前型号信息和当前颜色信息；
所述将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆的步骤包括：
将所述当前车辆的品牌信息、型号信息、颜色信息、车牌信息分别一一与获取到的所述所有车辆的车辆信息中每台车辆的品牌信息、型号信息、颜色信息、车牌信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆。
进一步地，在本发明的一个实施例中，所述方法还包括：
对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析，以获取与当前车辆对应的当前车辆信息，所述当前车辆信息包括当前车牌信息；
根据车牌信息数据库中预设时间内的车辆记录信息对与当前车牌对应的车辆进行排查，所述车辆记录信息包括车牌信息、与所述车牌信息对应的抓拍时间及抓拍地点；
当在所述车牌信息数据库中查找到所述当前车牌信息对应的当前车牌在预 设时间内在第二卡口出现过时，根据所述当前卡口和所述第二卡口的位置信息、两者之间的路况信息、当前车牌的车速信息以及所述当前车牌在所述当前卡口和所述第二卡口出现的时间间隔信息，判断所述当前车辆和所述第二卡口抓拍到的所述当前车牌对应的车辆是否存在套牌车。
进一步地，在本发明的一个实施例中，所述当前车道卡口抓拍单元包括至少一台用于辅助车牌补光的补光灯，以及至少一台用于辅助抓拍人脸的补光灯；所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析的步骤包括：
采用视频虚拟线圈触发和补光灯联动信号输出使所述当前车道卡口抓拍单元抓拍所述当前车辆图片；
通过ISP成像控制对所述当前车辆图片进行处理，并对处理后的所述当前车辆图进行车辆识别分析和人脸识别分析。
进一步地，在本发明的一个实施例中，所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析的步骤包括：
对所述当前车辆图片进行车辆信息结构化提取，以获取当前车辆结构信息，所述当前车辆结构信息至少包括当前车辆的当前品牌信息、当前型号信息、当前颜色信息；
对所述当前车辆图片进行车牌检测识别，以获取所述当前车牌信息；
对所述当前车辆结构信息和所述当前车牌信息进行汇总，以生成所述当前车辆信息。
进一步地，在本发明的一个实施例中，所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行人脸识别分析的步骤包括：
对所述当前车辆图片进行人脸检测，判断是否存在人脸；
若是，则在人脸所在区域中确定人脸位置，并进行人脸特征提取、确定人脸大小以及各个面部器官的位置信息，以获取所述当前人脸信息。
本发明还提出一种车辆套牌检测装置，解决现有技术的车辆抓拍系统无法识别出车辆套牌的问题，所述装置包括：
抓拍分析模块，用于对当前车道卡口抓拍单元抓拍到的当前车辆图片进行 车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息；
获取判断模块，用于根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；
对比判断模块，用于当所述查找判断模块判断到所述车主信息和所述驾驶员信息不一致时，获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将所述当前车辆信息与所述驾驶员名下的所有车辆的车辆信息进行对比，以判断所述驾驶员名下的所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；
标记模块，用于当所述对比判断模块判断到所述驾驶员名下的所有车辆中存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆时，确定所述当前车辆为套牌车。
本发明还提出一种可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述方法的步骤。
本发明还提出一种电子设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，还包括车道卡口抓拍单元，所述处理器执行所述程序时实现上述方法的步骤。
本发明的车辆套牌检测方法，基于人脸识别技术和车辆识别技术，主要分析抓拍到的当前车辆与驾驶该当前车辆的驾驶员之间的关系，首先对抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，获得当前车辆的当前车辆信息以及驾驶该当前车辆的当前人脸信息，然后分别对当前车辆信息和当前人脸信息进行对比分析，根据当前车辆信息中的当前车牌信息获取当前车牌信息对应的车主信息，同时根据当前人脸信息获取对应的驾驶员信息，若两者不一致，继续查询该驾驶员名下的所有车辆信息并与当前车辆信息进行对比，最后当在驾驶员名下的所有车辆中存在与当前车辆结构信息一致，但与当前车牌信息不一致的车辆时，可以确定抓拍到的当前车辆是套牌车，并进行标记，该方法能够解决现有技术中车辆抓拍系统不具备识别车辆套牌功能的问题，能够减轻人 工侦察套牌车的工作量。
本发明实施例的上述和/或附加的方面和优点从结合下面附图对实施例的描述中将变得明显和容易理解，其中：
图1是根据本发明第一实施例的车辆套牌检测方法的流程图；
图2是图1中车辆识别分析的流程图；
图3是图1中人脸识别分析的流程图；
图4是根据本发明第二实施例的车辆套牌检测方法的流程图；
图5是根据本发明第三实施例的车辆套牌检测装置的结构示意图。
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
请参阅图1，本发明第一实施例提出的车辆套牌检测方法，包括：
S101，对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息。
其中，所述当前人脸信息为驾驶当前车辆的驾驶员人脸信息。当前卡口抓拍单元通常采用摄像头，摄像头可以安装在主要道路、市际卡口、高速出入口等位置处，摄像头例如采用700万像素的高清摄像头，具体实施时，还需要配备与摄像头进行网络通讯的服务器，该服务器例如采用计算机，能够接收摄像头抓拍的图像，并对进行抓拍到的图像进行数据分析和处理，本实施例提供的 方法执行主体即为该服务器。此外，为了提升抓拍效果，当前车道卡口抓拍单元还包括至少一台用于辅助车牌补光的补光灯，以及至少一台用于辅助抓拍人脸的补光灯，以提升摄像头对车辆以及驾驶员的抓拍能力。
该步骤中，可以采用视频虚拟线圈触发和补光灯联动信号输出使当前车道卡口抓拍单元抓拍当前车辆图片，即在距离道路卡口的相应位置设置虚拟线圈，当车辆经过该虚拟线圈时，引起视频虚拟线圈触发，与此同时，配合补光灯联动信号输出，即用于辅助车牌补光的补光灯和用于辅助抓拍人脸的补光灯同时开启，从而使相应的摄像头进行抓拍，得到当前车辆图片。当前车辆图片中同时具有当前车辆以及驾驶该当前车辆的驾驶员的图像。得到当前车辆图片后，可以通过ISP(Image Signal Processing，图像信号处理)成像控制对所述当前车辆图片进行处理，以提升图片质量，具体可以通过采用自动对焦算法、自动曝光算法、自动白平衡算法等对图片进行处理，并对处理后的当前车辆图片进行车辆识别分析和人脸识别分析。
这里需要分别对当前车辆图进行车辆识别分析和人脸识别分析。
第一方面，请参阅图2，在进行车辆识别分析时，具体可以采用以下方法：
S1011a，对所述当前车辆图片进行车辆信息结构化提取，以获取当前车辆结构信息，所述当前车辆结构信息至少包括当前车辆的当前品牌信息、当前型号信息、当前颜色信息；
其中，具体可以采用车辆识别技术，获取当前车辆结构信息，当前车辆结构信息还可以包括当前车辆的总质量、碰撞情况等信息，具体的，可以通过当前品牌信息和当前型号信息在车型数据库中查找当前车辆的总质量信息，可以通过将当前车辆图片中的当前车辆与车型数据库备案的车辆图片进行对比，得出当前车辆的碰撞情况信息。
S1012a，对所述当前车辆图片进行车牌检测识别，以获取所述当前车辆的车牌信息；
其中，具体可以采用车牌号码识别技术对当前车辆图片进行车牌检测识别，需要指出的是，由于车牌号码识别技术比较成熟，因此，车牌号码识别技术也可以集成在当前车道卡口抓拍单元中，即集成在摄像头中。
S1013a，对所述当前车辆结构信息和所述当前车辆的车牌信息进行汇总，以生成所述当前车辆信息。
最后，对当前车辆结构信息和当前车牌信息进行汇总，就可以获取当前车辆信息。
第二方面，请参阅图3，在进行人脸识别分析时，具体可以采用以下方法：
S1011b，对所述当前车辆图片进行人脸检测，判断是否存在人脸；
S1012b，若是，则在人脸所在区域中确定人脸位置，并进行人脸特征提取、确定人脸大小以及各个面部器官的位置信息，以获取所述当前人脸信息。
具体实施时，可以首先在当前车辆图片中确定出驾驶员所在区域，即驾驶员座位附近的像素范围，然后通过基于深度神经网络的人脸检测算法进行人脸检测，判断是否存在人脸。若存在，则进一步对人脸所在区域进行人脸特征提取，确定人脸位置、大小以及各个面部器官的位置信息，最终获取当前人脸信息。
S102，根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；
其中，车辆信息库中存储有车牌信息及与车牌信息对应的车主信息。驾驶员数据库中存储有驾驶员人脸信息及与人脸信息对应的驾驶员信息。具体实施时，车辆信息库和驾驶员数据库也可以集成在一起。
具体实施时，可以采用以下方式进行：
根据确定的当前车牌信息在所述车辆信息库中获取与确定的车牌信息对应 的车主信息，所述车主信息包括车主的身份信息；
根据所述当前人脸信息在驾驶员数据库中获取与当前人脸信息对应的驾驶员信息，所述驾驶员信息包括驾驶员的身份信息；
判断所述车主的身份信息和所述驾驶员的身份信息是否一致。
其中，身份信息可以包括居民身份证上的相关信息。
S103，若不一致，则获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；
其中，若当前车主信息和当前驾驶员信息不一致，即不是当前车牌信息对应的车主本人在驾驶当前车辆，则服务器会从驾驶员数据库中获取当前驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，具体可以采用以下方式进行：
判断所述当前驾驶员信息对应的驾驶员名下是否有车辆；
若是，则确定所述当前驾驶员信息对应的驾驶员名下所有车辆的车辆信息，所述所有车辆的车辆信息包括每台车辆的品牌信息、型号信息、颜色信息、车牌信息。
在获取上述信息后，将所述当前车辆的品牌信息、型号信息、颜色信息、车牌信息分别一一与获取到的所述所有车辆的车辆信息中每台车辆的品牌信息、型号信息、颜色信息、车牌信息进行对比，以判断所述驾驶员名下的所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆。
S104，若存在，则将所述当前车辆标记为套牌车。
其中，若判断到所述驾驶员名下的所有车辆中存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆，由于车辆/驾驶员数据库中存储 的驾驶员名下的所有车辆的相关信息都是正确的，因此，可以认定抓拍到的当前车辆为套牌车，将所述当前车辆标记为套牌车。
进一步的，作为一个具体示例，若确定了当前车辆为套牌车，可以对当前车辆以及驾驶该当前车辆的驾驶员的相关信息进行存储，以便后续警方进行取证分析，也可以主动向警方推送告警消息。
根据本发明实施例的车辆套牌检测方法，基于人脸识别技术和车辆识别技术，主要分析抓拍到的当前车辆与驾驶该当前车辆的驾驶员之间的关系，首先对抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，获得当前车辆的当前车辆信息以及驾驶该当前车辆的当前人脸信息，然后分别对当前车辆信息和当前人脸信息进行对比分析，根据当前车辆信息中的当前车牌信息获取当前车牌信息对应的车主信息，同时根据当前人脸信息获取对应的驾驶员信息，若两者不一致，继续查询该驾驶员名下的所有车辆信息并与当前车辆信息进行对比，最后当在驾驶员名下的所有车辆中存在与当前车辆结构信息一致，但与当前车牌信息不一致的车辆时，可以确定抓拍到的当前车辆是套牌车，并进行标记，该方法能够解决现有技术中车辆抓拍系统不具备识别车辆套牌功能的问题，能够减轻人工侦察套牌车的工作量。
请参阅图4，本发明第二实施例提出的车辆套牌检测方法，包括：
S201，对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析，以获取与当前车辆对应的当前车辆信息，所述当前车辆信息包括当前车牌信息；
其中，该步骤中卡口抓拍单元、车辆识别分析等方法和实现过程与第一实施例相同，本实施例重点说明的是与上一实施例的不同之处，各个实施例之间相同相似的部分未重复描述，可以相互参见。
S202，根据车牌信息数据库中预设时间内的车辆记录信息对与当前车牌对应的车辆进行排查，车辆记录信息包括车牌信息、与所述车牌信息对应的抓拍时间及抓拍地点(；
本实施例中，车牌信息数据库可以预先存储在服务器中，车牌信息数据库是采用大数据处理技术，将所有卡口抓拍到的车辆进行存储并分析，具体实施时，为了减少数据处理量，可以限定一定范围内的卡口，例如对某个省或某个市的所有卡口抓拍到的车辆图片进行存储和分析，从中提取并记录相应的车牌信息，还记录有抓怕时的抓拍时间和抓拍地点，然后不断的积累保存所抓拍到的数据，形成大数据，然后将实时抓拍到的当前车牌信息与该车牌信息数据库中的车辆记录信息进行对比，具体实施时，可以限定比对时间范围，例如将当前车牌与车牌信息数据库中近一个小时内的车辆记录信息进行比对。
S203，当在所述车牌信息数据库中查找到所述当前车牌信息对应的当前车牌在预设时间内在第二卡口出现过时，根据所述当前卡口和所述第二卡口的位置信息、两者之间的路况信息、当前车牌的车速信息以及所述当前车牌在所述当前卡口和所述第二卡口出现的时间间隔信息，判断所述当前车辆和所述第二卡口抓拍到的所述当前车牌对应的车辆是否存在套牌车。
其中，若在车牌信息数据库中查找到在预设时间内当前车牌在第二卡口也出现了，则首先获取当前车牌出现在第二卡口时的时间和地点，然后根据当前卡口和第二卡口的位置信息、两者之间的路况信息、车速信息以及当前车牌在当前卡口和第二卡口出现的时间间隔信息，判断同一辆车在所述时间间隔出现在两个卡口处的可能性，具体实施时，可以采用相应的计算公式或者采用排出法进行分析，例如，当前卡口与第二卡口相距200公里，当前车牌出现在当前第二卡口的时间为10：00am，而当前车牌出现在当前卡口的时间为同一天的10：20am，同一辆车不可能按照上述的两个时间点分别出现在两个卡口，因此可以判定，当前车辆和第二卡口抓拍到的当前车牌对应的车辆中存在套牌车，该分析结果可以推送给警方做进一步分析。本实施例作为第一实施例的补充，缩小了套牌车的检测范围，因此可以提升套牌车辆检测的效率，进一步够减轻人工侦察套牌车的工作量。
需要说明是，本实施例提供的方法同样适用于第一实施例中无法做出判断 的情况，具体包括以下几种情况：
第一种，当前车主信息和当前驾驶员信息一致；
第二种，驾驶当前车辆的驾驶员无驾驶证，即在车辆/驾驶员数据库中没有驾驶员的相关信息；
第三种，驾驶员有驾驶证，但其名下没有车辆；
第四种，驾驶员名下有车，但不存在与当前车辆结构信息一致，但与当前车牌信息不一致的车辆。
对于上述几种情况，均可以采用本实施例提供的方法进行补充检测，以提升套牌车辆检测的效率，够减轻人工侦察套牌车的工作量。
请参阅图5，基于同一发明构思，本发明第三实施例提出的一种车辆套牌检测装置，包括：
抓拍分析模块10，用于对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息；
获取判断模块20，用于根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；
对比判断模块30，用于当所述查找判断模块判断到所述车主信息和所述驾驶员信息不一致时，获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；
标记模块40，用于当所述对比判断模块判断到所述驾驶员名下的所有车辆中存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆时， 将所述当前车辆标记为套牌车。
本实施例中，所述获取判断模块20包括：
第一获取单元201，用于根据确定的当前车牌信息在车辆信息库中获取与确定的车牌信息对应的车主信息，所述车主信息包括车主的身份信息；
第二获取单元202，用于根据所述当前人脸信息在驾驶员中获取与当前人脸信息对应的驾驶员信息，所述驾驶员信息包括驾驶员的身份信息；
判断单元203，用于判断所述车主的身份信息和所述驾驶员的身份信息是否一致。
本实施例中，所述对比判断模块30具体用于：
判断所述当前驾驶员信息对应的驾驶员名下是否有车辆；
若是，则确定所述当前驾驶员信息对应的驾驶员名下所有车辆的车辆信息，所述所有车辆的车辆信息包括每台车辆的品牌信息、型号信息、颜色信息、车牌信息。
本实施例中，所述当前车辆结构信息包括当前车辆的当前品牌信息、当前型号信息和当前颜色信息；
所述对比判断模块30还用于：
将所述当前车辆的品牌信息、型号信息、颜色信息、车牌信息分别一一与获取到的所述所有车辆的车辆信息中每台车辆的品牌信息、型号信息、颜色信息、车牌信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆。
本实施例中，所述车辆套牌检测装置还包括：
排查模块50，根据车牌信息数据库中预设时间内的车辆记录信息对与当前车牌对应的车辆进行排查，所述车辆记录信息包括车牌信息、与所述车牌信息对应的抓拍时间及抓拍地点；
判断模块60，用于当在所述车牌信息数据库中查找到所述当前车牌信息对应的当前车牌在预设时间内在第二卡口出现过时，根据所述当前卡口和所述第二卡口的位置信息、两者之间的路况信息、当前车牌的车速信息以及所述当前车牌在所述当前卡口和所述第二卡口出现的时间间隔信息，判断所述当前车辆或所述第二卡口抓拍到的所述当前车牌对应的车辆是否存在套牌车。
本实施例中，所述当前车道卡口抓拍单元包括至少一台用于辅助车牌补光的补光灯，以及至少一台用于辅助抓拍人脸的补光灯；
所述抓拍分析模块10具体用于：
采用视频虚拟线圈触发和补光灯联动信号输出使所述当前车道卡口抓拍单元抓拍所述当前车辆图片；
通过ISP成像控制对所述当前车辆图片进行处理，并对处理后的所述当前车辆图进行车辆识别分析和人脸识别分析。
本实施例中，所述抓拍分析模块10还用于：
对所述当前车辆图片进行车辆信息结构化提取，以获取当前车辆结构信息，所述当前车辆结构信息至少包括当前车辆的当前品牌信息、当前型号信息、当前颜色信息；
对所述当前车辆图片进行车牌检测识别，以获取所述当前车牌信息；
对所述当前车辆结构信息和所述当前车牌信息进行汇总，以生成所述当前车辆信息。
本实施例中，所述抓拍分析模块10还用于：
对所述当前车辆图片进行人脸检测，判断是否存在人脸；
若是，则在人脸所在区域中确定人脸位置，并进行人脸特征提取、确定人脸大小以及各个面部器官的位置信息，以获取所述当前人脸信息。
本发明实施例提出的车辆套牌检测装置的技术特征和技术效果与本发明实 施例提出的方法相同，在此不予赘述。
此外，本发明的实施例还提出一种可读存储介质，其上存储有计算机指令，该指令被处理器执行时实现上述方法的步骤。
此外，本发明的实施例还提出一种电子设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，还包括车道卡口抓拍单元，所述处理器执行所述程序时实现上述方法的步骤。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，“计算机可读介质”可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。
计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有 用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
Claims (11)
- 一种车辆套牌检测方法，其特征在于，包括：对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息；根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；若不一致，则获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息，并将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；若存在，则将所述当前车辆标记为套牌车。
- 根据权利要求1所述的车辆套牌检测方法，其特征在于，所述根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致的步骤包括：根据确定的当前车牌信息在车辆信息库中获取与确定的车牌信息对应的车主信息，所述车主信息包括车主的身份信息；根据所述当前人脸信息在驾驶员数据库中获取与当前人脸信息对应的驾驶员信息，所述驾驶员信息包括驾驶员的身份信息；判断所述车主的身份信息和所述驾驶员的身份信息是否一致。
- 根据权利要求1所述的车辆套牌检测方法，其特征在于，所述获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信息的步骤包括：判断所述当前驾驶员信息对应的驾驶员名下是否有车辆；若是，则确定所述当前驾驶员信息对应的驾驶员名下所有车辆的车辆信息，所述所有车辆的车辆信息包括每台车辆的品牌信息、型号信息、颜色信息、车 牌信息。
- 根据权利要求3所述的车辆套牌检测方法，其特征在于，所述当前车辆结构信息包括当前车辆的当前品牌信息、当前型号信息和当前颜色信息；所述将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆的步骤包括：将所述当前车辆的品牌信息、型号信息、颜色信息、车牌信息分别一一与获取到的所述所有车辆的车辆信息中每台车辆的品牌信息、型号信息、颜色信息、车牌信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆。
- 根据权利要求1所述的车辆套牌检测方法，其特征在于，所述方法还包括：对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析，以获取与当前车辆对应的当前车辆信息，所述当前车辆信息包括当前车牌信息；根据车牌信息数据库中预设时间内的车辆记录信息对与当前车牌对应的车辆进行排查，所述车辆记录信息包括车牌信息、与所述车牌信息对应的抓拍时间及抓拍地点；当在所述车牌信息数据库中查找到所述当前车牌信息对应的当前车牌在预设时间内在第二卡口出现过时，根据所述当前卡口和所述第二卡口的位置信息、两者之间的路况信息、当前车牌的车速信息以及所述当前车牌在所述当前卡口和所述第二卡口出现的时间间隔信息，判断所述当前车辆和所述第二卡口抓拍到的所述当前车牌对应的车辆是否存在套牌车。
- 根据权利要求1所述的车辆套牌检测方法，其特征在于，所述当前车道卡口抓拍单元包括至少一台用于辅助车牌补光的补光灯，以及至少一台用于辅助抓拍人脸的补光灯；所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析的步骤包括：采用视频虚拟线圈触发和补光灯联动信号输出使所述当前车道卡口抓拍单元抓拍所述当前车辆图片；通过ISP成像控制对所述当前车辆图片进行处理，并对处理后的所述当前车辆图进行车辆识别分析和人脸识别分析。
- 根据权利要求6所述的车辆套牌检测方法，其特征在于，所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析的步骤包括：对所述当前车辆图片进行车辆信息结构化提取，以获取当前车辆结构信息，所述当前车辆结构信息至少包括当前车辆的当前品牌信息、当前型号信息、当前颜色信息；对所述当前车辆图片进行车牌检测识别，以获取所述当前车牌信息；对所述当前车辆结构信息和所述当前车牌信息进行汇总，以生成所述当前车辆信息。
- 根据权利要求7所述的车辆套牌检测方法，其特征在于，所述对当前车道卡口抓拍单元抓拍到的当前车辆图片进行人脸识别分析的步骤包括：对所述当前车辆图片进行人脸检测，判断是否存在人脸；若是，则在人脸所在区域中确定人脸位置，并进行人脸特征提取、确定人脸大小以及各个面部器官的位置信息，以获取所述当前人脸信息。
- 一种车辆套牌检测装置，其特征在于，包括：抓拍分析模块，用于对当前车道卡口抓拍单元抓拍到的当前车辆图片进行车辆识别分析和人脸识别分析，以获取与当前车辆对应的当前车辆信息和当前人脸信息，所述当前车辆信息包括当前车牌信息和当前车辆结构信息；获取判断模块，用于根据确定的当前车牌信息，获取与确定的当前车牌信息对应的车主信息，根据确定的当前人脸信息，获取与确定的当前人脸信息对应的驾驶员信息，并判断获取的车主信息与获取的驾驶员信息是否一致；对比判断模块，用于当所述查找判断模块判断到所述车主信息和所述驾驶员信息不一致时，获取所述驾驶员信息对应的驾驶员名下的所有车辆的车辆信 息，并将所述当前车辆信息与所述所有车辆的车辆信息进行对比，以判断所述所有车辆中是否存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆；标记模块，用于当所述对比判断模块判断到所述所有车辆中存在与所述当前车辆结构信息一致，但与所述当前车牌信息不一致的车辆时，将所述当前车辆标记为套牌车。
- 一种可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-8任意一项所述的方法。
- 一种电子设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，还包括车道卡口抓拍单元，所述处理器执行所述程序时实现如权利要求1至8任意一项所述的方法。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/626,524 US10762338B2 (en) | 2017-12-01 | 2018-11-27 | Method and apparatus for detecting fake license plates of vehicles, readable storage medium, and electronic device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711248759.1A CN107967806B (zh) | 2017-12-01 | 2017-12-01 | 车辆套牌检测方法、装置、可读存储介质及电子设备 |
| CN201711248759.1 | 2017-12-01 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019105342A1 true WO2019105342A1 (zh) | 2019-06-06 |
Family
ID=61999346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/117685 WO2019105342A1 (zh) | 2017-12-01 | 2018-11-27 | 车辆套牌检测方法、装置、可读存储介质及电子设备 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US10762338B2 (zh) |
| CN (1) | CN107967806B (zh) |
| WO (1) | WO2019105342A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114999173A (zh) * | 2022-05-25 | 2022-09-02 | 广东飞达交通工程有限公司 | 一种基于深度卷积神经网络的道路交通目标属性识别方法 |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967806B (zh) | 2017-12-01 | 2019-10-25 | 深圳励飞科技有限公司 | 车辆套牌检测方法、装置、可读存储介质及电子设备 |
| CN108846316A (zh) * | 2018-05-11 | 2018-11-20 | 北京尚易德科技有限公司 | 一种基于卡口车辆数据的目标人员管控方法及装置 |
| CN110874934B (zh) * | 2018-08-29 | 2021-03-19 | 北京万集科技股份有限公司 | 车牌的识别方法、系统和装置 |
| CN111354194A (zh) * | 2018-12-20 | 2020-06-30 | 中国移动通信集团山东有限公司 | 一种高速公路车辆识别方法及装置 |
| CN109726701A (zh) * | 2019-01-07 | 2019-05-07 | 福建睿思特科技股份有限公司 | 车辆识别方法及系统 |
| CN111723604B (zh) * | 2019-03-19 | 2023-07-25 | 杭州海康威视系统技术有限公司 | 车辆套牌检测方法及装置 |
| CN109859492A (zh) * | 2019-03-27 | 2019-06-07 | 成都市公安科学技术研究所 | 一种识别套牌车的系统和方法 |
| CN110008903B (zh) * | 2019-04-04 | 2022-01-28 | 北京旷视科技有限公司 | 人脸识别方法、装置、系统、存储介质和人脸支付方法 |
| JP7428360B2 (ja) * | 2019-05-20 | 2024-02-06 | ｉ－ＰＲＯ株式会社 | 車両監視システムおよび車両監視方法 |
| CN111368617B (zh) * | 2019-07-31 | 2023-11-24 | 杭州海康威视系统技术有限公司 | 车辆出入数据处理方法及装置 |
| CN111369801B (zh) * | 2019-08-27 | 2021-11-23 | 杭州海康威视系统技术有限公司 | 车辆识别方法、装置、设备和存储介质 |
| CN110648002B (zh) * | 2019-10-08 | 2022-05-10 | 深圳市鹏巨术信息技术有限公司 | 一种车辆诊断方法、装置、设备及可读存储介质 |
| CN110675639B (zh) * | 2019-12-03 | 2020-05-19 | 武汉中科通达高新技术股份有限公司 | 基于卡口过车数据分析套牌车所属真牌的方法 |
| WO2021119977A1 (en) * | 2019-12-17 | 2021-06-24 | Motorola Solutions, Inc. | Image-assisted field verification of query response |
| CN111369805B (zh) * | 2020-01-09 | 2021-08-06 | 杭州海康威视系统技术有限公司 | 套牌检测的方法、装置、电子设备及计算机可读存储介质 |
| US11908172B2 (en) * | 2020-08-19 | 2024-02-20 | Privacy4Cars, Llc | Methods and systems to reduce privacy invasion and methods and systems to thwart same |
| CN112330967B (zh) * | 2020-11-11 | 2022-03-01 | 浙江大华技术股份有限公司 | 套牌车辆的识别方法、装置、系统和计算机设备 |
| CN113158721A (zh) * | 2020-12-16 | 2021-07-23 | 东方网力科技股份有限公司 | 一种车辆套牌的识别方法、装置、设备及存储介质 |
| CN112507939A (zh) * | 2020-12-17 | 2021-03-16 | 青岛以萨数据技术有限公司 | 一种重点车辆检测方法、系统、设备及存储介质 |
| CN112614347B (zh) * | 2020-12-22 | 2022-03-15 | 杭州海康威视系统技术有限公司 | 套牌检测方法、装置、计算机设备及存储介质 |
| CN114141023A (zh) * | 2021-10-15 | 2022-03-04 | 重庆紫光华山智安科技有限公司 | 一种套牌车检测方法、系统、存储介质及终端 |
| CN114005273B (zh) * | 2021-10-18 | 2022-11-25 | 北京中交兴路车联网科技有限公司 | 一种消息提醒的方法、装置、计算机设备及存储介质 |
| CN114283588A (zh) * | 2022-01-07 | 2022-04-05 | 刘高峰 | 一种用于车辆鸣笛抓拍系统防误报的方法 |
| CN115731707B (zh) * | 2022-11-14 | 2024-03-19 | 东南大学 | 一种高速公路车辆交通控制方法和系统 |
| CN117373259B (zh) * | 2023-12-07 | 2024-03-01 | 四川北斗云联科技有限公司 | 高速公路车辆逃费行为识别方法、装置、设备和存储介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6366222B1 (en) * | 1998-05-28 | 2002-04-02 | Edward L. Russell, Jr. | Able to operate tag |
| CN101533557A (zh) * | 2009-03-02 | 2009-09-16 | 上海高德威智能交通系统有限公司 | 交通信息检测方法和交通信息检测装置 |
| CN104700132A (zh) * | 2015-03-20 | 2015-06-10 | 周立成 | 机动车和驾驶员管理识别方法 |
| CN106652437A (zh) * | 2017-03-05 | 2017-05-10 | 赵莉莉 | 智能交通全面实时指挥管控系统 |
| CN107967806A (zh) * | 2017-12-01 | 2018-04-27 | 深圳云天励飞技术有限公司 | 车辆套牌检测方法、装置、可读存储介质及电子设备 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140201213A1 (en) * | 2010-11-03 | 2014-07-17 | Scott A. Jackson | System and method for ranking asset data probability of recovery |
| US8582819B2 (en) * | 2011-11-18 | 2013-11-12 | Xerox Corporation | Methods and systems for improving yield in wanted vehicle searches |
| CN103700148B (zh) * | 2013-12-13 | 2016-04-06 | 江苏大学 | 一种电动车停车场无线监控系统及防盗方法 |
| WO2016157196A1 (en) * | 2015-04-02 | 2016-10-06 | Fst21 Ltd | Portable identification and data display device and system and method of using same |
-
2017
- 2017-12-01 CN CN201711248759.1A patent/CN107967806B/zh active Active
-
2018
- 2018-11-27 US US16/626,524 patent/US10762338B2/en active Active
- 2018-11-27 WO PCT/CN2018/117685 patent/WO2019105342A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6366222B1 (en) * | 1998-05-28 | 2002-04-02 | Edward L. Russell, Jr. | Able to operate tag |
| CN101533557A (zh) * | 2009-03-02 | 2009-09-16 | 上海高德威智能交通系统有限公司 | 交通信息检测方法和交通信息检测装置 |
| CN104700132A (zh) * | 2015-03-20 | 2015-06-10 | 周立成 | 机动车和驾驶员管理识别方法 |
| CN106652437A (zh) * | 2017-03-05 | 2017-05-10 | 赵莉莉 | 智能交通全面实时指挥管控系统 |
| CN107967806A (zh) * | 2017-12-01 | 2018-04-27 | 深圳云天励飞技术有限公司 | 车辆套牌检测方法、装置、可读存储介质及电子设备 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114999173A (zh) * | 2022-05-25 | 2022-09-02 | 广东飞达交通工程有限公司 | 一种基于深度卷积神经网络的道路交通目标属性识别方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107967806B (zh) | 2019-10-25 |
| US20200250405A1 (en) | 2020-08-06 |
| US10762338B2 (en) | 2020-09-01 |
| CN107967806A (zh) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019105342A1 (zh) | 车辆套牌检测方法、装置、可读存储介质及电子设备 | |
| CN109800633B (zh) | 一种非机动车交通违法判断方法、装置和电子设备 | |
| CN110659539B (zh) | 一种信息处理方法、装置及机器可读存储介质 | |
| US9082038B2 (en) | Dram c adjustment of automatic license plate recognition processing based on vehicle class information | |
| US11380104B2 (en) | Method and device for detecting illegal parking, and electronic device | |
| CN103886759B (zh) | 一种闯红灯抓拍系统及方法 | |
| Guo et al. | Nighttime vehicle lamp detection and tracking with adaptive mask training | |
| CN106600977A (zh) | 基于多特征识别的违停检测方法及系统 | |
| US20100027009A1 (en) | Method and system for detecting signal color from a moving video platform | |
| WO2017125063A1 (zh) | 违规车辆处理方法及装置 | |
| CN110580808B (zh) | 一种信息处理方法、装置、电子设备及智能交通系统 | |
| CN110909699A (zh) | 视频车辆非导向行驶检测方法、装置及可读存储介质 | |
| CN105046966A (zh) | 即停即离区域的违章停车行为自动检测系统和方法 | |
| CN112509325B (zh) | 一种基于视频深度学习的非现场违法自动甄别方法 | |
| WO2019144416A1 (zh) | 信息处理方法、系统、云处理设备以及计算机程序产品 | |
| CN112651293B (zh) | 一种公路违法设摊事件视频检测方法 | |
| CN111292530A (zh) | 处理违章图片的方法、装置、服务器和存储介质 | |
| CN204856897U (zh) | 一种机动车即停即离区域的违章检测装置 | |
| CN113408364B (zh) | 一种临时车牌识别方法、系统、装置及存储介质 | |
| Ali et al. | License plate recognition system | |
| Persada et al. | Automatic face and VLP’s recognition for smart parking system | |
| CN109344829A (zh) | 一种高速铁路列车的车号识别方法及装置 | |
| CN108985197B (zh) | 基于多算法融合的出租车驾驶员吸烟行为的自动检测方法 | |
| CN111652137A (zh) | 违法车辆检测方法、装置、计算机设备和存储介质 | |
| CN114693722B (zh) | 一种车辆行驶行为检测方法、检测装置及检测设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18883343 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 30.09.2020) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18883343 Country of ref document: EP Kind code of ref document: A1 |