WO2022105019A1 - 一种车辆卡口设备抓拍质量评估方法、装置及可读介质 - Google Patents

一种车辆卡口设备抓拍质量评估方法、装置及可读介质 Download PDF

Info

Publication number
WO2022105019A1
WO2022105019A1 PCT/CN2020/139846 CN2020139846W WO2022105019A1 WO 2022105019 A1 WO2022105019 A1 WO 2022105019A1 CN 2020139846 W CN2020139846 W CN 2020139846W WO 2022105019 A1 WO2022105019 A1 WO 2022105019A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
license plate
snapshot
image
value
Prior art date
Application number
PCT/CN2020/139846
Other languages
English (en)
French (fr)
Inventor
范志建
陈生坚
李仁杰
陈延行
江文涛
张翔
Original Assignee
罗普特科技集团股份有限公司
罗普特(厦门)系统集成有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 罗普特科技集团股份有限公司, 罗普特(厦门)系统集成有限公司 filed Critical 罗普特科技集团股份有限公司
Publication of WO2022105019A1 publication Critical patent/WO2022105019A1/zh

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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

Definitions

  • the present disclosure relates to the field of vehicle image quality assessment, and in particular, to a method, device, and readable medium for capturing quality assessment of vehicle bayonet equipment.
  • Vehicle snapshot information is very important information in the field of video surveillance.
  • most of the bayonet devices used for vehicle snapshots have recognition functions.
  • the captured images need to be uploaded to the recognition engine for vehicle information recognition.
  • the effect of vehicle recognition depends on the quality of the snapshots, but the snapshots of all devices are good or bad. Good snapshots are good for vehicle recognition, while bad snapshots will waste computing resources, so the judgment of snapshots is crucial. important.
  • the present disclosure provides a method, device and readable medium for evaluating the quality of snapshots of a vehicle bayonet device.
  • a method for evaluating the quality of snapshots of a vehicle bayonet device includes the following steps:
  • Determine the quality evaluation parameter system obtain the result value and each weight of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value; obtain calculation according to each result value and its corresponding weight Score; sum the calculated scores of vehicle structured data, license plate number, license plate structured data, vehicle snapshot clarity and vehicle snapshot blackness value to obtain an evaluation value.
  • the quality evaluation parameter system includes:
  • the sharpness of the vehicle snapshot image is obtained by the Sobel edge detection method, and the specific function is: Among them, G X and G Y represent the image gray value of horizontal and vertical edge detection respectively, and the sharpness result value calculated by function G is L.
  • calculation score of the sharpness of the vehicle snapshot image is S4
  • calculation formula is:
  • w4 is the weight value of the sharpness of the vehicle snapshot image
  • L1 and L2 are coefficients
  • the method for obtaining the blackness value of the vehicle snapshot image includes the following steps: obtaining the pixel value M of the vehicle snapshot image, wherein the number of horizontal pixel points is rows, and the number of vertical pixel points is cols; converting the vehicle snapshot image from RGB to HSV; Traverse each pixel and judge the color of each pixel to obtain the proportion N of black pixels.
  • calculation score of the blackness value of the vehicle snapshot image is S5
  • its calculation formula is:
  • w5 is the weight of the blackness value of the vehicle snapshot image
  • N1 and N2 are coefficients
  • N1 80%
  • N2 50%.
  • a deep learning CNN is used to train and obtain classification for the identification of the vehicle clipping map, the license plate clipping map, and the vehicle snapshot image.
  • the calculation score of the license plate structured data is S2, Among them, the weight of the license plate structured data is w2, the license plate type is a, the value of a is 0 or 1, the color of the license plate is b, and the value of b is 0 or 1.
  • the vehicle structured data calculation score is S3, Among them, the vehicle structured data weight is w3, the vehicle type is c, the value of c is 0 or 1, the color of the body is d, the value of d is 0 or 1, the brand of vehicle is e, and the value of e is 0 or 1.
  • the method for obtaining a cropped image of the vehicle includes: detecting the width and position of the vehicle in the snapshot of the vehicle, and selecting the position of the vehicle closest to the center position and the largest proportion of the vehicle to obtain the cropped position.
  • Another aspect of the present disclosure provides a device for evaluating the quality of snapshots of a vehicle bayonet device, the device comprising:
  • the image acquisition module is used for the snapshot of the vehicle bayonet device to perform vehicle detection to obtain the snapshot of the vehicle with vehicle characteristics;
  • the image processing module is used for retrieving the vehicle position in the vehicle snapshot and cropping to obtain the vehicle cropping image with the complete vehicle; and detecting the position of the license plate in the vehicle cropping image, and performing the cropping to obtain the license plate cropping image;
  • the image quality evaluation module is used to determine the quality evaluation parameter system, and obtain the result values and respective weights of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value; according to each result value and its corresponding weight to obtain the calculation score; sum up the calculation scores of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value to obtain the evaluation value.
  • Another aspect of the present disclosure provides a computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the computer program.
  • Another aspect of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the above-mentioned method for evaluating the snapshot quality of a vehicle bayonet device.
  • the present disclosure extracts the vehicle clipping map and the license plate clipping map from the snapshot of the bayonet device, and extracts the vehicle structured data, license plate number, license plate structured data, and vehicle snapshot based on the device snapshot map, the vehicle clipping map and the license plate clipping map.
  • Judgment values are obtained from five angles of sharpness and vehicle snapshot blackness value, and a large number of up-to-standard and sub-standard license plates are collected for database feature training, and manual judgment combined with the training results are used as the judgment parameters for each judgment standard. Comprehensively judge the quality, so as to capture the quality of the vehicle bayonet equipment for evaluation.
  • FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
  • FIG. 2 is a flowchart of a method for evaluating the snapshot quality of a vehicle bayonet device according to an embodiment of the present disclosure
  • FIG. 3 is a first effect diagram of the detection effect of the snapshot image of multiple vehicles of the bayonet device according to an embodiment of the present disclosure
  • FIG. 4 is a second view of the detection effect of the snapshot image of multiple vehicles of the bayonet device according to an embodiment of the present disclosure
  • FIG. 5 is a night snapshot of a bayonet device according to an embodiment of the present disclosure, situation 1;
  • Fig. 6 is a night snapshot of a bayonet device according to an embodiment of the present disclosure, situation 2;
  • FIG. 7 is a structural diagram of a device for evaluating the snapshot quality of a vehicle bayonet device according to an embodiment of the present disclosure
  • FIG. 8 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present application.
  • FIG. 1 shows an exemplary system architecture 100 of a method for processing information or an apparatus for processing information to which embodiments of the present application may be applied.
  • the system architecture 100 may include terminal devices 101 , 102 , and 103 , a network 104 and a server 105 .
  • the network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 .
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
  • the user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like.
  • Various communication client applications may be installed on the terminal devices 101 , 102 and 103 , such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, and the like.
  • the terminal devices 101, 102, 103 may be various electronic devices with communication functions, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.
  • the server 105 may be a server that provides various services, such as a background information processing server that processes the verification request information sent by the terminal devices 101 , 102 and 103 .
  • the background information processing server can analyze and process the received verification request information, and obtain a processing result (for example, verification success information used to indicate that the verification request is a legitimate request).
  • the method for processing information provided by the embodiments of the present application is generally executed by the server 105 , and accordingly, the apparatus for processing information is generally set in the server 105 .
  • the methods for sending information provided in the embodiments of the present application are generally performed by terminal devices 101 , 102 , and 103 .
  • the server may be hardware or software.
  • the server can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server.
  • the server is software, it can be implemented as a plurality of software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module. There is no specific limitation here.
  • terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.
  • a method for evaluating the quality of snapshots of vehicle bayonet equipment includes the following steps:
  • S1 Take a snapshot of the vehicle bayonet device, and perform vehicle detection to obtain a snapshot of the vehicle with vehicle characteristics;
  • S2 retrieve the position of the vehicle in the vehicle snapshot, and crop it to obtain a cropped image of the vehicle with the complete vehicle;
  • S4 Determine the quality evaluation parameter system, and obtain the result values and respective weights of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value; Obtain calculation scores; sum the calculation scores of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value to obtain an evaluation value.
  • vehicle detection is performed first.
  • Vehicle detection is a necessary step, because there will be various types of pictures uploaded by the device, and not every picture contains vehicles.
  • the vehicle detection method can use deep learning CNN for training to obtain classifiers to intelligently identify pictures containing vehicles. .
  • S2 retrieve the position of the vehicle in the vehicle snapshot, and crop it to obtain a cropped image of the vehicle with the complete vehicle;
  • this step is entered. If there is only one vehicle in the picture, the position of the vehicle is directly selected and cropped; if the picture contains multiple vehicles, the vehicle selection and cropping are performed.
  • the method is: detect the width and position of the vehicle in the vehicle snapshot, and select the position of the vehicle closest to the center position and the largest proportion to obtain the clipping position.
  • the captured picture contains multiple vehicles, first select the vehicle, and the box in the illustration effect is For vehicle selection, the cropping position selects the vehicle position closest to the center position and the largest proportion, such as the black vehicle in Figure 3 and the front white vehicle in Figure 4.
  • the position of the license plate is detected based on the cropped image of the vehicle obtained in step S2, and the license plate detection method can use a deep learning CNN to train to obtain a classifier to intelligently identify pictures containing license plates.
  • the license plate clipping is performed to obtain the license plate clipping map.
  • S4 Determine the quality evaluation parameter system, and obtain the result values and respective weights of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value; Obtain calculation scores; sum the calculation scores of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value to obtain an evaluation value.
  • the quality assessment parameter system includes:
  • a vehicle clipping image is identified to obtain vehicle structured data with vehicle type, body color and vehicle brand characteristics
  • a license plate clipping image is identified to obtain a license plate number
  • a license plate clipping image is identified and obtained License plate structured data with license plate type and license plate color features can be calculated by training a classifier, or other methods that can achieve this effect.
  • the calculation score of the vehicle structured data is S3, the calculation score of the license plate number is S1, the calculation score of the license plate structured data is S2, the calculation score of the clarity of the vehicle snapshot is S4, and the blackness of the vehicle snapshot is S4.
  • the license plate structured data includes license plate type a, license plate color b, license plate structured data calculation score S2, license plate structured data weight w2, if the license plate type is detected, the value of a is 1, if If the license plate cannot be detected, the value of a is 0. If the color of the license plate is detected, the value of b is 1. If the color of the license plate cannot be detected, the value of b is 0, and the score is calculated from the structured data of the license plate.
  • the vehicle structured data includes vehicle type c, body color d and vehicle brand feature e
  • the vehicle structured data calculation score is S3
  • the vehicle structured data weight is w3
  • the calculation score of the sharpness of the snapshot of the vehicle is S4, the weight of the sharpness of the snapshot of the vehicle is w4, and the sharpness of the snapshot of the vehicle is obtained by using the Sobel edge detection method, and the specific function is: Among them, G X and G Y represent the image gray value of horizontal and vertical edge detection respectively, and the final sharpness calculation result value is L calculated by the function G.
  • the specific calculation method of the calculation score S4 for the clarity of the vehicle snapshot image is as follows:
  • the blackness value is to calculate the proportion of black pixels to the total pixels. For example, if there are 10,000 total pixels and 1,000 black pixels, the blackness value is 10%.
  • the method for obtaining the blackness value of the vehicle snapshot image includes the following steps: obtaining the pixel value M of the vehicle snapshot image, wherein the number of horizontal pixel points is rows, and the number of vertical pixel points is cols; converting the vehicle snapshot image from RGB to HSV; Traverse each pixel and judge the color of each pixel to obtain the proportion N of black pixels.
  • RGB Red, Green, Blue
  • Table 1 HSV color system values for colors
  • the S value is obtained, and according to the S value, the quality level of the snapshot image is obtained, see Table 2.
  • the sequence of steps from S1 to S4 is not fixed. It can also be that after obtaining a snapshot of the vehicle bayonet device, vehicle detection is performed on the snapshot to determine the number and position of internal vehicles.
  • vehicle detection is performed on the snapshot to determine the number and position of internal vehicles.
  • Select the vehicle especially when multiple vehicles are detected, select the position of the vehicle closest to the center and the vehicle with the largest proportion, and perform cropping based on the selected position to obtain a vehicle cropping map, identify the vehicle cropping map, and obtain vehicle structured data. , such as vehicle type value c, body color value d and vehicle brand feature value e, and then detect based on the vehicle clipping map, determine the position of the license plate, and cut it to obtain the license plate clipping map, identify the license plate clipping map, and obtain the license plate structure.
  • Data such as license plate type value a, license plate color value b; then convert the license plate clipping image into a grayscale image and identify it to determine whether the license plate number can be recognized to obtain the license plate number value; , license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value, according to each result value and its corresponding weight to obtain the calculation score, and sum the calculation score to obtain the evaluation value.
  • FIG. 7 another aspect of the present disclosure provides an evaluation device for capturing quality of a vehicle bayonet device, the device comprising:
  • the image acquisition module is used for the snapshot of the vehicle bayonet device to perform vehicle detection to obtain the snapshot of the vehicle with vehicle characteristics;
  • the image processing module is used for retrieving the vehicle position in the vehicle snapshot and cropping to obtain the vehicle cropping image with the complete vehicle; and detecting the position of the license plate in the vehicle cropping image, and performing the cropping to obtain the license plate cropping image;
  • the image quality evaluation module is used to determine the quality evaluation parameter system, and obtain the result values and respective weights of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value; according to each result value and its corresponding weight to obtain the calculation score; sum up the calculation scores of vehicle structured data, license plate number, license plate structured data, vehicle snapshot image clarity and vehicle snapshot image blackness value to obtain the evaluation value.
  • the vehicle clipping map and the license plate clipping map are extracted from the snapshot of the bayonet equipment, and the vehicle structured data, the license plate number, and the license plate structure are extracted from the device snapshot map, the vehicle clipping map, and the license plate clipping map.
  • the judgment value is obtained from five angles: data, vehicle snapshot image clarity and vehicle snapshot image blackness value, and a large number of qualified and unqualified license plates are collected for database building feature training, and manual judgment and training results are used as the judgment parameters for each judgment standard.
  • the quality of the snapshots of the bayonet equipment is comprehensively judged, so as to evaluate the quality of the snapshots of the vehicle bayonet equipment.
  • a computer system 800 includes a central processing unit (CPU) 801, which can be loaded into a random access memory (RAM) 803 according to a program stored in a read only memory (ROM) 802 or a program from a storage section 808 Instead, various appropriate actions and processes are performed.
  • RAM random access memory
  • ROM read only memory
  • various programs and data required for the operation of the system 800 are also stored.
  • the CPU 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804.
  • An input/output (I/O) interface 805 is also connected to bus 804 .
  • the following components are connected to the I/O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 808 including a hard disk, etc.; Communication section 809 of the network interface card, etc.
  • the communication section 809 performs communication processing via a network such as the Internet.
  • a drive 810 is also connected to the I/O interface 805 as needed.
  • a removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 810 as needed so that a computer program read therefrom is installed into the storage section 808 as needed.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication portion 809, and/or installed from the removable medium 811.
  • CPU central processing unit
  • the above-described functions defined in the method of the present application are performed.
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable medium, or any combination of the above two.
  • the computer readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable Read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for performing the operations of the present application may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional procedural programming language - such as "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider e.g., using an Internet service provider through Internet connection.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments of the present application may be implemented in a software manner, and may also be implemented in a hardware manner.
  • the described unit can also be set in the processor, for example, it can be described as: a processor includes a receiving module, an acquiring module, a determining module, a calculating module and a generating module.
  • a processor includes a receiving module, an acquiring module, a determining module, a calculating module and a generating module.
  • the names of these units do not constitute a limitation on the unit itself under certain circumstances, for example, the receiving unit may also be described as "in response to determining that the verification request information includes the user name, request time, user signature code and The client-side application coding, the module that obtains the preset and target user's configuration information".
  • the present application also provides a computer-readable medium.
  • the computer-readable medium may be included in the server described in the above embodiments, or may exist independently without being assembled into the server.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the server, the server is made to: receive the verification request information sent by the client of the target user; in response to determining the verification request information Including user name, request time, user signature code and client application code, to obtain the preset configuration information of the target user, wherein the configuration information includes the preset user password corresponding to the user name; the verification is determined according to the request time.
  • the server application encoding is obtained by calculation; in response to determining that the server application encoding matches the client application encoding, verification success information for indicating that the verification request is a legitimate request is generated.
  • the above-mentioned computer-readable medium may be included in the terminal device described in the above-mentioned embodiments; or may exist alone without being assembled into the terminal device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the terminal device, the terminal device: acquires user information input by the target user, wherein the user information includes a user name and a user password; Based on the user information, generate the user signature code used to characterize the target user; determine the request time; calculate the client application code based on the user password, request time and user signature code; generate the user name, request time, user signature code and client The verification request information encoded by the terminal application, and the verification request information is sent to the server.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

公开了一种车辆卡口设备抓拍质量评估方法及装置，包括：图像获取模块、图像处理模块及图像质量评估模块，通过对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值，从而达到对卡口设备的建设的质量进行评估的目的。

Description

一种车辆卡口设备抓拍质量评估方法、装置及可读介质
相关申请
本申请要求保护在2020年11月20日提交的申请号为202011308881.5的中国专利申请的优先权，该申请的全部内容以引用的方式结合到本文中。
技术领域
本公开涉及车辆图像质量评估领域，并且特别涉及一种车辆卡口设备抓拍质量评估方法、装置及可读介质。
背景技术
车辆抓拍信息是视频监控领域中非常重要的信息，目前大多数用于车辆抓拍的卡口设备都具备识别功能，不具备识别功能的设备，需要把抓拍的图像上传到识别引擎进行车辆信息识别。车辆识别的效果取决于抓拍图的质量，但所有设备的抓拍图都有好有坏，好的抓拍图利于车辆识别，坏的抓拍图则会浪费计算资源，所以对抓拍图的评判则至关重要。抓拍到的图像上传后可以进行不同质量的分类，然后对卡口设备的抓拍质量进行判断，从而对卡口设备的建设的质量进行评判。
公开内容
为了解决现有技术中无法对卡口设备的建设的质量进行评估的技术问题，本公开提出了一种车辆卡口设备抓拍质量评估方法、装置及可读介质。
本公开一方面提出了一种车辆卡口设备抓拍质量评估方法，包括以下步骤：
对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；
检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
进一步的，所述质量评估参数体系包括：
对车辆裁剪图进行识别以获得具有车辆类型、车身颜色和车辆品牌特征的车辆结构化数据；
对车牌裁剪图进行识别以获得车牌号；
对车牌裁剪图进行识别与获得具有车牌类型和车牌颜色特征的车牌结构化数据；
获取车辆抓拍图的清晰度和黑度值。
进一步的，获取车辆抓拍图的清晰度采用Sobel边缘检测方法获得，具体函数为：
Figure PCTCN2020139846-appb-000001
其中G X和G Y分别表示横向和纵向边缘检测的图像灰度值，函数G计算的清晰度结果值为L。
进一步的，车辆抓拍图清晰度的计算得分为S4，其计算公式为：
Figure PCTCN2020139846-appb-000002
其中，w4为车辆抓拍图清晰度的权重值，L1和L2为系数，L1＝300，L2＝3000。
进一步的，获取车辆抓拍图的黑度值的方法包括以下步骤：获得车辆抓拍图的像素值M，其中，横向像素点数为rows，纵向像素点数为cols；将车辆抓拍图从RGB转换成HSV；遍历每个像素点，并判断每个像素点的颜色，以获得黑色像素点的占比N。
进一步的，所述车辆抓拍图黑度值的计算得分为S5，其计算公式为：
Figure PCTCN2020139846-appb-000003
其中，w5为车辆抓拍图黑度值的权重，N1、N2为系数，N1＝80％、N2＝50％。
进一步的,所述对车辆裁剪图、车牌裁剪图、车辆抓拍图的识别采用深度学习的CNN进行训练获取分类。
进一步的，获得车牌号的计算得分包括：将车牌裁剪图灰度化处理，再进行车牌号识别，若无车牌号，S1＝0，若有车牌号，S1＝w1，其中S1为车牌号计算得分，w1为车牌号的参数权重。
进一步的，车牌结构化数据计算得分为S2，
Figure PCTCN2020139846-appb-000004
其中，车牌结构化数据权重为w2，车牌类型为a，a值为0或1，车牌颜色为b，b值为0或1。
进一步的，车辆结构化数据计算得分为S3，
Figure PCTCN2020139846-appb-000005
其中，车辆结构化数据权重为w3，车辆类型为c，c值为0或1，车身颜色为d，d值为0或1，车辆品牌为e，e值为0或1。
进一步的，获得车辆裁剪图的方法包括：检测车辆抓拍图中的车辆的宽度与位置，选取最靠近中心位置和最大占比的车辆位置以获得裁剪位置。
本公开另一方面提出一种车辆卡口设备抓拍质量评估装置，所述装置包括：
图像获取模块，用于对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
图像处理模块，用于检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；及检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
图像质量评估模块，用于确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
本公开另一方面提出一种计算机设备，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现上述一种车辆卡口设备抓拍质量评估方法。
本公开另一方面提出一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述一种车辆卡口设备抓拍质量评估方法。
本公开通过对卡口设备抓拍图中提取车辆裁剪图和车牌裁剪图，并基于设备抓拍图、车辆裁剪图和车牌裁剪图中从车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值五个角度获得判断值，并且收集大量达标、未达标车牌进行建库特征训练，将人工判断结合训练结果作为各个判断标准的判断参数，对卡口设备抓拍图质量进行综合判断，从而对车辆卡口设备抓拍质量以评估。
附图说明
包括附图以提供对实施例的进一步理解并且附图被并入本说明书中并且构成本说明书的一部分。附图图示了实施例并且与描述一起用于解释本公开的原理。将容易认识到其它实施例和实施例的很多预期优点，因为通过引用以下详细描述，它们变得被更好地理解。附图的元件不一定是相互按照比例的。同样的附图标记指代对应的类似部件。
图1是本申请可以应用于其中的示例性系统架构图；
图2是根据本公开的一个实施例的车辆卡口设备抓拍质量的评估方法的流程图；
图3是根据本公开的一个实施例的卡口设备多辆车辆抓拍图检测效果图一；
图4是根据本公开的一个实施例的卡口设备多辆车辆抓拍图检测效果图二；
图5是根据本公开的一个实施例的卡口设备夜晚抓拍图情况一；
图6是根据本公开的一个实施例的卡口设备夜晚抓拍图情况二；
图7是根据本公开的一个实施例的车辆卡口设备抓拍质量的评估装置结构图；
图8是适于用来实现本申请实施例的终端设备或服务器的计算机系统的结构示意图。
具体实施方式
在以下详细描述中，参考附图，该附图形成详细描述的一部分，并且通过其中可实践本公开的说明性具体实施例来示出。对此，参考描述的图的取向来使用方向术语，例如“顶”、“底”、“左”、“右”、“上”、“下”等。因为实施例的部件可被定位于若干不同取向中，为了图示的目的使用方向术语并且方向术语绝非限制。应当理解的是，可以利用其他实施例或可以做出逻辑改变，而不背离本公开的范围。因此以下详细描述不应当在限制的意义上被采用，并且本公开的范围由所附权利要求来限定。
图1示出了可以应用本申请实施例的用于处理信息的方法或用于处理信息的装置的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如网页浏览器应用、购物类应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等。
终端设备101、102、103可以是具有通信功能的各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103发送的校验请求信息进行处理的后台信息处理服务器。后台信息处理服务器可以对接收到的校验请求信息进行分析等处理，并得到处理结果(例如用于表征校验请求为合法请求的校验成功信息)。
需要说明的是，本申请实施例所提供的用于处理信息的方法一般由服务器105执行， 相应地，用于处理信息的装置一般设置于服务器105中。另外，本申请实施例所提供的用于发送信息的方法一般由终端设备101、102、103执行，相应地，用于发送信息的装置一般设置于终端设备101、102、103中。
需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。
如图2所示一种车辆卡口设备抓拍质量评估方法，包括以下步骤：
S1：对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
S2：检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；
S3：检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
S4：确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
在具体实施例中，S1中获取车辆卡口设备的抓拍图后，首先进行车辆检测。车辆检测是必须的一步，因为设备上传的会有各种类型的图片，并不是每个图片内都包含车辆，车辆检测方法可以采用深度学习的CNN进行训练获取分类器以智能识别包含车辆的图片。
S2：检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；
在具体实施例中，当检测到图片含有车辆时，进入该步骤，若图片内仅有一辆车辆，直接选取车辆的位置，进行裁剪；若图片内包含多个车辆时，进行车辆选取及裁剪的方法为：检测车辆抓拍图中的车辆的宽度与位置，选取最靠近中心位置和最大占比的车辆位置以获得裁剪位置。参考图3、图4的效果图(因申请需要将图片效果变更为黑白照片，实际应用时为彩色照片)，抓拍图片内含多辆车辆，首先进行车辆选取，图示效果中的方框即为车辆选取，裁切位置则选取最靠近中心位置和最大占比的车辆位置，如图3中黑色车辆、图4中最前面的白色车辆。
S3：检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
在具体实施例中，基于S2步骤获得的车辆裁剪图，进行车牌位置的检测，车牌检测方法可以采用深度学习的CNN进行训练获取分类器以智能识别包含车牌的图片。当检测到车牌位置后，进行车牌裁剪以获得车牌裁剪图。
S4：确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
在具体实施例中，质量评估参数体系包括：
对车辆裁剪图进行识别以获得具有车辆类型、车身颜色和车辆品牌特征的车辆结构化数据；
对车牌裁剪图进行识别以获得车牌号；
对车牌裁剪图进行识别与获得具有车牌类型和车牌颜色特征的车牌结构化数据；
获取车辆抓拍图的清晰度和黑度值。
在具体实施例中，对车辆裁剪图进行识别以获得具有车辆类型、车身颜色和车辆品牌特征的车辆结构化数据、对车牌裁剪图进行识别以获得车牌号，以及对车牌裁剪图进行识别与获得具有车牌类型和车牌颜色特征的车牌结构化数据均可以采用训练获取分类器进行计算的方式，也可以采用其他可以达到该效果的方式。
在具体实施例中，车辆结构化数据的计算得分为S3、车牌号的计算得分为S1、车牌结构化数据的计算得分为S2、车辆抓拍图清晰度的计算得分为S4和车辆抓拍图黑度值的计算得分为S5，评估值S＝S1+S2+S3+S4+S5，其中各个计算得分的具体获取方式如下。
在具体实施例中，获得车牌号的计算得分S1的方法包括：首先将车牌裁剪图灰度化处理，再进行车牌号识别，w1为车牌号的参数权重。若无车牌号，S1＝0，若有车牌号S1＝w1。
在具体实施例中，车牌结构化数据包括车牌类型为a，车牌颜色为b，车牌结构化数据计算得分为S2，车牌结构化数据权重为w2，若检测出车牌类型，a值为1，若无法检测出车牌，a值为0，若检测出车牌颜色，b值为1，所无法检测出车牌颜色，b值为0，车牌结构化数据计算得分
Figure PCTCN2020139846-appb-000006
在具体实施例中，车辆结构化数据包括车辆类型c、车身颜色d和车辆品牌特征e，车辆结构化数据计算得分为S3，车辆结构化数据权重为w3，若检测出车辆类型，c值为1，若检测不出车辆类型，c值为0，若检测出车身颜色，d值为1，若检测不出车身颜色， d值为0，若检测出车辆品牌，e值为1，若检测不出车辆品牌，d值为0，车辆结构化数据计算得分
Figure PCTCN2020139846-appb-000007
在具体实施例中，车辆抓拍图清晰度的计算得分为S4，车辆抓拍图清晰度的权重值为w4，对于获取车辆抓拍图的清晰度采用Sobel边缘检测方法获得，具体函数为：
Figure PCTCN2020139846-appb-000008
Figure PCTCN2020139846-appb-000009
其中G X和G Y分别表示横向和纵向边缘检测的图像灰度值，通过函数G计算得到最终清晰度计算结果值为L。而车辆抓拍图清晰度的计算得分S4具体计算方式为：
Figure PCTCN2020139846-appb-000010
其中，L1和L2为系数，L1＝300，L2＝3000。
在具体实施例中，如图:5、6所示，在晚上，大多数车辆卡口抓拍时都有补光灯，但是有些补光灯损坏或者老化，以致补光不足，导致抓拍的车辆图片一片漆黑，或者补光后的抓拍图是灰色的，所以需要计算图片的黑色像素点。而黑度值是计算黑色像素点占总像素点的占比，比如总像素点有10000个，黑色像素点有1000个，则黑度值是10％。
具体的，获取车辆抓拍图的黑度值的方法包括以下步骤：获得车辆抓拍图的像素值M，其中，横向像素点数为rows，纵向像素点数为cols；将车辆抓拍图从RGB转换成HSV；遍历每个像素点，并判断每个像素点的颜色，以获得黑色像素点的占比N。
通常我们使用RGB来表示的黑色是(0,0,0)，RGB格式可以看出各个颜色的代表RGB色系值，但不知道各个颜色，R、G、B三个值的范围是多少。而使用HSV色系，可以清楚的得知各个颜色的范围取值，参考表1。
表1：颜色的HSV色系值
Figure PCTCN2020139846-appb-000011
车辆抓拍图黑度值的计算得分为S5，车辆抓拍图黑度值的权重为w5，N1、N2为系数，N1＝80％、N2＝50％。
Figure PCTCN2020139846-appb-000012
根据上述参数求和得出S值，根据S值，得出抓拍图的质量等级，参见表2。
表2：S值对应图片质量等级
分值区间 等级
S>80 优
60<S<＝80 良
30<＝S<60 中
S<30 差
在实际应用中，S1至S4的步骤顺序并不固定顺序，也可以是获取车辆卡口设备的抓拍图后，对抓拍图进行车辆检测，确定内部车辆的数量及位置，当检测到车辆时，选取车辆，特别是当检测到多个车辆时，选取最靠近中心位置和占比最大的车辆位置，基于选取的位置进行裁剪，得到车辆裁剪图，对车辆裁剪图进行识别，获得车辆结构化数据，如车辆类型值c、车身颜色值d和车辆品牌特征值e，然后基于车辆裁剪图进行检测，确定车牌位置，并进行裁剪以获得车牌裁剪图，对车牌裁剪图进行识别，获得车牌结构化数据，如车牌类型值a，车牌颜色值b；再对车牌裁剪图转换成灰度图并进行识别，判断是否可以识别到车牌号，以获得车牌号值；分别对车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值，根据各个结果值和其对应权重以获得计算得分，并将计算得分求和，以获得评估值。
如图7所示，本公开另一方面提出一种车辆卡口设备抓拍质量的评估装置，所述装置包括：
图像获取模块，用于对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
图像处理模块，用于检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；及检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
图像质量评估模块，用于确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
通过本装置及本方法，通过对卡口设备抓拍图中提取车辆裁剪图和车牌裁剪图，并基于设备抓拍图、车辆裁剪图和车牌裁剪图中从车辆结构化数据、车牌号、车牌结构化 数据、车辆抓拍图清晰度和车辆抓拍图黑度值五个角度获得判断值，并且收集大量达标、未达标车牌进行建库特征训练，将人工判断结合训练结果作为各个判断标准的判断参数，对卡口设备抓拍图质量进行综合判断，从而对车辆卡口设备抓拍质量以评估。
如图8所示，计算机系统800包括中央处理单元(CPU)801，其可以根据存储在只读存储器(ROM)802中的程序或者从存储部分808加载到随机访问存储器(RAM)803中的程序而执行各种适当的动作和处理。在RAM 803中，还存储有系统800操作所需的各种程序和数据。CPU 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。
以下部件连接至I/O接口805：包括键盘、鼠标等的输入部分806；包括液晶显示器(LCD)等以及扬声器等的输出部分807；包括硬盘等的存储部分808；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分809。通信部分809经由诸如因特网的网络执行通信处理。驱动器810也根据需要连接至I/O接口805。可拆卸介质811，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器810上，以便于从其上读出的计算机程序根据需要被安装入存储部分808。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分809从网络上被下载和安装，和/或从可拆卸介质811被安装。在该计算机程序被中央处理单元(CPU)801执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读介质或者是上述两者的任意组合。计算机可读介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。 计算机可读的信号介质还可以是计算机可读介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括接收模块、获取模块、确定模块、计算模块和生成模块。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，接收单元还可以被描述为“响应于确定校验请求信息中包括用户名、请求时间、用户签名编码和客户端应用编码，获取预设的、目标用户的配置信息的模块”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的服务器中所包含的；也可以是单独存在，而未装配入该服务器中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该服务器执行 时，使得该服务器：接收目标用户的客户端发送的校验请求信息；响应于确定校验请求信息中包括用户名、请求时间、用户签名编码和客户端应用编码，获取预设的、目标用户的配置信息，其中，配置信息包括预设的、用户名对应的用户密码；根据请求时间确定校验请求信息是否有效，响应于确定有效，确定预设存储区内是否包括用户签名编码；响应于确定不包括，将用户签名编码存储至预设存储区内，以及基于用户密码、请求时间和用户签名编码，计算得到服务端应用编码；响应于确定服务端应用编码和客户端应用编码匹配，生成用于表征校验请求为合法请求的校验成功信息。
另外，上述计算机可读介质可以是上述实施例中描述的终端设备中所包含的；也可以是单独存在，而未装配入该终端设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该终端设备执行时，使得该终端设备：获取目标用户输入的用户信息，其中，用户信息包括用户名和用户密码；基于用户信息，生成用于表征目标用户的用户签名编码；确定请求时间；基于用户密码、请求时间和用户签名编码，计算得到客户端应用编码；生成包括用户名、请求时间、用户签名编码和客户端应用编码的校验请求信息，以及将校验请求信息发送至服务端。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (14)

  1. 一种车辆卡口设备抓拍质量评估方法，其特征在于，包括以下步骤：
    对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
    检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；
    检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
    确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
  2. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，所述质量评估参数体系包括：
    对车辆裁剪图进行识别以获得具有车辆类型、车身颜色和车辆品牌特征的车辆结构化数据；
    对车牌裁剪图进行识别以获得车牌号；
    对车牌裁剪图进行识别与获得具有车牌类型和车牌颜色特征的车牌结构化数据；
    获取车辆抓拍图的清晰度和黑度值。
  3. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，获取车辆抓拍图的清晰度采用Sobel边缘检测方法获得，具体函数为：
    Figure PCTCN2020139846-appb-100001
    其中G X和G Y分别表示横向和纵向边缘检测的图像灰度值，函数G计算的清晰度结果值为L。
  4. 根据权利要求3所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，车辆抓拍图清晰度的计算得分为S4，其计算公式为：
    Figure PCTCN2020139846-appb-100002
    其中，w4为车辆抓拍图清晰度的权重值，L1和L2为系数，L1＝300，L2＝3000。
  5. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，获取车辆抓拍图的黑度值的方法包括以下步骤：
    获得车辆抓拍图的像素值M，其中，横向像素点数为rows，纵向像素点数为cols；将车辆抓拍图从RGB转换成HSV；遍历每个像素点，并判断每个像素点的颜色，以获得黑色像素点的占比N。
  6. 根据权利要求5所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，所述车辆抓拍图黑度值的计算得分为S5，其计算公式为：
    Figure PCTCN2020139846-appb-100003
    其中，w5为车辆抓拍图黑度值的权重，N1、N2为系数，N1＝80％、N2＝50％。
  7. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于,所述对车辆裁剪图、车牌裁剪图、车辆抓拍图的识别采用深度学习的CNN进行训练获取分类器。
  8. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，获得车牌号的计算得分包括：
    将车牌裁剪图灰度化处理，再进行车牌号识别，若无车牌号，S1＝0，若有车牌号，S1＝w1，其中S1为车牌号计算得分，w1为车牌号的参数权重。
  9. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，车牌结构化数据计算得分为S2，
    Figure PCTCN2020139846-appb-100004
    其中，车牌结构化数据权重为w2，车牌类型为a，a值为0或1，车牌颜色为b，b值为0或1。
  10. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，车辆结构化数据计算得分为S3，
    Figure PCTCN2020139846-appb-100005
    其中，车辆结构化数据权重为w3，车辆类型为c，c值为0或1，车身颜色为d，d值为0或1，车辆品牌为e，e值为0或1。
  11. 根据权利要求1所述的一种车辆卡口设备抓拍质量评估方法，其特征在于，获得车辆裁剪图的方法包括：检测车辆抓拍图中的车辆的宽度与位置，选取最靠近中心位置和最大占比的车辆位置以获得裁剪位置。
  12. 一种车辆卡口设备抓拍质量评估装置，其特征在于，所述装置包括：
    图像获取模块，用于对车辆卡口设备的抓拍图，进行车辆检测以获得具有车辆特征的车辆抓拍图；
    图像处理模块，用于检索车辆抓拍图中的车辆位置，并进行裁剪以获得具有完整车辆的车辆裁剪图；及检测车辆裁剪图中的车牌位置，并进行裁剪以获得车牌裁剪图；
    图像质量评估模块，用于确定质量评估参数体系，获得车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的结果值及各个权重；根据各个结果值和其对应权重以获得计算得分；将车辆结构化数据、车牌号、车牌结构化数据、车辆抓拍图清晰度和车辆抓拍图黑度值的计算得分求和，以获得评估值。
  13. 一种计算机设备，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求中1至11任一所述的一种车辆卡口设备抓拍质量评估方法。
  14. 一种计算机可读存储介质，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1-11中任一所述的一种车辆卡口设备抓拍质量评估方法。
PCT/CN2020/139846 2020-11-20 2020-12-28 一种车辆卡口设备抓拍质量评估方法、装置及可读介质 WO2022105019A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011308881.5A CN112270309A (zh) 2020-11-20 2020-11-20 一种车辆卡口设备抓拍质量评估方法、装置及可读介质
CN202011308881.5 2020-11-20

Publications (1)

Publication Number Publication Date
WO2022105019A1 true WO2022105019A1 (zh) 2022-05-27

Family

ID=74339750

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/139846 WO2022105019A1 (zh) 2020-11-20 2020-12-28 一种车辆卡口设备抓拍质量评估方法、装置及可读介质

Country Status (2)

Country Link
CN (1) CN112270309A (zh)
WO (1) WO2022105019A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376315A (zh) * 2022-08-09 2022-11-22 北京交通发展研究院 一种面向路网排放核算的多层级卡口质量控制方法
CN115457777A (zh) * 2022-09-06 2022-12-09 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113012439B (zh) * 2021-03-29 2022-06-21 北京百度网讯科技有限公司 车辆检测方法、装置、设备和存储介质
CN113362612A (zh) * 2021-06-02 2021-09-07 国电内蒙古东胜热电有限公司 一种车辆识别方法及系统
CN113660461B (zh) * 2021-08-09 2024-03-15 青岛海信网络科技股份有限公司 一种视频过车设备性能的评价方法、装置及设备
CN113408550B (zh) * 2021-08-17 2021-11-26 中国建筑第五工程局有限公司 基于图像处理的智能称重管理系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484655A (zh) * 2014-12-18 2015-04-01 广州市华标科技发展有限公司 一种基于视频图像的车牌区域定位方法及系统
WO2019148912A1 (zh) * 2018-02-02 2019-08-08 杭州海康威视数字技术股份有限公司 一种图像处理方法、装置、电子设备及存储介质
CN111611863A (zh) * 2020-04-22 2020-09-01 浙江大华技术股份有限公司 车牌图像质量评价方法、装置以及计算机设备
CN111932496A (zh) * 2020-07-01 2020-11-13 浙江大华技术股份有限公司 车牌图像质量的确定方法、装置、存储介质及电子装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170140237A1 (en) * 2015-11-13 2017-05-18 Hunter Engineering Company Methods For Vehicle Identification And Specification Recall With Localization Optimization For License Plate Recognition
CN110969160B (zh) * 2019-11-21 2023-04-14 合肥工业大学 一种基于深度学习的车牌图像校正、识别方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484655A (zh) * 2014-12-18 2015-04-01 广州市华标科技发展有限公司 一种基于视频图像的车牌区域定位方法及系统
WO2019148912A1 (zh) * 2018-02-02 2019-08-08 杭州海康威视数字技术股份有限公司 一种图像处理方法、装置、电子设备及存储介质
CN111611863A (zh) * 2020-04-22 2020-09-01 浙江大华技术股份有限公司 车牌图像质量评价方法、装置以及计算机设备
CN111932496A (zh) * 2020-07-01 2020-11-13 浙江大华技术股份有限公司 车牌图像质量的确定方法、装置、存储介质及电子装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376315A (zh) * 2022-08-09 2022-11-22 北京交通发展研究院 一种面向路网排放核算的多层级卡口质量控制方法
CN115376315B (zh) * 2022-08-09 2023-10-24 北京交通发展研究院 一种面向路网排放核算的多层级卡口质量控制方法
CN115457777A (zh) * 2022-09-06 2022-12-09 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法
CN115457777B (zh) * 2022-09-06 2023-09-19 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法

Also Published As

Publication number Publication date
CN112270309A (zh) 2021-01-26

Similar Documents

Publication Publication Date Title
WO2022105019A1 (zh) 一种车辆卡口设备抓拍质量评估方法、装置及可读介质
JP2020504358A (ja) 画像ベースの車両損害評価方法、装置、およびシステム、ならびに電子デバイス
CN110348522B (zh) 一种图像检测识别方法及系统、电子设备、图像分类网络优化方法及系统
US20120070041A1 (en) System And Method For Face Verification Using Video Sequence
KR102002024B1 (ko) 객체 라벨링 처리 방법 및 객체 관리 서버
CN109558792B (zh) 一种基于样本和特征检测互联网徽标内容的方法和系统
WO2023178930A1 (zh) 图像识别方法、训练方法、装置、系统及存储介质
WO2019056503A1 (zh) 门店监控评价方法、装置及存储介质
CN110958467B (zh) 视频质量预测方法和装置及电子设备
CN111563398A (zh) 用于确定目标物的信息的方法和装置
CN113947570B (zh) 一种基于机器学习算法和计算机视觉的裂纹辨识方法
CN113255590A (zh) 一种缺陷检测模型训练方法、缺陷检测方法、装置及系统
US20230049656A1 (en) Method of processing image, electronic device, and medium
CN111523400B (zh) 视频代表帧提取方法及装置
CN111369557B (zh) 图像处理方法、装置、计算设备和存储介质
EP4220545A1 (en) Abnormality detection device, abnormality detection method, and abnormality detection system
CN117854402A (zh) 显示屏的异常显示检测方法、装置、终端设备
CN111523399A (zh) 敏感视频检测及装置
US20230048649A1 (en) Method of processing image, electronic device, and medium
CN111582278A (zh) 人像分割方法、装置及电子设备
CN116468914A (zh) 页面对比方法、装置、存储介质及电子设备
CN116977256A (zh) 缺陷检测模型的训练方法、装置、设备及存储介质
CN115147752A (zh) 一种视频分析方法、装置及计算机设备
CN110213457B (zh) 一种图像传输方法及装置
CN115950887B (zh) 电子变压器缺陷检测方法、存储介质以及设备

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: 20962310

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20962310

Country of ref document: EP

Kind code of ref document: A1

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 19.10.2023)