WO2023024787A1

WO2023024787A1 - Image processing method and apparatus, electronic device, computer-readable storage medium, and computer program product

Info

Publication number: WO2023024787A1
Application number: PCT/CN2022/107671
Authority: WO
Inventors: 熊鹏; 朱斌; 周俊竹; 钱能胜; 阮佳彬
Original assignee: 上海商汤智能科技有限公司
Priority date: 2021-08-23
Filing date: 2022-07-25
Publication date: 2023-03-02
Also published as: CN113705417A; CN113705417B

Abstract

The present application provides an image processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises: when it is determined that a first target vehicle is in a photographing area of a first camera, determining that a first video source device of the first target vehicle is the first camera; and when it is determined that the first target vehicle enters a photographing area of a second camera from the photographing area of the first camera, switching the first video source device of the first target vehicle from the first camera to the second camera, the first camera being different from the second camera.

Description

Image processing method and device, electronic device, computer-readable storage medium, and computer program product

Cross References to Related Applications

This disclosure is based on the Chinese patent application with the application number 202110971089.6, the filing date is August 23, 2021, and the invention title is "image processing method and device, electronic equipment and computer-readable storage medium", and requires the Chinese patent application Priority, the entire content of the Chinese patent application is hereby incorporated by reference into this disclosure.

technical field

The present disclosure relates to the technical field of image processing, and in particular to an image processing method and device, electronic equipment, computer-readable storage media, and computer program products.

Background technique

With the increase of cameras, more and more scenes use cameras to improve social security management capabilities. For example, tracking vehicles entering a specific area is one of the application scenarios.

In the current method, after it is determined that the camera captures the vehicle, the video captured by the camera will be displayed. But after the vehicle drives out of the shooting area of the camera, the video captured by the camera is still displayed instead of the real-time video of the vehicle.

Contents of the invention

The disclosure provides an image processing method and device, electronic equipment, a computer-readable storage medium, and a computer program product.

In a first aspect, an image processing method is provided, the method comprising:

When it is determined that the first target vehicle is in the shooting area of the first camera, it is determined that the first video source device of the first target vehicle is the first camera; When the shooting area of the first camera enters the shooting area of the second camera, the first video source device of the first target vehicle is switched from the first camera to the second camera, and the first The camera is different from said second camera.

In a second aspect, an image processing device is provided, the device comprising:

The first processing unit is configured to determine that the first video source device of the first target vehicle is the first camera when it is determined that the first target vehicle is within the shooting area of the first camera; the second processing A unit configured to transfer the first video source device of the first target vehicle from the first video source device of the first target vehicle to the A camera is switched to the second camera, and the first camera is different from the second camera.

In a third aspect, an electronic device is provided, including: a processor and a memory, the memory is used to store computer program codes, the computer program codes include computer instructions, and when the processor executes the computer instructions , the electronic device executes the method according to the foregoing first aspect and any possible implementation manner thereof.

In a fourth aspect, a computer-readable storage medium is provided. A computer program is stored in the computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the The processor executes the method according to the first aspect and any possible implementation manner thereof.

In a fifth aspect, a computer program product is provided, the computer program product includes a computer program or an instruction, and when the computer program or instruction is run on a computer, the computer executes the first aspect and any of the above-mentioned aspects. A method of one possible implementation.

In the embodiment of the present disclosure, when it is determined that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, the first video source device of the first target vehicle is transferred from the Switching the first camera to the second camera can improve the accuracy of the determined real-time first video source device, thereby improving the effect of video relay.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the background art, the following will describe the drawings that need to be used in the embodiments of the present disclosure or the background art.

The accompanying drawings here are incorporated into the description and constitute a part of the present description. These drawings show embodiments consistent with the present disclosure, and are used together with the description to explain the technical solution of the present disclosure.

FIG. 1 is a schematic diagram of the architecture of an image processing system provided by an embodiment of the present disclosure;

FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a display page provided by an embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a hardware structure of an image processing device provided by an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is a part of the embodiments of the present disclosure, but not all of them. Based on the embodiments in the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present disclosure.

The terms "first", "second" and the like in the specification and claims of the present disclosure and the above drawings are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally further includes For other steps or units inherent in these processes, methods, products or devices.

It should be understood that in this disclosure, "at least one (item)" means one or more, "multiple" means two or more, and "at least two (items)" means two or three And three or more, "and/or", is used to describe the association relationship of associated objects, indicating that there can be three types of relationships, for example, "A and/or B" can mean: only A exists, only B exists, and A exists at the same time and B, where A and B can be singular or plural. The character "/" can indicate that the contextual objects are an "or" relationship, which refers to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one item (piece) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c ", where a, b, c can be single or multiple. The character "/" can also represent a division sign in mathematical operations, for example, a/b=a divided by b; 6/3=2. "At least one of the following" or similar expressions.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present disclosure. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

In the current method, after it is determined that the camera captures the vehicle, the video captured by the camera will be displayed. But after the vehicle drives out of the shooting area of the camera, the video collected by the camera is still displayed, but the real-time video of the vehicle cannot be displayed. Based on this, the embodiment of the present disclosure provides a technical solution to display the real-time video of the vehicle.

The execution subject of the embodiments of the present disclosure is an image processing apparatus, where the image processing apparatus may be any electronic device capable of executing the technical solutions disclosed in the method embodiments of the present disclosure. The image processing device may be one of the following: a mobile phone, a computer, a tablet computer, and a wearable smart device.

It should be understood that the method embodiments of the present disclosure may also be implemented in a manner in which a processor executes computer program codes. Embodiments of the present disclosure are described below with reference to the accompanying drawings in the embodiments of the present disclosure.

Please refer to FIG. 1 . FIG. 1 is a schematic diagram of an image processing system 1000 provided by an embodiment of the present disclosure. In FIG. 1 , there is a communication connection between an image processing device 1001 and at least two cameras 1002 . The image processing apparatus 1001 also has a communication connection with the display device 1003 , and the image processing apparatus 1001 can display through the display device 1003 based on the communication connection.

In some embodiments, the image processing apparatus 1001 is a server. The image processing device 1001 can be deployed in the control center of the management area. At least two cameras 1002 are deployed in the management area for collecting images and/or videos in the management area.

The image processing device 1001 processes the images and/or videos collected by at least two cameras 1002 based on the technical solutions provided below, determines the first video source device of the first target vehicle, and then can display the first video through the display device 1003 The capture screen of the source device. For example, the at least two cameras 1002 include a first camera and a second camera. When the image processing device 1001 determines that the first target vehicle appears in the shooting area of the first camera, it determines that the first video source device is the first camera, and then displays the picture taken by the first camera through the display device 1003 . When the image processing device 1001 determines that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera, it switches the first video source device from the first camera to the second camera, and then displays the display device 1003 The display screen of the first camera is switched from the shooting screen of the first camera to the shooting screen of the second camera.

Thus, based on the image processing system 1000 , real-time display of the video of the first target vehicle in the management area can be realized.

In some embodiments, the image processing device 1001 and the display device 1003 may be the same terminal device, and the terminal device includes both image processing and analysis capabilities and display capabilities, and can simultaneously implement the method steps performed by the image processing device 1001 and the display device 1003 . For example, the image processing apparatus 1001 and the display device 1003 are computers.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure, the method is executed by an electronic device, and the method includes the following

steps

201 and 202, wherein:

Step 201. When it is determined that the first target vehicle is within the shooting area of the first camera, determine that the first video source device of the first target vehicle is the first camera.

In some embodiments, the vehicle (including the above-mentioned first target vehicle, and the second target vehicle and the vehicle to be identified which will be mentioned below) may be any vehicle. For example, the first target vehicle is a sedan. For another example, the first target vehicle is a dump truck. For another example, the first target vehicle is a bus.

In some embodiments, the camera (including the above-mentioned first camera and the second camera to be mentioned below) may be a camera, and the camera may also be a capture machine.

In some embodiments, the video source device of the vehicle (including the first video source device of the above-mentioned first target vehicle and the second video source device of the second target vehicle to be mentioned below) is, when displaying the real-time video of the vehicle The source of the video shown.

For example, if the first video source device of the first target vehicle is camera a, then when displaying the real-time video of the first target vehicle, the real-time video captured by camera a is displayed.

The first target vehicle is in the shooting area of the first camera, indicating that when displaying the real-time video of the first target vehicle, the real-time video collected by the first camera should be displayed. Therefore, in this case, the image processing device determines the first target The first video source device of the vehicle is the first camera.

Step 202. When it is determined that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera, switch the first video source device of the first target vehicle from the first camera to the above-mentioned The second camera, the above-mentioned first camera is different from the above-mentioned second camera.

The first target vehicle drives from the shooting area of the first camera into the shooting area of the second camera. When displaying the real-time video of the first target vehicle, the displayed video should be switched from the real-time video collected by the first camera to the second camera. Captured real-time video. Therefore, when it is determined that the first target vehicle is driving from the shooting area of the first camera into the shooting area of the second camera, the first video source device of the first target vehicle is switched from the first camera to the second camera.

In some embodiments, the image processing device switches the first video source device of the first target vehicle from the first camera when the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera is the second camera, so that the first video source device of the first target vehicle can be determined in real time.

In this way, after the first video source device of the first target vehicle is determined, the real-time video of the first target vehicle can be displayed by displaying the real-time video collected by the first video source device.

For the convenience of expression, when the first target vehicle drives from the shooting area of the first camera into the shooting area of the second camera, the first video source device of the first target vehicle is switched from the first camera to the second camera, which is called video relay.

Before the image processing device determines that the above-mentioned first target vehicle enters the shooting area of the second camera from the shooting area of the above-mentioned first camera, it also performs the following steps:

Step 1. Acquire a time difference threshold and at least two first images.

In some embodiments, the time difference threshold is a positive number. The at least two first images may be one first image, and the at least two first images may also be two or more first images. Each of the at least two first images includes a first target vehicle. The at least one first image includes an image captured by the first camera and an image captured by the second camera.

For example, the at least two first images include image a and image b. At this time, image a is captured by the first camera, and image b is captured by the second camera. Moreover, both image a and image b include the first target vehicle.

In an implementation manner of acquiring a time difference threshold, the image processing apparatus receives a time difference threshold input by a user through an input component. The above-mentioned input components include: a keyboard, a mouse, a touch screen, a touch pad, an audio input device, and the like.

In another implementation manner of acquiring the time difference threshold, the image processing apparatus receives the time difference threshold sent by the terminal. The above-mentioned terminals include: mobile phones, computers, tablet computers, and servers.

In an implementation manner of acquiring at least two first images, the image processing device receives at least two first images input by a user through an input component.

In another implementation manner of acquiring at least two first images, the image processing apparatus receives at least two first images sent by the terminal.

It should be understood that, in the embodiment of the present disclosure, the step of acquiring at least two first images and the step of acquiring the time difference threshold may be performed separately, or may be performed simultaneously. For example, the image processing device may first acquire at least two first images, and then acquire the time difference threshold. For another example, the image processing device may acquire the time difference threshold first, and then acquire at least two first images. For another example, the image processing apparatus acquires a time difference threshold during the process of acquiring at least two first images, or acquires at least two first images during the process of acquiring the time difference threshold.

Step 2. Determine the difference between the time stamp of the second image and the time stamp of the third image.

In some embodiments, the second image is the image with the smallest time stamp collected by the second camera among the at least two first images, and the third image is the time stamp collected by the first camera among the at least two first images minimal image.

For example, the at least two first images include image a, image b, image c, and image d, where image a and image d are captured by the first camera, and image b and image c are captured by the second camera. If the acquisition time of image a is earlier than the acquisition time of image d, that is, the time stamp of image a is smaller than the time stamp of image d, then the second image is image a. If the acquisition time of image b is earlier than the acquisition time of image c, that is, the time stamp of image b is smaller than the time stamp of image c, then the third image is image b.

In the embodiment of the present disclosure, the difference between the time stamp of the second image and the time stamp of the third image is the difference obtained by subtracting the time stamp of the third image from the time stamp of the second image. The difference characterizes the time difference between the acquisition time of the second image and the acquisition time of the third image.

After steps 1 and 2 are executed, the image processing device determines that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera by performing the following steps:

Step 3. If the difference is greater than the time difference threshold, determine that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera.

The first target vehicle drives from the shooting area of the first camera into the shooting area of the second camera, that is, the first target vehicle first appears in the shooting area of the first camera image, and then appears in the shooting area of the second camera. That is to say, the first camera captures the first target vehicle first, and the second camera captures the first target vehicle afterwards. In addition, it takes a certain amount of time for the vehicle to drive into the shooting area of the first camera and leave the shooting area of the first camera, that is, there is a gap between the first target vehicle captured by the first camera and the first target vehicle captured by the second camera. Time difference. Therefore, it can be judged whether the first target vehicle drives into the shooting area of the second camera from the shooting area of the first camera by the time difference between the collection time of the second image and the collection time of the third image.

In the embodiment of the present disclosure, the time difference threshold may be understood as the time required for the vehicle to drive out of the shooting area of the camera from entering the shooting area of the camera. It should be understood that the time difference threshold is an empirical value, and the value of the time difference threshold may be set according to actual conditions.

If the difference obtained in step 2 is greater than the time difference threshold, on the one hand, because the time difference threshold is a positive number, the first camera captures the first target vehicle first, and the second camera captures the first target vehicle later. On the other hand, if the first target vehicle is greater than the time difference threshold, it means that the first target vehicle has driven out of the shooting area of the first camera. That is to say, the first target vehicle has driven into the shooting area of the second camera from the shooting area of the first camera.

Therefore, the image processing device determines that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera when the difference value is greater than the time difference threshold.

If the difference obtained in step 2 is less than or equal to the time difference threshold, it includes the following two situations:

1) The second camera captures the first target vehicle first, and then the first camera captures the first target vehicle. At this time, the first target vehicle is in the shooting area of the first camera;

2) The first camera captures the first target vehicle first, and then the second camera captures the first target vehicle. However, the first target vehicle does not drive out of the shooting area of the first camera, that is, the first target vehicle is still in the shooting area of the first camera.

Therefore, in a possible implementation manner, the image processing device determines that the target vehicle is within the shooting area of the first camera when the difference value is less than or equal to the time difference threshold.

In step 1 and step 2, the image processing device judges whether the first target vehicle has driven from the shooting area of the first camera into the shooting area of the second camera through the difference between the time stamp of the second image and the time stamp of the third image. The shooting area can improve the accuracy of judgment, thereby improving the effect of video relay.

As a possible implementation manner, the at least two first images include n images with the largest timestamp in the target vehicle image set, the images in the target vehicle image set all include the first target vehicle, and the images in the target vehicle image set Both include images collected by the first camera and images collected by the second camera, and n is an integer greater than 1.

The images collected by the camera are time-sensitive, and the video relay needs to determine the real-time first video source device, so when at least two first images include the n images with the largest time stamp in the target vehicle image set, the determination can be improved. The accuracy of the first video source device in real time, thereby improving the effect of video relay.

As a possible implementation manner, after the image processing device determines that the above-mentioned difference value is greater than the above-mentioned time difference threshold, before determining that the first target vehicle has entered the shooting area of the second camera from the shooting area of the above-mentioned first camera, Also perform the following steps:

Step 4. Determine the first size of the first target vehicle in the second image and the second size of the first target vehicle in the third image.

In the embodiment of the present disclosure, the size of the first target vehicle in the image may be the size of the pixel area covered by the first target vehicle.

In a possible implementation manner, the size of the first target vehicle in the image is an area including a vehicle detection frame of the first target vehicle, wherein the vehicle detection frame is obtained by performing vehicle detection processing on the image. For example, the image processing device obtains the first vehicle detection frame including the first target vehicle by performing vehicle detection processing on the second image, and obtains the second vehicle detection frame including the first target vehicle by performing vehicle detection processing on the third image. The area of the first vehicle detection frame is the first size, and the area of the second vehicle detection frame is the second size.

After step 4 is executed, the image processing device determines that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera by performing the following steps:

Step 5. If the first size is larger than the second size, determine that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera.

If the first size is greater than the second size, it means that the distance between the first target vehicle and the second camera is smaller than the distance between the first target vehicle and the first camera. At this time, the second camera should be used as the first video source of the first target vehicle equipment. Therefore, when the first size is greater than the second size, the image processing device determines that the first target vehicle drives into the shooting area of the second camera from the shooting area of the first camera.

If the first size is smaller than the second size, it means that the distance between the first target vehicle and the second camera is greater than the distance between the first target vehicle and the first camera. At this time, the first camera should be used as the first video source of the first target vehicle equipment. In some embodiments, the image processing device determines that the first target vehicle is still within the shooting area of the first camera when the first size is smaller than the second size.

If the first size is equal to the second size, it means that the distance between the first target vehicle and the second camera is the same as the distance between the first target vehicle and the first camera, but since the current first video source device of the first target vehicle is the first camera , in order to make the display effect of the video relay more smooth, the first camera can still be used as the first video source device of the first target vehicle at this time. In some embodiments, the image processing device determines that the first target vehicle is still within the shooting area of the first camera when the first size is equal to the second size.

In step 4 and step 5, if the difference is greater than the time difference threshold, the image processing device further judges whether the first target vehicle enters the area of the second camera from the shooting area of the first camera based on the first size and the second size. The shooting area can improve the accuracy of judgment, thereby improving the effect of video relay.

As a possible implementation manner, the image processing device also displays the shooting picture of the first video source device, so that the real-time video of the first target vehicle can be displayed, achieving the effect of visually tracking the first target vehicle. In some embodiments, there is a communication connection between the image processing device and the display device, through which the image processing device displays the captured picture of the first video source device on the display device.

As a possible implementation manner, both the first camera and the second camera are deployed in the target area. In the embodiment of the present disclosure, the target area may be any area, for example, the target area is a school, and for example, the target area is an industrial park. In some embodiments, the target area includes an administrative area. Both the first camera and the second camera are deployed in the target area, that is, both the shooting area of the first camera and the shooting area of the second camera are located in the target area.

The image processing device also stops displaying the shooting picture of the first video source device when it is determined that the first target vehicle has left the target area. This can release hardware resources for tracking and displaying the first target vehicle, and improve the utilization rate of hardware resources of the image processing device, wherein the hardware resources include: hardware resources for determining the first video source device of the first target vehicle and The hardware resource used for displaying the captured picture of the first video source device of the first target vehicle.

In this embodiment, the image processing device tracks the track of the first target vehicle in the target area through the first camera and the second camera, and displays the video of the first target vehicle in the target area in real time. When it is determined that the first target vehicle has left the target area, it is determined that there is no need to continue to track the track of the first target vehicle in the target area, so stop displaying the captured picture of the first video source device, so as to improve the utilization of hardware resources of the image processing device Rate.

In some embodiments, stopping displaying the shooting picture of the first video source device is to stop displaying the shooting picture newly collected by the first video source device, but take the last frame image of the first target vehicle leaving the target area as the first tracking A display screen of the display area, wherein the first tracking display area is used to display the video of the first target vehicle in the target area. For example, if the image processing device determines that the first target vehicle leaves the target area after driving out of the shooting area of the second camera, and the last frame captured by the second camera includes the image of the first target vehicle as image a, then the image processing device will Image a is used as the display screen of the first tracking display area, that is, the display screen of the first tracking display area is always image a after the first target vehicle leaves the target area.

In a possible implementation manner, upon receiving an instruction that the first target vehicle has left the target area, it is determined that the first target vehicle has left the target area. The instruction may be input by the user to the image processing device through the input component, or the instruction may be sent by the terminal to the image processing device.

In another possible implementation manner, the image processing device determines that the first target vehicle disappears from the shooting area of the bayonet camera, and the first target vehicle disappears before the first target vehicle disappears from the shooting area of the bayonet camera. If there is a track record in the target area, it is determined that the first target vehicle has left the target area, wherein the bayonet camera includes a camera deployed at an entrance and exit of the target area.

In this embodiment, since the bayonet camera is deployed at the entrance and exit of the target area, when the first target vehicle disappears from the shooting area of the bayonet camera, it means that the first target vehicle has either entered the target area or left target area. Also, since the first target vehicle has a track record in the target area before the first target vehicle disappears from the shooting area of the bayonet camera, it means that the first target vehicle has left the target area. Therefore, the image processing device determines in this case that the first target vehicle has left the target area.

As a possible implementation, the shooting picture of the first video source is displayed in the first display area of the display page, and the display page also includes a second display area, and the second display area is used to display the second video source of the second target vehicle In the shooting screen of the device, the first target vehicle is different from the second target vehicle. In this embodiment, the display page can simultaneously display the real-time video of the first target vehicle and the real-time video of the second target vehicle.

It should be understood that the first display area and the second display area in the embodiment of the present disclosure are only examples, and should not be understood as only real-time videos of two vehicles can be displayed simultaneously on the display page. In practical applications, the image processing device may simultaneously display the implementation videos of m vehicles on the display page, where m is an integer greater than 1.

For example, in the display page shown in FIG. 3 , it includes four different display areas, namely the first display area 301, the second display area 302, the third display area 303 and the fourth display area 304, wherein different display areas Regions are used to display real-time video of different vehicles respectively. For example, the first display area 301 is used to display the real-time video of vehicle a, the second display area 302 is used to display the real-time video of vehicle b, the third display area 303 is used to display the real-time video of vehicle c, and the fourth display area 304 is used to display the real-time video of vehicle a. to display real-time video of vehicle d.

As a possible implementation manner, before the image processing device determines that the first target vehicle is within the shooting area of the above-mentioned first camera, the following steps are further performed:

Step 6. Obtain the second image captured by the above-mentioned first camera.

In a possible implementation manner, there is a communication connection between the image processing device and the first camera, and the image processing device acquires the second image captured by the first camera through the communication connection.

In another possible implementation manner, the image processing apparatus receives the second image input by the user through the input component.

In yet another possible implementation manner, the image processing apparatus receives the second image sent by the terminal.

After step 6 is executed, the image processing device determines that the first target vehicle is within the shooting area of the first camera when it is determined that the second image includes the first target vehicle.

As a possible implementation manner, the second image includes the vehicle to be identified, and the image processing device further performs the following steps before determining that the second image includes the first target vehicle:

Step 7. Obtain the target characteristic data of the first target vehicle.

In some embodiments, the target characteristic data of the first target vehicle carries the identity information of the first target vehicle, that is, by comparing the characteristic data of any vehicle with the target characteristic data, it can be determined whether the vehicle is the same as the first target vehicle . In some embodiments, the target feature data includes a feature vector carrying identity information of the first target vehicle.

In a possible implementation manner, the target feature data carries local feature information of the first target vehicle. For example, the target characteristic data carries at least one of the following information: characteristic information of vehicle lights, characteristic information of vehicle logos, and characteristic information of vehicle windows.

In another possible implementation manner, the target feature data carries global feature information of the first target vehicle, where the global feature information includes overall appearance feature information of the first target vehicle.

In yet another possible implementation manner, the target feature data carries not only local feature information of the first target vehicle, but also global feature information of the first target vehicle.

In an implementation manner of acquiring target feature data, the image processing device receives target feature data input by a user through an input component.

In another implementation manner of acquiring target feature data, the image processing apparatus receives target feature data sent by the terminal.

After performing step 7, the image processing device determines that the second image includes the first target vehicle by performing the following steps:

Step 8. Perform feature extraction processing on the second image to obtain the first feature data of the vehicle to be identified.

In some embodiments, the first feature data carries the identity information of the vehicle to be identified, that is, by comparing the feature data of any vehicle with the first feature data, it can be determined whether the vehicle is the same as the vehicle to be identified. In some other embodiments, the first feature data includes a feature vector carrying identity information of the vehicle to be identified.

In a possible implementation manner, the first feature data carries local feature information of the vehicle to be identified. For example, the first characteristic data carries at least one of the following information: characteristic information of vehicle lights, characteristic information of vehicle logos, and characteristic information of vehicle windows.

In another possible implementation manner, the first feature data carries global feature information of the vehicle to be identified, where the global feature information includes overall appearance feature information of the vehicle to be identified.

In yet another possible implementation manner, the first feature data carries not only local feature information of the vehicle to be identified, but also global feature information of the vehicle to be identified.

In the embodiment of the present disclosure, the feature extraction process is used to extract feature data of the vehicle in the image. In a possible implementation manner, the image processing device implements feature extraction processing on the image by performing convolution processing on the image.

In another possible implementation manner, the feature extraction processing of the image is implemented through a convolutional neural network. By using images with labeled information as training data, the convolutional neural network is trained, so that the trained convolutional neural network can complete the feature extraction process of the image. Wherein, the annotation information of the training data includes at least one of the following: local feature information of the vehicle in the image, and global feature information of the vehicle in the image.

Step 9. Obtain a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity between the target feature data and the first feature data.

In some embodiments, the first similarity is the similarity between the target feature data and the first feature data. The comparison result includes that the first target vehicle is the same as the vehicle to be identified, and the comparison result may include that the first target vehicle is different from the vehicle to be identified.

In a possible implementation manner, the image processing device determines that the comparison result includes that the first target vehicle is the same as the vehicle to be identified when the first similarity is greater than the feature comparison threshold; the image processing device determines that the first similarity is less than or equal to the feature comparison threshold, it is determined that the comparison result includes that the first target vehicle is different from the vehicle to be identified.

In another possible implementation manner, the image processing device determines the square of the first similarity to obtain the squared similarity. In the case where the square similarity is greater than the feature comparison threshold, determining the comparison result includes that the first target vehicle is the same as the vehicle to be identified; when the square similarity is less than or equal to the feature comparison threshold, the image processing device determines the comparison result It is included that the first target vehicle is different from the vehicle to be identified.

Step 10. When the comparison result includes that the first target vehicle is the same as the vehicle to be identified, determine that the second image includes the first target vehicle.

In steps 7 to 10, the image processing device compares the first feature data with the target feature data to obtain the first similarity, and then determines whether the vehicle to be recognized is the first target vehicle according to the first similarity, thereby determining Whether the first target vehicle is included in the second image.

In some embodiments, if the comparison result includes that the first target vehicle is different from the vehicle to be identified, it is determined that the second image does not include the first target vehicle.

As a possible implementation manner, before performing step 9, the image processing device further performs the following steps:

Step 11. Obtain at least one first target vehicle attribute of the above-mentioned first target vehicle.

In some embodiments, the vehicle attribute (including the above-mentioned first target vehicle attribute and the first target vehicle attribute to be mentioned below) includes at least one of the following: vehicle type, body color, vehicle brand, vehicle number, and vehicle model.

In a possible implementation manner, the vehicle types include: a hatchback sedan, a sedan sedan, a sport utility vehicle (sport utility vehicle, SUV), a pickup, a truck, a bus, a dump truck, and a muck truck.

In a possible implementation manner, the body colors include: black, blue, gray, white, navy blue, yellow, red, green, and purple.

In a possible implementation manner, the vehicle brands include: Mercedes-Benz, BMW, Audi, Volkswagen, Honda, Toyota, Nissan, Great Wall, and BYD.

In the implementation of the present disclosure, the first target vehicle attribute is the vehicle attribute of the first target vehicle. The at least one first target vehicle attribute may be one first target vehicle attribute, and the at least one first target vehicle attribute may also be two or more first target vehicle attributes. For example, the at least one first target vehicle attribute includes a body color of the first target vehicle. For another example, the at least one attribute of the first target vehicle includes the body color of the first target vehicle and the vehicle type of the first target vehicle.

In an implementation manner of acquiring at least one first target vehicle attribute of a first target vehicle, the at least one first target vehicle attribute of the first target vehicle is stored in an image processing device. The image processing device acquires at least one first target vehicle attribute of the first target vehicle by reading at least one first target vehicle attribute of the first target vehicle from the storage medium.

In another implementation manner of acquiring at least one first target vehicle attribute of a first target vehicle, the image processing device receives at least one first target vehicle attribute of the first target vehicle input by a user through an input component.

In yet another implementation manner of acquiring at least one first target vehicle attribute of the first target vehicle, the image processing device receives the at least one first target vehicle attribute of the first target vehicle sent by the terminal.

Step 12. Perform vehicle attribute extraction processing on the second image to obtain at least one first vehicle attribute of the vehicle to be identified.

In some embodiments, a vehicle attribute extraction process is used to extract vehicle attributes in the image. The vehicle attribute extraction process can be realized by a vehicle attribute extraction model, wherein the vehicle attribute extraction model is a computer vision model for extracting vehicle attributes.

In the embodiment of the present disclosure, the first vehicle attribute is the vehicle attribute of the vehicle to be recognized obtained by performing vehicle attribute extraction processing on the first image. The at least one first vehicle attribute may be one first vehicle attribute, and the at least one first vehicle attribute may also be two or more first vehicle attributes. For example, the at least one first vehicle attribute includes the body color of the vehicle to be identified. For another example, the at least one first vehicle attribute includes the body color of the vehicle to be identified and the vehicle type of the vehicle to be identified.

After performing step 11 and step 12, the image processing device performs the following steps in the process of performing step 9:

Step 13. Obtain a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity and the second similarity. The second similarity is the at least one first target vehicle attribute and the at least one first target vehicle attribute. A similarity between vehicle attributes.

In a possible implementation manner, the image processing device determines that the comparison result includes the first target vehicle and the vehicle to be identified when the first similarity is greater than the feature comparison threshold and the second similarity is greater than the attribute comparison threshold. same. Otherwise, the image processing device determines that the comparison result includes that the first target vehicle is different from the vehicle to be identified.

In this implementation manner, the first similarity degree is greater than the feature comparison threshold, indicating that the feature data of the first target vehicle is similar to the feature data of the vehicle to be identified. The second similarity is greater than the attribute comparison threshold, indicating that the vehicle attribute of the first target vehicle is similar to the vehicle attribute of the vehicle to be identified. Therefore, in this case, judging that the first target vehicle is the same as the vehicle to be recognized can improve the judgment accuracy.

In another possible implementation manner, the image processing apparatus obtains the third similarity according to the first similarity and the second similarity. In a case where the third similarity is greater than the similarity threshold, it is determined that the comparison result includes that the first target vehicle is the same as the vehicle to be identified. In a case where the third similarity is less than or equal to the similarity threshold, it is determined that the comparison result includes that the first target vehicle is different from the vehicle to be identified.

Suppose the first similarity is s1, the second similarity is s2, and the third similarity is s3. In a possible implementation manner, the image processing apparatus obtains the third similarity by weighting and summing the first similarity and the second similarity. At this time, s1, s2, and s3 satisfy the following formula:

s3=c1×s1+c2×s2…Formula (1)

Wherein, both c1 and c2 are non-negative numbers less than or equal to 1, and c1+c2=1.

In another possible implementation, s1, s2, and s3 satisfy the following formula:

s3=s1×s2...Formula (2)

In yet another possible implementation, s1, s2, and s3 satisfy the following formula:

s3=(s1×s2) ² ...Formula (3)

In steps 11 to 13, the image processing device obtains the comparison result according to the first similarity and the second similarity, which not only utilizes the information carried by the characteristic data, but also utilizes the information carried by the vehicle attribute, so the comparison result can be improved. accuracy of the results.

As a possible implementation manner, when the first camera is deployed in the target area, the image processing device performs the following steps in the process of executing step 7:

Step 14, acquiring the vehicle database to be tracked.

In some embodiments, the database of vehicles to be tracked includes characteristic data of at least one vehicle to be tracked. For example, the database of vehicles to be tracked includes feature data of vehicle a to be tracked and feature data of vehicle b to be tracked.

In some embodiments, the at least one vehicle to be tracked includes a vehicle whose trajectory is to be tracked within the target area. For example, the target area is the management area. For the safety of the target area, any vehicle entering the target area needs to be tracked. At this time, the vehicle entering the target area is the vehicle to be tracked.

In some implementations, the target vehicle may be any one of the at least one vehicle to be tracked, that is, the target vehicle is a vehicle that needs to track a trajectory within the target area.

In an implementation manner of acquiring a database of vehicles to be tracked, the image processing device receives the database of vehicles to be tracked input by a user through an input component.

In another implementation manner of acquiring the database of vehicles to be tracked, the image processing device receives the database of vehicles to be tracked sent by the terminal.

Step 15. In the case of acquiring the second image captured by the first camera, acquire a characteristic data from the database of the vehicle to be tracked as the characteristic data of the target.

The first camera is deployed in the target area, and the second image is collected by the first camera, and the second image includes the vehicle to be identified. Then the image processing device obtains the second image collected by the first camera, indicating that the vehicle to be identified has entered the target area, so it is necessary to determine the identity of the vehicle to be identified, that is, to determine which of the at least one vehicle to be tracked is the vehicle to be identified car.

Therefore, when the image processing device acquires the second image captured by the first camera, it acquires a feature data from the database of the vehicle to be tracked, and uses the feature data as target feature data. In this way, it can be determined whether the vehicle to be identified is the target vehicle by comparing the first characteristic data with the target characteristic data.

It should be understood that the target feature data in step 15 is only an example, and it should not be understood that the image processing device only acquires feature data of a vehicle to be tracked from the vehicle to be tracked database, and determines the relationship between the vehicle to be identified and at least one vehicle to be tracked Is one of the cars in the same. In practical applications, the image processing device may compare the first characteristic data with the characteristic data of each vehicle to be tracked in the database of vehicles to be tracked, so as to determine the identity of the vehicle to be identified.

As a possible implementation, when the comparison result includes that the first target vehicle is the same as the vehicle to be identified, the following steps are also performed: acquiring the fifth image of the target area and the first image of the first camera in the fifth image. Position: Determine a second position of the first target vehicle in the fifth image according to the first position.

The comparison result includes that the first target vehicle is the same as the vehicle to be identified, indicating that the first target vehicle has appeared in the shooting area of the first camera. Therefore, the position of the first target vehicle in the fifth image, ie, the second position, can be determined according to the first position. In a possible implementation manner, the image processing apparatus uses the first location as the second location.

In some embodiments, the target area is a map missing area. The missing area of the map includes an area missing detailed information on the map, wherein the detailed information includes at least one of the following: building information and road information. In this way, by determining the position of the first target vehicle in the fifth map, the accuracy of positioning in the target area can be improved.

In some embodiments, after the second position is determined, the second position is displayed in the fifth image, that is, the position of the first target vehicle within the target area is displayed.

In some embodiments, when the image processing device obtains at least two positions of the first target vehicle in the fifth image, determine the track of the first target vehicle in the fifth image according to the at least two positions, and The track is displayed.

As a possible implementation manner, the image processing device performs the following steps in the process of executing step 14:

Step 16. Acquire at least one fourth image, where the at least one fourth image includes the at least one vehicle to be tracked.

In an implementation manner of acquiring at least one fourth image, the image processing apparatus receives at least one fourth image input by a user through an input component.

In another implementation manner of acquiring at least one fourth image, the image processing apparatus receives at least one fourth image sent by the terminal.

In yet another implementation manner of acquiring at least one fourth image, there is a communication connection between the image processing device and at least one checkpoint camera, wherein the at least one checkpoint camera includes a camera deployed at an entrance and exit of the target area. The image processing device acquires at least one image to be confirmed captured by at least one bayonet camera as at least one fourth image through the communication connection.

In some embodiments, after acquiring the image to be confirmed, the image processing device determines that the vehicle in the image to be confirmed does not have a track record in the target area, and uses the image to be confirmed as the fourth image, thereby obtaining at least one a fourth image.

For example, at least one image to be confirmed includes image a and image b, wherein image a includes vehicle A, and image b includes vehicle B. If there is no track record of vehicle A in the target area, the image processing device uses image a as the fourth image. If the vehicle B has a track record in the target area, the image processing device does not use the image b as the fourth image. At this time, at least one fourth image includes image a.

Step 17. Obtain the vehicle database to be tracked according to the at least one fourth image.

In a possible implementation manner, the image processing device obtains the vehicle database to be tracked by performing structural processing on at least one fourth image.

In another possible implementation manner, the image processing device obtains feature data of at least one vehicle to be tracked by performing feature extraction processing on at least one fourth image, and obtains a database of vehicles to be tracked.

As a possible implementation manner, the image processing device performs the following steps during the execution of step 16:

Step 18. Acquire at least one sixth image.

In an embodiment of the present disclosure, each of the at least one sixth image includes a vehicle. In some embodiments, the vehicle in at least one sixth image is a vehicle to be confirmed, that is, the vehicle to be confirmed needs to be further confirmed whether it needs to track a trajectory within the target area.

In an implementation manner of acquiring at least one sixth image, there is a communication connection between the image processing device and at least one checkpoint camera, wherein the at least one checkpoint camera includes a camera deployed at an entrance and exit of the target area. The image processing device acquires at least one image to be confirmed collected by at least one bayonet camera through the communication connection. After the image processing device acquires the image to be confirmed, if it is determined that the vehicle in the image to be confirmed does not have a track record in the target area, the image to be confirmed is used as the sixth image, thereby obtaining at least one sixth image.

For example, at least one image to be confirmed includes image a and image b, wherein image a includes vehicle A, and image b includes vehicle B. If there is no track record of vehicle A in the target area, the image processing device uses image a as the sixth image. If the vehicle B has a track record in the target area, the image processing device does not use the image b as the sixth image. At this time, at least one sixth image includes image a.

Step 19. Obtaining at least one fourth image according to the at least one sixth image and the deletion instruction when a deletion instruction for at least one sixth image is detected.

In some embodiments, the deletion instruction may be input by the user to the image processing apparatus. By inputting the deletion instruction to the image processing device, the user can delete at least one image in the at least one sixth image, thereby determining at least one vehicle to be confirmed from the at least one vehicle to be confirmed included in the at least one sixth image. Track vehicles.

For example, at least one sixth image includes image a and image b, wherein image a includes vehicle A to be confirmed, and image b includes vehicle B to be confirmed. The user confirms that the image a is blurred. If the vehicle database to be tracked is obtained based on the image a, the accuracy of the data in the vehicle database to be tracked may be affected. Therefore, the user inputs a delete instruction to delete the image b to the image processing device. When the image processing device detects the deletion instruction, delete the image b in the at least one sixth image to obtain at least one fourth image. At this time, at least one fourth image includes image a, and at least one vehicle to be tracked includes vehicle A.

As a possible implementation manner, the image processing device performs the following steps in the process of executing step 19:

Step 20. Delete at least one image in the sixth image according to the deletion instruction to obtain at least one seventh image.

For the implementation of this step, please refer to the implementation of step 19. In other words, at least one seventh image in this step corresponds to at least one fourth image in step 19, that is, in this step, the image processing device according to The deleting instruction deletes the image in the at least one sixth image to obtain not at least one fourth image but at least one seventh image. At this time, the vehicles in at least one seventh image are all vehicles to be confirmed, that is, at least one seventh image includes at least one vehicle to be confirmed.

Step 21: In a case where a confirmation tracking instruction for at least one seventh image is detected, use the at least one seventh image indicated by the confirmation tracking instruction as at least one fourth image.

In some embodiments, the confirmation tracking instruction may be input by a user to the image processing device. The user can determine at least one vehicle to be tracked from at least one vehicle to be confirmed included in at least one seventh image by inputting a confirmation tracking instruction to the image processing device, and then determine at least one vehicle to be tracked from at least one seventh image. Four images.

For example, at least one seventh image includes image a and image b, wherein image a includes vehicle A to be confirmed, and image b includes vehicle B to be confirmed. The user confirms that the vehicle B to be confirmed is the vehicle of the staff in the target area, so there is no need to track the vehicle B to be confirmed. Therefore, the user inputs a confirmation tracking instruction to the image processing device, so that the image processing device takes the vehicle A as the vehicle to be tracked. When the image processing device detects the confirmation tracking instruction, the image a in the at least one seventh image is used as the at least one fourth image. At this time, at least one fourth image includes image a, and at least one vehicle to be tracked includes vehicle A.

As a possible implementation manner, the database of vehicles to be tracked further includes at least one second vehicle attribute of at least one vehicle to be tracked, and the at least one second vehicle attribute is obtained by performing vehicle attribute extraction processing on at least one fourth image.

In this implementation manner, the image processing device performs the following steps during the execution of step 17:

Step 22. According to the at least one fourth image, obtain the feature data of the at least one vehicle to be tracked and at least one third vehicle attribute of the at least one vehicle to be tracked.

According to the implementation manner provided in step 17, the image processing device can obtain feature data of at least one vehicle to be tracked according to at least one fourth image. The image processing device can obtain at least one third vehicle attribute of at least one vehicle to be tracked by performing vehicle attribute extraction processing on at least one fourth image.

Step 23 , when an editing instruction for the at least one third attribute is detected, edit the at least one third vehicle attribute according to the editing instruction to obtain the at least one second vehicle attribute.

In some embodiments, the editing instruction may be input by the user to the image processing device. The user can edit at least one third vehicle attribute by inputting the editing command to the image processing device.

For example, the image processing device determines that the body color of the vehicle A to be tracked is white by performing step 22 . However, the body color of the vehicle A to be tracked is actually gray. At this time, the user can modify the body color of the vehicle A to be tracked to gray by inputting an edit command to the image processing device. At this time, at least one second vehicle attribute includes that the body color of the vehicle A to be tracked is gray.

Step 24: Obtain the vehicle database to be tracked according to the feature data of the at least one vehicle to be tracked and the at least one second attribute.

In a possible implementation manner, the image processing device stores the feature data and at least one second attribute of at least one vehicle to be tracked in the vehicle to be tracked database.

Based on the technical solutions provided in steps 22 to 24, the user can modify the vehicle attributes of the vehicle to be tracked by inputting editing instructions to the image processing device, thereby improving the accuracy of the data in the vehicle to be tracked database.

As a possible implementation manner, before performing step 24, the image processing device further performs the following steps:

Step 25: Perform vehicle detection processing on at least one seventh image, and determine at least one third position of at least one vehicle to be tracked in the at least one seventh image.

In some embodiments, a vehicle detection process is used to detect the position of the vehicle in the image. The image processing device determines the position of each vehicle to be tracked in the image by performing vehicle detection processing on each seventh image, and obtains at least one third position.

For example, at least one seventh image includes image a and image b. The image processing device determines the position of the vehicle A in the image a in the image a as a third position by performing vehicle detection processing on the image a. The image processing device determines the position of the vehicle B in the image b as a third position by performing vehicle detection processing on the image b. At this time, at least one third position includes the position of vehicle A in image a and the position of vehicle B in image b.

Step 26: Intercept at least one pixel region determined according to at least one third position from at least one seventh image to obtain at least one eighth image.

In a possible implementation manner, the image processing device can determine the position of the vehicle detection frame including the vehicle to be tracked in the image according to the third position, and then can use the pixel area included in the vehicle detection frame including the vehicle to be tracked as Eighth image.

For example, the at least one third position includes the position of vehicle A in image a and the position of vehicle B in image b. The image processing device determines the pixel area included in the vehicle detection frame of vehicle A according to the position of vehicle A in image a, and intercepts the pixel area included in the vehicle detection frame of vehicle A as image c. The image processing device determines the pixel area included in the vehicle detection frame of the vehicle B according to the position of the vehicle B in the image b, and intercepts the pixel area included in the vehicle detection frame of the vehicle B as the image d. At this time, at least one eighth image includes image c and image d.

After performing step 26, the image processing device performs the following steps in the process of performing step 24:

Step 27. Store at least one eighth image, feature data of at least one vehicle to be tracked, at least one second vehicle attribute and at least one seventh image in the vehicle to be tracked database.

As a possible implementation manner, the image processing device also performs the following steps:

Step 28, obtaining retrieval conditions.

In some embodiments, the retrieval condition is used to retrieve the record of the vehicle to be tracked entering the target area from the vehicle to be tracked database. The retrieval condition includes at least one of the following information: time requirement, body color, vehicle type, vehicle model, license plate number.

In an implementation manner of obtaining retrieval conditions, the image processing apparatus receives retrieval conditions input by a user through an input component.

In another implementation manner of acquiring retrieval conditions, the image processing apparatus receives the retrieval conditions sent by the terminal.

After performing step 28, the image processing device performs one of the following steps:

Step 29: Search the database of vehicles to be tracked by using the retrieval conditions to obtain image data matching the retrieval conditions, the image data includes at least one of the following: at least one seventh image, at least one eighth image.

In a possible implementation manner, the retrieval condition includes a time requirement, and the image processing device collects images whose time meets the time requirement as image data matching the retrieval condition.

For example, the retrieval condition includes vehicles to be tracked that have entered the target area within the last 5 days. The image processing device uses the seventh image whose collection time is within the last 5 days and the eighth image whose collection time is within the last 5 days as the image data matching the retrieval condition.

It should be understood that the acquisition time of the eighth image is the same as the acquisition time of the corresponding seventh image, for example, the eighth image a is obtained by intercepting the pixel area in the seventh image b, then the acquisition time of the eighth image a is the same as that of the seventh image The acquisition time of b is the same.

In another possible implementation manner, the retrieval condition includes a vehicle attribute, and the image processing device uses the included image matching the vehicle attribute of the vehicle to be tracked with the vehicle attribute in the retrieval condition as the image data matching the retrieval condition.

For example, the retrieval condition includes a vehicle to be tracked whose body color is red. The image processing device takes the seventh image containing the red vehicle to be tracked and the eighth image containing the red vehicle to be tracked as image data matching the retrieval condition.

Step 30: Search the database of vehicles to be tracked by using the retrieval conditions to obtain at least one second vehicle attribute matching the retrieval conditions.

In a possible implementation, the retrieval condition includes a time requirement, and the image processing device takes the image whose acquisition time meets the time requirement as the image data matching the retrieval condition, and uses the image data that matches the retrieval condition to be tracked At least one second vehicle attribute of the vehicle is used as the at least one second vehicle attribute matching the retrieval condition.

For example, the retrieval condition includes vehicles to be tracked that have entered the target area within the last 5 days. The image processing device takes the seventh image whose acquisition time is within the last 5 days as the image data matching the retrieval condition. Taking at least one second vehicle attribute of the vehicle to be tracked in the seventh image as the at least one second vehicle attribute matching the retrieval condition.

In some embodiments, the image processing device searches the database of vehicles to be tracked using the retrieval conditions, and can obtain not only image data matching the retrieval conditions, but also at least one second vehicle attribute matching the retrieval conditions.

In some embodiments, after obtaining the image data matching the retrieval condition and at least one second vehicle attribute matching the retrieval condition, the image processing device may display the trajectory of the corresponding vehicle to be tracked within the target area.

As a possible implementation manner, before performing step 6, the image processing device further performs the following steps:

Step 31, obtaining the working time zone.

In order to improve the working efficiency of the first camera and reduce the energy consumption of the first camera, the first camera can collect images within a specified time period. In some embodiments, the working time period is the time period during which the first camera collects images according to regulations.

In an implementation manner of acquiring the working time period, the image processing apparatus receives the working time period input by the user through the input component.

In another implementation manner of acquiring the working time period, the image processing apparatus receives the working time period sent by the terminal.

Step 32: Sending a vehicle tracking instruction to the first camera, where the vehicle tracking instruction is used to instruct the first camera to collect images within a working time period.

In some embodiments, the vehicle tracking instruction is used to instruct the first camera to collect images within a working time period. By executing step 32, the image processing device can enable the first camera to collect images during the working time period, thereby improving the working efficiency of the first camera and reducing the energy consumption of the first camera.

Those skilled in the art can understand that in the above-mentioned method of specific implementation, the writing order of each step does not imply a strict execution order and constitutes any limitation on the implementation process, and the execution order of each step should be based on its function and possible internal Logically OK.

The method of the embodiment of the present disclosure has been described in detail above, and the device of the embodiment of the present disclosure is provided below.

Please refer to FIG. 4 . FIG. 4 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure. The image processing device 1 includes: a first processing unit 11 and a second processing unit 12 . In some embodiments, the image processing device 1 further includes: an acquisition unit 13, a determination unit 14, a display unit 15, an extraction unit 16, and a third processing unit 17, wherein:

The first processing unit 11 is configured to determine that the first video source device of the first target vehicle is the first camera when it is determined that the first target vehicle is within the shooting area of the first camera;

The second processing unit 12 is configured to send the first video source device of the first target vehicle to the Switching from the first camera to the second camera, where the first camera is different from the second camera.

In combination with any embodiment of the present disclosure, the image processing device further includes: an acquisition unit 13 configured to, when determining that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, Before the case of , acquire a time difference threshold and at least two first images, the time difference threshold is a positive number, both of the at least two first images include the first target vehicle, and the at least one first image Including the image collected by the first camera and the image collected by the second camera; the determination unit 14 is configured to determine the difference between the time stamp of the second image and the time stamp of the third image, the second image is the image with the smallest time stamp collected by the second camera in the at least two first images, and the third image is the time of the at least two first images collected by the first camera Poke the smallest image;

The second processing unit 12 is configured to determine that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera when the difference is greater than the time difference threshold .

In combination with any embodiment of the present disclosure, the at least two first images include n images with the largest time stamp in the target vehicle image set, the images in the target vehicle image set all include the first target vehicle, and the target The images in the vehicle image set include images captured by the first camera and images captured by the second camera, and the n is an integer greater than 1.

In combination with any embodiment of the present disclosure, the determining unit 14 is further configured to determine the shooting area of the first target vehicle from the first camera after the difference is greater than the time difference threshold Before entering the shooting area of the second camera, determine a first size of the first target vehicle in the second image and a second size of the first target vehicle in the third image;

The second processing unit 12 is configured to determine that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera when the first size is larger than the second size. area.

In combination with any implementation manner of the present disclosure, the device further includes: a display unit 15 configured to display a captured image of the first video source device.

In combination with any embodiment of the present disclosure, both the first camera and the second camera are deployed in the target area; the display unit 15 is further configured to determine that the first target vehicle has left the target area In this case, stop displaying the shooting picture of the first video source device.

In combination with any implementation manner of the present disclosure, the shooting picture of the first video source device is displayed in the first display area of the display page, and the display page further includes a second display area, and the second display area is used to display the second A shooting picture of a second video source device of a target vehicle, where the first target vehicle is different from the second target vehicle.

In combination with any embodiment of the present disclosure, the acquiring unit 13 is configured to acquire the second image captured by the first camera before determining that the first target vehicle is within the shooting area of the first camera;

The first processing unit 11 is configured to determine that the first target vehicle is within the shooting area of the first camera when it is determined that the second image includes the first target vehicle.

In combination with any embodiment of the present disclosure, the second image includes a vehicle to be identified; the acquiring unit 13 is further configured to: before determining that the second image includes the first target vehicle, acquire the Target characteristic data of the first target vehicle;

The first processing unit 11 is configured to perform feature extraction processing on the second image to obtain first feature data of the vehicle to be identified; according to the first feature data between the target feature data and the first feature data Similarity, obtain the comparison result of the first target vehicle and the vehicle to be identified; if the comparison result includes that the first target vehicle is the same as the vehicle to be identified, determine the second An image includes the first target vehicle.

In combination with any embodiment of the present disclosure, the acquisition unit 13 is further configured to: obtain the first target vehicle and the target vehicle according to the first similarity between the target feature data and the first feature data. Before identifying the comparison result of the vehicle, at least one first target vehicle attribute of the first target vehicle is obtained;

The image processing device further includes: an extraction unit 16 configured to: perform vehicle attribute extraction processing on the second image to obtain at least one first vehicle attribute of the vehicle to be identified;

The first processing unit 11 is configured to: obtain a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity and the second similarity, the second similarity being the The similarity between the at least one first target vehicle attribute and the at least one first vehicle attribute.

In combination with any embodiment of the present disclosure, the first processing unit 11 is configured to: perform weighted summation of the first similarity and the second similarity to obtain a third similarity; When the degree of similarity is greater than the similarity threshold, it is determined that the comparison result includes that the vehicle to be identified is the same as the target vehicle; when the third similarity is less than or equal to the similarity threshold, it is determined that the comparison The result includes that the vehicle to be identified is different from the target vehicle.

In combination with any implementation manner of the present disclosure, the first camera is deployed in the target area;

The acquisition unit 13 is configured to: acquire a database of vehicles to be tracked, the database of vehicles to be tracked includes characteristic data of at least one vehicle to be tracked, and the at least one vehicle to be tracked includes vehicles that need to be tracked in the target area track vehicle, and the target vehicle is any one of the at least one vehicle to be tracked; in the case of acquiring the second image collected by the first camera, from the vehicle to be tracked The database obtains a feature data as the target feature data.

In combination with any embodiment of the present disclosure, the acquisition unit 13 is configured to: acquire at least one fourth image, the at least one fourth image includes the at least one vehicle to be tracked; according to the at least one first Four images to obtain the vehicle database to be tracked.

In combination with any embodiment of the present disclosure, the acquisition unit 13 is configured to: acquire the at least one fourth image captured by at least one checkpoint camera, and the at least one checkpoint camera is deployed at the entrance and exit of the target area .

In combination with any embodiment of the present disclosure, the comparison result includes that the first target vehicle is the same as the vehicle to be identified, and the acquiring unit 13 is further configured to: acquire the fifth image of the target area and the The first position of the first camera in the fifth image; the image processing device further includes: a third processing unit 17, and is also configured to: according to the first position, determine that the first target vehicle is in the The second position in the fifth image.

In some embodiments, the functions of the device provided by the embodiments of the present disclosure or the modules included therein can be used to execute the methods described in the above method embodiments, and the implementation can refer to the descriptions of the above method embodiments.

FIG. 5 is a schematic diagram of a hardware structure of an image processing device provided by an embodiment of the present disclosure. The image processing device 2 includes a processor 21 , a memory 22 , an input device 23 and an output device 24 . The processor 21 , the memory 22 , the input device 23 and the output device 24 are coupled through connectors, and the connectors include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment of the present disclosure. It should be understood that in various embodiments of the present disclosure, coupling refers to interconnection in a specific manner, including direct connection or indirect connection through other devices, for example, connection through various interfaces, transmission lines, and buses.

The processor 21 may be one or more graphics processing units (graphics processing unit, GPU), and in the case where the processor 21 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. The processor 21 may be a processor group composed of multiple GPUs, and the multiple processors are coupled to each other through one or more buses. The processor may also be other types of processors, etc., which are not limited in this embodiment of the present disclosure.

The memory 22 can be used to store computer program instructions and various computer program codes including program codes for implementing the solutions of the present disclosure. Memory includes but not limited to random access memory (random access memory, RAM), read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable read only memory, EPROM), or portable Read-only memory (compact disc read-only memory, CD-ROM), which is used for related instructions and data.

The input device 23 is used for inputting data and/or signals and the output device 24 is used for outputting data and/or signals. The input device 23 and the output device 24 can be independent devices, or an integrated device.

It can be understood that in the embodiment of the present disclosure, the memory 22 may not only be used to store related instructions, but also be used to store related data.

It can be understood that Fig. 5 only shows a simplified design of an image processing device. In practical applications, the image processing device may also include other necessary components, including but not limited to any number of input/output devices, processors, memories, etc., and all image processing devices that can implement the embodiments of the present disclosure are included in this within the scope of public protection.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementation should not be considered beyond the scope of the present disclosure.

Those skilled in the art can clearly understand that for the convenience and brevity of description, the working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment. Those skilled in the art can also clearly understand that the descriptions of each embodiment of the present disclosure have their own emphases. For convenience and brevity of description, the same or similar parts may not be repeatedly described in different embodiments. Therefore, in a certain implementation For the parts not described in the examples or not described in detail, please refer to the records of other examples.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, all or part of the processes or functions according to the embodiments of the present disclosure will be generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted via a computer-readable storage medium. The computer instructions can be sent from a website site, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) Another website site, computer, server or data center for transmission. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including a server, a data center, and the like integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (digital versatile disc, DVD)), or a semiconductor medium (for example, a solid state disk (solid state disk, SSD) )wait.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments are realized. The processes can be completed by computer programs to instruct related hardware. The programs can be stored in computer-readable storage media. When the programs are executed , may include the processes of the foregoing method embodiments. The aforementioned storage medium includes: various media capable of storing program codes such as read-only memory (ROM) or random access memory (RAM), magnetic disk or optical disk.

Industrial Applicability

In the embodiment of the present disclosure, the image processing method includes: determining that the first target vehicle is in the shooting area of the first camera, determining that the first video source device of the first target vehicle is the first camera; When it is determined that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, the first video source device of the first target vehicle is switched from the first camera to the shooting area of the second camera. The second camera, the first camera is different from the second camera. In the embodiment of the present disclosure, when it is determined that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, the first video source device of the first target vehicle is transferred from the Switching the first camera to the second camera can improve the accuracy of the determined real-time first video source device, thereby improving the effect of video relay.

Claims

An image processing method, the method comprising:

When it is determined that the first target vehicle is in the shooting area of the first camera, it is determined that the first video source device of the first target vehicle is the first camera;

When it is determined that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, the first video source device of the first target vehicle is switched from the first camera to As for the second camera, the first camera is different from the second camera.
The method according to claim 1, wherein, before determining that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera, the method further comprises:

Acquire a time difference threshold and at least two first images, the time difference threshold is a positive number, the at least two first images both include the first target vehicle, and the at least one first image includes the first The image collected by the camera and the image collected by the second camera;

determining the difference between the time stamp of the second image and the time stamp of the third image, the second image being the image with the smallest time stamp collected by the second camera among the at least two first images, the The third image is an image with the smallest time stamp collected by the first camera among the at least two first images;

The determining that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera includes:

If the difference is greater than the time difference threshold, it is determined that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera.
The method according to claim 2, wherein the at least two first images include n images with the largest time stamp in the target vehicle image set, and the images in the target vehicle image set all include the first target vehicle, and The images in the target vehicle image set all include images captured by the first camera and images captured by the second camera, and the n is an integer greater than 1.
The method according to claim 2 or 3, wherein after said difference is greater than said time difference threshold, said determining that said first target vehicle enters from the shooting area of said first camera Before the shooting area of the second camera, the method also includes:

determining a first size of the first target vehicle in the second image and a second size of the first target vehicle in the third image;

The determining that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera includes:

In a case where the first size is greater than the second size, it is determined that the first target vehicle enters the shooting area of the second camera from the shooting area of the first camera.
The method according to any one of claims 1 to 4, wherein the method further comprises: displaying a shooting picture of the first video source device.
The method according to claim 5, wherein both the first camera and the second camera are deployed in a target area;

The method further includes: when it is determined that the first target vehicle has left the target area, stop displaying the shooting picture of the first video source device.
The method according to claim 5 or 6, wherein, the shooting picture of the first video source device is displayed in a first display area of a display page, and the display page further includes a second display area, and the second display area A shooting picture of a second video source device for displaying a second target vehicle, the first target vehicle is different from the second target vehicle.
The method according to any one of claims 1 to 7, wherein, before determining that the first target vehicle is in the shooting area of the first camera, the method further comprises:

acquiring a second image captured by the first camera;

The determining that the first target vehicle is in the shooting area of the first camera includes:

If it is determined that the second image includes the first target vehicle, it is determined that the first target vehicle is within a shooting area of the first camera.
The method according to claim 8, wherein the second image includes a vehicle to be identified, and before determining that the second image includes the first target vehicle, the method further comprises:

acquiring target characteristic data of the first target vehicle;

The determining that the second image includes the first target vehicle includes:

performing feature extraction processing on the second image to obtain first feature data of the vehicle to be identified;

Obtain a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity between the target feature data and the first feature data;

If the comparison result includes that the first target vehicle is the same as the vehicle to be identified, it is determined that the second image includes the first target vehicle.
The method according to claim 9, wherein, according to the first similarity between the target feature data and the first feature data, the comparison between the first target vehicle and the vehicle to be identified is obtained Before the result, the method also includes:

obtaining at least one first target vehicle attribute of the first target vehicle;

Carrying out vehicle attribute extraction processing on the second image to obtain at least one first vehicle attribute of the vehicle to be identified;

The obtaining the comparison result between the first target vehicle and the vehicle to be identified according to the first similarity between the target feature data and the first feature data includes:

A comparison result between the first target vehicle and the vehicle to be identified is obtained according to the first similarity and the second similarity, the second similarity is the attribute of the at least one first target vehicle and the A degree of similarity between at least one first vehicle attribute.
The method according to claim 10, wherein said obtaining a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity and the second similarity comprises:

performing weighted summation on the first similarity and the second similarity to obtain a third similarity;

In the case where the third similarity is greater than a similarity threshold, determining that the comparison result includes that the vehicle to be identified is the same as the target vehicle;

In a case where the third similarity is less than or equal to a similarity threshold, it is determined that the comparison result includes that the vehicle to be identified is different from the target vehicle.
The method according to any one of claims 9 to 11, wherein the first camera is deployed in the target area; the acquisition of the target feature data of the first target vehicle includes:

Obtaining a database of vehicles to be tracked, the database of vehicles to be tracked includes characteristic data of at least one vehicle to be tracked, the at least one vehicle to be tracked includes a vehicle that needs to track a trajectory in the target area, and the target vehicle is any one of the at least one vehicle to be tracked;

In the case of acquiring the second image captured by the first camera, acquiring a piece of feature data from the database of the vehicle to be tracked as the target feature data.
The method according to claim 12, wherein said obtaining the vehicle database to be tracked comprises:

acquiring at least one fourth image, the at least one fourth image including the at least one vehicle to be tracked;

Obtain the vehicle database to be tracked according to the at least one fourth image.
The method according to claim 13, wherein said acquiring at least one fourth image comprises:

The at least one fourth image captured by at least one checkpoint camera is acquired, and the at least one checkpoint camera is deployed at an entrance and exit of the target area.
The method according to any one of claims 12 to 14, wherein the comparison result includes that the first target vehicle is identical to the vehicle to be identified, and the method further comprises:

acquiring a fifth image of the target area and a first position of the first camera in the fifth image;

A second position of the first target vehicle in the fifth image is determined based on the first position.
An image processing device, the device comprising:

The first processing unit is configured to determine that the first video source device of the first target vehicle is the first camera when it is determined that the first target vehicle is within the shooting area of the first camera;

The second processing unit is configured to send the first video source device of the first target vehicle from the first video source device of the first target vehicle to the The first camera is switched to the second camera, and the first camera is different from the second camera.
The apparatus of claim 16, wherein the apparatus further comprises:

The acquiring unit is configured to acquire a time difference threshold and at least two first images before it is determined that the first target vehicle has driven from the shooting area of the first camera into the shooting area of the second camera, The time difference threshold is a positive number, the at least two first images both include the first target vehicle, and the at least one first image includes the image captured by the first camera and the image captured by the second camera. to the image;

The determining unit is configured to determine the difference between the time stamp of the second image and the time stamp of the third image, the second image being the smallest time stamp collected by the second camera among the at least two first images The image of the third image is the image with the smallest time stamp collected by the first camera among the at least two first images;

The second processing unit is configured to:

If the difference is greater than the time difference threshold, it is determined that the first target vehicle has entered the shooting area of the second camera from the shooting area of the first camera.
The device according to claim 17, wherein the at least two first images include n images with the largest time stamp in the target vehicle image set, and the images in the target vehicle image set all include the first target vehicle, and The images in the target vehicle image set all include images captured by the first camera and images captured by the second camera, and the n is an integer greater than 1.
The device according to any one of claims 16 to 18, wherein the device further comprises:

The display unit is configured to display the shooting picture of the first video source device.
The apparatus according to claim 19, wherein both the first camera and the second camera are deployed in a target area;

The display unit is further configured to: stop displaying the shooting picture of the first video source device when it is determined that the first target vehicle has left the target area.
The device according to any one of claims 19 or 20, wherein the shooting picture of the first video source device is displayed in a first display area of a display page, and the display page further includes a second display area, the first The second display area is used for displaying a shooting picture of a second video source device of a second target vehicle, and the first target vehicle is different from the second target vehicle.
The device according to any one of claims 16 to 21, wherein the device further includes an acquisition unit configured to: before determining that the first target vehicle is within the shooting area of the first camera, acquire the The second image collected by the first camera;

The first processing unit is configured as:

If it is determined that the second image includes the first target vehicle, it is determined that the first target vehicle is within a shooting area of the first camera.
The device according to claim 22, wherein the second image includes a vehicle to be identified, and the acquiring unit is further configured to: before determining that the second image includes the first target vehicle, acquire Target characteristic data of the first target vehicle;

The first processing unit is configured as:

performing feature extraction processing on the second image to obtain first feature data of the vehicle to be identified;

Obtain a comparison result between the first target vehicle and the vehicle to be identified according to the first similarity between the target feature data and the first feature data;

If the comparison result includes that the first target vehicle is the same as the vehicle to be identified, it is determined that the second image includes the first target vehicle.
The device according to claim 23, wherein the acquisition unit is further configured to: obtain the first target vehicle and the first target vehicle according to the first similarity between the target feature data and the first feature data. Before the comparison result of the vehicle to be identified, at least one first target vehicle attribute of the first target vehicle is obtained;

The device further includes: an extraction unit configured to perform vehicle attribute extraction processing on the second image to obtain at least one first vehicle attribute of the vehicle to be identified;

The first processing unit is configured as:

A comparison result between the first target vehicle and the vehicle to be identified is obtained according to the first similarity and the second similarity, the second similarity is the attribute of the at least one first target vehicle and the A degree of similarity between at least one first vehicle attribute.
The apparatus according to claim 24, wherein the first processing unit is configured to:

performing weighted summation on the first similarity and the second similarity to obtain a third similarity;

In the case where the third similarity is greater than a similarity threshold, determining that the comparison result includes that the vehicle to be identified is the same as the target vehicle;

In a case where the third similarity is less than or equal to a similarity threshold, it is determined that the comparison result includes that the vehicle to be identified is different from the target vehicle.
The device according to any one of claims 23 to 25, wherein the first camera is deployed in a target area;

The acquisition unit is configured as:

Obtaining a database of vehicles to be tracked, the database of vehicles to be tracked includes characteristic data of at least one vehicle to be tracked, the at least one vehicle to be tracked includes a vehicle that needs to track a trajectory in the target area, and the target vehicle is any one of the at least one vehicle to be tracked;

In the case of acquiring the second image captured by the first camera, acquiring a piece of feature data from the database of the vehicle to be tracked as the target feature data.
The device according to claim 26, wherein the acquiring unit is configured to:

acquiring at least one fourth image, the at least one fourth image including the at least one vehicle to be tracked;

Obtain the vehicle database to be tracked according to the at least one fourth image.
The device according to claim 27, wherein the acquisition unit is configured to:

The at least one fourth image captured by at least one checkpoint camera is acquired, and the at least one checkpoint camera is deployed at an entrance and exit of the target area.
The device according to any one of claims 26 to 28, wherein the comparison result includes that the first target vehicle is the same as the vehicle to be identified, and the acquisition unit is further configured to: acquire the target area The fifth image and the first position of the first camera in the fifth image; the device further includes: a third processing unit, further configured to determine the first target vehicle according to the first position at the second position in the fifth image.
An electronic device, comprising: a processor and a memory, the memory is used to store computer program codes, the computer program codes include computer instructions, and when the processor executes the computer instructions, the electronic device executes A method as claimed in any one of claims 1 to 15.
A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is made to perform the claims The method described in any one of 1 to 15.
A computer program product comprising a computer program or instructions which, when run on a computer, causes the computer to perform the method according to any one of claims 1 to 15 .