阅读说明：本技术 车辆信息的验证方法和系统、终端和计算机可读存储介质 (Vehicle information verification method and system, terminal, and computer-readable storage medium ) 是由 王智恒 张天明 王树栋 薛韬略 李�杰 孟辉 陈天钰 戴桂婷 吴朝辉 周多庆 王 于 2020-01-22 设计创作，主要内容包括：本发明提供了一种车辆信息的验证方法和系统、终端和计算机可读存储介质,其中,车辆信息的验证方法包括：获取服务器随机生成的第一坐标信息,根据第一坐标信息在预设显示范围内确定图像获取区域；在预设显示范围内输出第一图像信息,并在第一图像信息与图像获取区域相重合的区域内截取第二图像信息；根据第二图像信息对车辆信息进行验证。应用了本发明提供的技术方案,有效地避免了部分司机通过预先录制的“伪造”视频欺骗车辆信息验证,极大的提高了车辆信息验证的可靠性。在通过CNN网络对车辆图像进行搜索识别时,仅需在图像获取区域内搜索目标车辆,而无需进行全图搜索,极大地降低了计算所需资源,有效地提高了识别速度。(The invention provides a vehicle information verification method and system, a terminal and a computer readable storage medium, wherein the vehicle information verification method comprises the following steps: acquiring first coordinate information randomly generated by a server, and determining an image acquisition area in a preset display range according to the first coordinate information; outputting first image information in a preset display range, and intercepting second image information in an area where the first image information is overlapped with an image acquisition area; and verifying the vehicle information according to the second image information. By applying the technical scheme provided by the invention, the vehicle information verification is effectively prevented from being deceived by part of drivers through the prerecorded 'fake' video, and the reliability of the vehicle information verification is greatly improved. When the vehicle image is searched and identified through the CNN network, only a target vehicle needs to be searched in the image acquisition area, and the whole image search is not needed, so that resources required by calculation are greatly reduced, and the identification speed is effectively improved.)

1. A vehicle information verification method for a terminal, the vehicle information verification method comprising:

acquiring first coordinate information randomly generated by a server, and determining an image acquisition area in a preset display range according to the first coordinate information;

Outputting first image information in the preset display range, and intercepting second image information in an area where the first image information is overlapped with the image acquisition area;

and verifying the vehicle information according to the second image information.

2. The vehicle information verification method according to claim 1, characterized in that, before the step of verifying the vehicle information from the second image information, the vehicle information verification method further comprises:

detecting the second image information through a vehicle detection model;

and determining that a vehicle image and a license plate image exist in the second image information, and the area ratio of the vehicle image in the second image information accords with a preset ratio range, and executing the step of verifying the vehicle information according to the second image information.

3. The method for verifying the vehicle information according to claim 2, wherein the step of verifying the vehicle information based on the second image information specifically includes:

acquiring coordinate information of a license plate in the second image information through the vehicle detection model;

determining that the coordinate information of the license plate is matched with preset license plate coordinate information, the vehicle image is a complete vehicle image, determining that the second image information is a qualified image, and acquiring a license plate number corresponding to the license plate through a license plate recognition model;

And determining that the license plate number is matched with a preset license plate number, and determining that the vehicle information passes verification.

4. The method according to claim 3, wherein an image acquisition device is provided on the terminal, and before the step of outputting the first image information within the preset display range, the method further comprises:

acquiring video information through the image acquisition device, and converting the video information into continuous frame images;

and determining the second image information according to the frame image.

5. The method for verifying the vehicle information according to claim 4, wherein before the step of obtaining the license plate number corresponding to the license plate through the license plate recognition model, the method for verifying the vehicle information further comprises:

intercepting a video clip with preset duration in the video information, and converting the video clip into a continuous frame image to be detected;

and determining that all the frame images to be detected are qualified images, and executing the step of obtaining the license plate number corresponding to the license plate through the license plate recognition model.

6. The verification method of the vehicle information according to any one of claims 2 to 5, characterized in that, prior to the step of detecting the second image information by the vehicle detection model, the verification method of the vehicle information further includes:

Acquiring historical vehicle image information and acquiring a preset detection model;

and marking license plate position information, license plate coordinate information and license plate information in the historical vehicle information to form a vehicle recognition training set, and training the preset detection model through the vehicle recognition training set to obtain the vehicle detection model.

7. The method for verifying vehicle information according to any one of claims 3 to 5, wherein, before the step of obtaining the license plate number corresponding to the license plate by the license plate recognition model, the method for verifying vehicle information further comprises:

acquiring a preset character recognition model;

and training the preset character recognition model based on a CNN convolutional neural network, an LSTM long-short term memory network and a CTC time sequence loss function to obtain the license plate recognition model.

8. The vehicle information verification method according to claim 5, wherein the preset proportion range is: greater than or equal to 40% and less than or equal to 80%;

the preset duration range is as follows: greater than or equal to 2 seconds and less than or equal to 5 seconds.

9. A vehicle information verification system, comprising:

a memory configured to store a computer program;

A processor configured to execute the computer program to implement the vehicle information verification method according to any one of claims 1 to 8.

10. A terminal, comprising:

an image acquisition device configured to acquire video information;

a display device configured to display image information, the display device having a display area including a preset display area;

the verification system of vehicle information according to claim 9, being connected with the image acquisition device and the display device.

11. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing a method of verifying vehicle information according to any one of claims 1 to 8.

Technical Field

The invention relates to the technical field of image recognition, in particular to a vehicle information verification method, a vehicle information verification system, a terminal and a computer-readable storage medium.

Background

In the related art, for the online car appointment platform, the registered vehicle information needs to be verified, and video verification or image verification is generally adopted. And the general image verification has the possibility of cheating, and part of drivers can forcedly upload vehicle video deception audit shot in an off-site mode, so that the vehicle information verification result is inaccurate.

Disclosure of Invention

The present invention is directed to solving at least one of the problems of the prior art or the related art.

To this end, a first aspect of the invention proposes a method of verifying vehicle information.

A second aspect of the invention proposes a verification system of vehicle information.

A third aspect of the present invention provides a terminal.

A fourth aspect of the present invention is directed to a computer-readable storage medium.

In view of this, a first aspect of the present invention provides a method for verifying vehicle information, which is used for a terminal, and includes: acquiring first coordinate information randomly generated by a server, and determining an image acquisition area in a preset display range according to the first coordinate information; outputting first image information in a preset display range, and intercepting second image information in an area where the first image information is overlapped with an image acquisition area; and verifying the vehicle information according to the second image information.

In the technical scheme, the terminal can be a mobile phone held by a user (such as a driver), when vehicle information is verified through the terminal, at least part of a display screen of the terminal is used for displaying an image acquired by a camera of the terminal, the part is recorded as a preset display range, and the image acquired by the camera is first image information. Meanwhile, the server randomly generates first coordinate information and sends the first coordinate information to the terminal, an image acquisition area can be determined in the display range according to the first coordinate information, the area of the image acquisition area is smaller than the preset display range, and the image acquisition area is located at a random position in the preset display range.

At the moment, the first image information and the second image information of the engine base are overlapped. Specifically, the image capturing area may be a "mark frame" in the screen display content, and after a part of the first image information captured by the camera is placed in the "mark frame", an image of the part is the second image information. And verifying the vehicle information through the second image information.

By applying the technical scheme provided by the invention, when vehicle information is verified, the random area on the terminal screen is marked as the image acquisition area through the coordinate information randomly generated by the server. When a driver video-authenticates his vehicle, it is necessary to place an image of the vehicle within the image capture area. Because the image acquisition area is generated based on the random coordinate information, the position of the image acquisition area is also random, thereby effectively avoiding that part of drivers deceive the vehicle information verification through the prerecorded 'fake' video and greatly improving the reliability of the vehicle information verification.

Meanwhile, the acquired overall image is limited in a relatively small range through the image acquisition area, and the vehicle image is ensured to be positioned in the small range, so that when the vehicle image is searched and identified through a CNN (Convolutional Neural network) network, only a target vehicle needs to be searched in the image acquisition area, and a full-map search is not needed, so that resources required by calculation are greatly reduced, and the identification speed is effectively improved.

In addition, the vehicle information verification method in the above technical solution provided by the present invention may further have the following additional technical features:

in the above technical solution, before the step of verifying the vehicle information according to the second image information, the method for verifying the vehicle information further includes: detecting second image information through the vehicle detection model; and determining that the vehicle image and the license plate image exist in the second image information, and the area ratio of the vehicle image in the second image information accords with a preset proportion range, and executing the step of verifying the vehicle information according to the second image information.

In the technical scheme, after the second image information is acquired, whether the acquired second image information meets the requirement of vehicle information verification is verified firstly. Specifically, the acquired second image information needs to meet the requirement of confirming that the second image information contains the vehicle image and the license plate image, and meanwhile, the area of the vehicle image in the second image information meets the preset proportion range, so that the acquired second image information can be determined to meet the requirement, and at the moment, the step of vehicle information verification is further executed, so that the success rate of vehicle information verification can be ensured.

In any of the above technical solutions, the step of verifying the vehicle information according to the second image information specifically includes: acquiring coordinate information of a license plate in the second image information through the vehicle detection model; determining that the coordinate information of the license plate is matched with preset license plate coordinate information, the vehicle image is a complete vehicle image, determining that the second image information is a qualified image, and acquiring the license plate number corresponding to the license plate through a license plate recognition model; and determining that the license plate number is matched with the preset license plate number, and determining that the vehicle information passes the verification.

According to the technical scheme, vehicle information is verified, firstly, coordinate information of a license plate is located through a vehicle detection model, after license plate coordinates are located, whether the coordinate information of the license plate is matched with preset license plate coordinate information or not is determined, and if the license plate coordinate information is matched with the preset license plate coordinate information and second image information comprises a complete vehicle image, the second image information intercepted at this time is determined to be a qualified image. At the moment, the license plate number on the license plate is recognized through the license plate recognition model, and if the recognized license plate number is matched with the preset license plate number, the vehicle information is judged to pass the verification.

By limiting the license plate coordinates and the integrity of the vehicle images, if and only if the license plate coordinates and the vehicle images meet the requirements, the second image information is determined to be a qualified image, otherwise, the step of verifying the vehicle information according to the license plate number is not executed, so that the reliability of vehicle information verification is effectively ensured, and the vehicle information management is facilitated.

In any of the above technical solutions, the terminal is provided with an image obtaining device, and before the step of outputting the first image information within the preset display range, the vehicle information verification method further includes: acquiring video information through an image acquisition device, and converting the video information into continuous frame images; second image information is determined from the frame image.

In the technical scheme, video information is recorded in real time through an image acquisition device arranged on a terminal such as a mobile phone, and the real-time video information is displayed in a display range, so that a user can manually adjust the position of a video, so that a vehicle is placed in an image acquisition area and starts to be recorded. After the video information is acquired in a recording mode, the video information is converted into continuous frame images, any frame image can be used as first image information, and second image information is acquired according to the frame image information converted from the video, so that the reliability of vehicle information verification can be further improved, users are prevented from cheating, and the safety of a network appointment platform is improved.

In any of the above technical solutions, before the step of obtaining the license plate number corresponding to the license plate through the license plate recognition model, the method for verifying the vehicle information further includes: intercepting a video clip with preset duration in the video information, and converting the video clip into a continuous frame image to be detected; and determining that all the frame images to be detected are qualified images, and executing the step of obtaining the license plate number corresponding to the license plate through the license plate recognition model.

In the technical scheme, in order to ensure the reliability of vehicle information verification, after a video is recorded and acquired, video segments with preset duration are randomly intercepted, the video segments are converted into continuous frame images to be detected, and all the frame images to be detected are verified. And if and only if all the frame images to be detected are qualified images, determining that the recorded video is effective, and further executing the step of identifying the license plate number.

By ensuring that all the frame images within the preset time duration in the video are qualified images, the reliability of vehicle information verification can be further improved, users are prevented from cheating, and the safety of the network taxi appointment platform is improved.

In any of the above technical solutions, before the step of detecting the second image information by the vehicle detection model, the method for verifying the vehicle information further includes: acquiring historical vehicle image information and acquiring a preset detection model; and marking license plate position information, license plate coordinate information and license plate information in the historical vehicle information to form a vehicle recognition training set, and training a preset detection model through the vehicle recognition training set to obtain a vehicle detection model.

In this technical solution, before the second image information is detected by the vehicle detection model, the vehicle detection model needs to be trained. Specifically, a certain amount of historical vehicle image information is acquired, and the historical vehicle image can be an image in an RGB (red, green and blue) format. And manually or automatically labeling training elements such as vehicle positions, license plate position information, license plate coordinate information, license plate information and the like in the historical image information to form a vehicle recognition training set. The preset detection model is trained through the vehicle identification training set, so that the vehicle detection model with high identification precision can be obtained, and the reliability of vehicle information detection is improved.

In any of the above technical solutions, before the step of obtaining the license plate number corresponding to the license plate through the license plate recognition model, the method for verifying the vehicle information further includes: acquiring a preset character recognition model; and training a preset character recognition model based on the CNN convolutional neural network, the LSTM long-short term memory network and the CTC time sequence loss function to obtain a license plate recognition model.

In the technical scheme, in order to ensure the accuracy of license plate number recognition, an initial OCR model can be trained based on a CNN convolutional neural network, an LSTM (Long Shot-Term Memory) Long and short Term Memory network and a CTC time sequence loss function, so that a specialized recognition model aiming at license plate character detection, namely a license plate recognition model, is obtained, the success rate of license plate recognition is improved, and the reliability of vehicle information recognition and verification is improved.

In any of the above technical solutions, the preset proportion range is: greater than or equal to 40% and less than or equal to 80%; the preset duration range is as follows: greater than or equal to 2 seconds and less than or equal to 5 seconds.

In the technical scheme, when the area proportion of the vehicle image in the second image information is between 40% and 80%, the vehicle image can be determined to be complete and the position is proper. When the video is judged to be qualified, the video with the minimum duration of 2 seconds and the maximum duration of 5 seconds can be intercepted for verification, and the continuous video with the duration of 3 seconds can be intercepted preferably.

It is to be understood that the preset range may be freely adjusted according to the calculation force requirement and the strictness of the vehicle information verification, and is not necessarily limited to the above-mentioned increased proportion range or duration range.

A second aspect of the present invention provides a vehicle information verification system, including: a memory configured to store a computer program; the processor is configured to execute the computer program to implement the method for verifying the vehicle information provided in any one of the above technical solutions, and therefore, the system for verifying the vehicle information includes all the beneficial effects of the method for verifying the vehicle information provided in any one of the above technical solutions, which are not described herein again.

A third aspect of the present invention provides a terminal, including: an image acquisition device configured to acquire video information; a display device configured to display image information, the display device having a display area including a preset display area; according to the vehicle information verification system provided by any one of the above technical solutions, the vehicle information verification system is connected with the image acquisition device and the display device. Therefore, the terminal includes all the benefits of the vehicle information verification system provided in any of the above technical solutions, and details are not repeated herein.

A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for verifying vehicle information provided in any one of the above technical solutions, and therefore, the computer-readable storage medium includes all the beneficial effects of the method for verifying vehicle information provided in any one of the above technical solutions, which are not described herein again.

Drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 shows a flowchart of a verification method of vehicle information according to an embodiment of the invention;

FIG. 2 illustrates an interface diagram of a method of verifying vehicle information according to one embodiment of the invention;

FIG. 3 illustrates another flow diagram of a method of verifying vehicle information in accordance with one embodiment of the present invention;

FIG. 4 illustrates yet another flow diagram of a method of verifying vehicle information in accordance with an embodiment of the present invention;

FIG. 5 illustrates yet another flowchart of a method of verifying vehicle information according to an embodiment of the invention;

FIG. 6 illustrates yet another flowchart of a method of verifying vehicle information according to an embodiment of the invention;

Fig. 7 shows still another flowchart of a verification method of vehicle information according to an embodiment of the invention;

fig. 8 shows still another flowchart of a verification method of vehicle information according to an embodiment of the invention;

FIG. 9 illustrates a system logic diagram of a vehicle information identification method according to one embodiment of the present invention;

FIG. 10 illustrates a verification interaction flow diagram of a vehicle information identification method according to one embodiment of the invention;

fig. 11 is a block diagram showing the configuration of a vehicle information recognition system according to an embodiment of the invention;

fig. 12 shows a block diagram of a terminal according to an embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

A method of verifying vehicle information, a system of verifying vehicle information, a terminal, and a computer-readable storage medium according to some embodiments of the present invention are described below with reference to fig. 1 to 12.