Information processing method, driving recorder, edge node, device, and storage medium

Abstract

Embodiments of the present application disclose an information processing method, a driving recorder, an edge node, communication equipment, a chip and a computer readable storage medium, wherein the method is applied to the driving recorder and includes: judging whether a vehicle in a video has a violation behavior; if the judgment result indicates that the vehicle has the violation behavior, sending first information to an edge node corresponding to the driving recorder; the first information includes at least one of the following: the video, a location of the video shooting and a time of the video shooting.

Description

Technical Field

[0001] This application relates to the field of edge computing technology, and in particular to an information processing method, a dashcam, an edge node, a communication device, and a computer-readable storage medium. Background Technology

[0002] In today's society, with the increasing number of vehicles, traffic violations also occur frequently, such as crossing solid lines and using emergency lanes on highways. These behaviors are dangerous and need to be prohibited. Generally, in such cases, surveillance cameras installed along the road are used to take photos and then process them. However, surveillance cannot cover all road sections, and often these violations are missed. Some people take photos of these violations and then hand them over to the traffic management department for punishment. This can reduce the occurrence of violations, but it is time-consuming, labor-intensive, and inefficient. Summary of the Invention

[0003] This application provides an information processing method, a dashcam, an edge node, a communication device, and a computer-readable storage medium.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] In a first aspect, embodiments of this application provide an information processing method applied to a dashcam, comprising:

[0006] Determine whether the vehicles in the video have committed any traffic violations;

[0007] If the judgment result indicates that a violation has occurred, the first information is sent to the edge node corresponding to the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

[0008] Secondly, embodiments of this application provide an information processing method applied to edge nodes, including:

[0009] Receive first information sent by the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured;

[0010] The license plate information of the offending vehicle is extracted from the video, and the violation information is sent to the cloud server; the violation information includes at least one of the following: license plate information, the location where the video was taken, and the time when the video was taken.

[0011] Thirdly, this application provides a dashcam, comprising:

[0012] Judgment unit: Used to determine whether the vehicle in the video has committed a traffic violation;

[0013] Sending unit: If the judgment result indicates that there is a violation, it is used to send the first information to the edge node corresponding to the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

[0014] Fourthly, this application provides an edge node, characterized in that it includes:

[0015] Receiving unit: used to receive first information sent by the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured;

[0016] Processing unit: used to extract the license plate information of the vehicle violating the traffic violation from the video and send the violation information to the cloud server; the violation information includes at least one of the following: license plate information, the location where the video was taken, and the time when the video was taken.

[0017] Fifthly, this application provides a communication device, including: a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute any of the information processing methods provided in the embodiments of this application.

[0018] Sixthly, this application provides a chip, including: a processor, configured to call and run a computer program from a memory, causing a device equipped with the chip to execute any of the information processing methods provided in the embodiments of this application.

[0019] In a seventh aspect, this application provides a computer-readable storage medium for storing a computer program that causes a computer to execute any of the information processing methods provided in the embodiments of this application.

[0020] The information processing method provided in this application embodiment can fully utilize the characteristics of dashcam video recording and edge computing to automatically and quickly identify violations, saving a lot of manpower and time, improving efficiency, and enabling urban video security to search for specific vehicles. Attached Figure Description

[0021] Figure 1 Schematic diagram of the implementation flow of the information processing method provided in the embodiments of this application Figure 1 ;

[0022] Figure 2 A schematic diagram illustrating offset calculation provided in an embodiment of this application;

[0023] Figure 3 Schematic diagram of the implementation flow of the information processing method provided in the embodiments of this application Figure 2 ;

[0024] Figure 4 This is a schematic diagram of the network structure for extracting license plate information provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram of the RDB structure provided in an embodiment of this application;

[0026] Figure 6 Implementation flow of the information processing method provided in the embodiments of this application Figure 3 ;

[0027] Figure 7 This is a schematic diagram of the structure of the dashcam 700 provided in the embodiments of this application;

[0028] Figure 8 This is a schematic diagram of the structure of the edge node 800 provided in an embodiment of this application;

[0029] Figure 9 A schematic structural diagram of a communication device provided in an embodiment of this application;

[0030] Figure 10 This is a schematic structural diagram of the chip provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0032] It should be noted that, in the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, in the embodiments of this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0033] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0034] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0035] Figure 1Schematic diagram of the implementation flow of the information processing method provided in the embodiments of this application Figure 1 ,like Figure 1 As shown in the figure, this application provides an information processing method applied to a dashcam, the method including the following steps:

[0036] Step 101: Determine whether the vehicle in the video has committed any traffic violations.

[0037] Here, violations can include changing lanes over a solid line, using the emergency lane, speeding, etc., and this application does not limit them.

[0038] For example, a neural network and positioning system can be built into a dashcam. The neural network can be used to determine whether a vehicle in the video has committed a traffic violation. In practical applications, a lightweight neural network can be set up in the dashcam. The lightweight neural network can use MobileNet's depthwise separable convolution to replace the original convolutional layer. The parameters can be pre-trained in the cloud and then built into the dashcam. The convolution result of depthwise separable convolution is the same as that of the original convolution, but it can greatly reduce the number of parameters and the amount of computation, save computing time and storage space, and ensure that the dashcam can respond quickly.

[0039] Step 102: If the judgment result indicates that there is a violation, the first information is sent to the edge node corresponding to the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

[0040] In practical applications, the video needs to include footage of the vehicle committing the traffic violation, and the video length can be set according to the actual situation.

[0041] When multiple dashcams determine that the same vehicle has committed a traffic violation within a specific timeframe, for example, when vehicle A captures vehicle B's violation, vehicle A uses the location functions of both dashcams to calculate the distance between the two vehicles. Vehicle C, which calculates its distance to vehicle B first, sends a message to vehicles within a certain radius (e.g., 5 meters) indicating that it has captured vehicle B's violation. If a vehicle receiving this message has also captured vehicle B's violation, it calculates its straight-line distance and offset to vehicle B and sends this information to vehicle C. From the moment vehicle C sends its message, a short period, such as 10 seconds, is set to collect all transmitted distance and offset information. After this period, vehicle C calculates the distances and then selects the vehicle with the smallest result from smallest to largest to send a response message. If its own result is the smallest, it does not send messages to other vehicles.

[0042] Vehicles that receive a response from vehicle C (or vehicle C itself) will report the captured traffic violation information to the edge node. Other vehicles that do not receive a response will not report traffic violations.

[0043] Based on this, in this embodiment of the application, when multiple dashcams determine that the same vehicle has committed a traffic violation within a first specific time period, the step of sending the first information to the edge node corresponding to the dashcam includes:

[0044] The first dashcam that calculates its distance from the violating vehicle sends a second message to all dashcams within a specific range; the second message indicates that the first dashcam captured the violating vehicle's traffic violation.

[0045] If, within a second specific time period, the dashcam that received the second information captures the traffic violation of the offending vehicle, then the dashcam sends third information to the first dashcam; the third information represents the distance between the dashcam and the offending vehicle.

[0046] The first dashcam sends a return message to the dashcam with the smallest distance; the return message is used to instruct the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node.

[0047] Here, distance includes straight-line distance and vehicle B's offset. Offset calculation is as follows: Figure 2 As shown, Figure 2 This is a schematic diagram of offset calculation provided in an embodiment of this application, in which the captured image N (where N is an odd number) is divided into equal parts. Figure 2 Divide the vehicle into 5 equal parts, with the middle part having an offset of 0, and the offset increasing towards both sides. In practical applications, the offset can be determined according to the position of the license plate number, such as... Figure 2 In the diagram above, the offset of vehicle 1 is 1, the offset of vehicle 2 is 2, and the offset of vehicle 3 in the diagram below is 0. Correspondingly, after receiving the straight-line distance and offset information, vehicle C calculates the distance according to a certain ratio between the two, such as the straight-line distance accounting for 50% and the offset accounting for 50%.

[0048] Based on this, in this embodiment of the application, the distance includes the straight-line distance and offset between the dashcam and the vehicle violating the traffic rules. Correspondingly, before the first dashcam sends a return message to the dashcam with the smallest distance, the following steps are also included:

[0049] The first dashcam calculates the distance between each dashcam and the violating vehicle based on the straight-line distance and offset received from each dashcam, according to a preset weight.

[0050] Dashcams can also perform vehicle searches, functioning as cameras in video security systems. Edge nodes send information about specific vehicles to their corresponding dashcams. These vehicles can be civilian vehicles or special vehicles such as ambulances and fire trucks. Once the dashcam detects a target vehicle in the video, it sends the video, the location where the video was captured, and the time the video was captured to its corresponding edge node for further processing. In practical applications, dashcams can use built-in neural networks to recognize license plate information to determine if it is a target vehicle.

[0051] Based on this, in the embodiments of this application, the information processing method further includes:

[0052] Receive vehicle information sent by edge nodes;

[0053] Search for the target vehicle based on the vehicle information;

[0054] When a target vehicle is found, a fourth piece of information is sent to its corresponding edge node. The fourth piece of information includes at least one of the following: video, the location where the video was taken, and the time when the video was taken.

[0055] Figure 3 Schematic diagram of the implementation flow of the information processing method provided in the embodiments of this application Figure 2 ,like Figure 3 As shown in the figure, this application provides an information processing method applied to edge nodes, the method including the following steps:

[0056] Step 301: Receive first information sent by the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured;

[0057] Step 302: Extract the license plate information of the vehicle violating the traffic violation from the video and send the violation information to the cloud server; the violation information includes at least one of the following: license plate information, the location where the video was taken, and the time when the video was taken.

[0058] After receiving the first information from the dashcam, the edge node begins task analysis to extract the license plate information of the offending vehicle from the video.

[0059] To improve the accuracy of traffic violation judgment, before extracting the license plate information of the offending vehicle, a more accurate neural network is used to determine whether the vehicle in the video has actually committed a traffic violation. If no violation is found, no further processing is performed. If a violation is confirmed, the violation information of the offending vehicle is then extracted.

[0060] Based on this, in this embodiment of the application, before extracting the license plate information of the offending vehicle from the video, the method further includes:

[0061] The second neural network is used to determine whether there are any violations in the video;

[0062] If the judgment result indicates that there is a violation, then the license plate information of the vehicle violating the violation is extracted from the video;

[0063] If the judgment result indicates that there is no violation, no further processing will be performed; wherein, the dashcam has a built-in first neural network, and the accuracy of the second neural network is greater than that of the first neural network.

[0064] To ensure the accuracy of license plate information extraction from edge nodes, a screenshot of a single frame from the video containing the illegal vehicle's behavior is taken and reconstructed at super resolution to obtain clear license plate information of the illegal vehicle, thus ensuring the accuracy of license plate information extraction.

[0065] For example, refer to Figure 4 , Figure 4 This is a schematic diagram of the network structure for extracting license plate information provided in an embodiment of this application, such as... Figure 4 As shown, the V channel of the HSV of the cropped low-resolution image is used as the input to the network, and a convolution operation is performed on it as follows: F i (Y)=W i *F1(Y)+B i Among them, W i The convolution kernel represents the convolution operation, F1(Y) represents the input image, and B... i F represents the bias of the convolution operation. i (Y) represents the output image after the convolution operation.

[0066] The result F after convolution i (Y) Perform three RDB operations, refer to Figure 5 , Figure 5 This is a schematic diagram of the RDB structure provided in the embodiments of this application, such as... Figure 5 As shown, this embodiment introduces multi-scale convolution operations into the RDB structure. Each RDB contains three multi-scale convolutions, followed by a concatenated concatenation layer and a convolutional layer. The multi-scale convolution operation can be described by the following formula:

[0067] F i (Y)=P([W 3*3 *(W i *F1(Y)+B i )+B j W 5*5 *(W i *F1(Y)+B i )+B k ]), where W i *F1(Y)+Bi W represents the result after the first convolutional layer with multi-scale convolution. 3*3 and W 5*5 The value represents the size of the convolution kernel, P represents the activation function, and B represents the value of the convolution kernel. k [] represents the bias setting, and [] represents the cascading operation.

[0068] The multi-scale convolution operation is followed by a concatenation operation and a convolution operation, which can be expressed by the following formula: F d,con =P((W i *[F i (Y)]+B i ), where F d,con This represents the output of an RDB.

[0069] It should be noted that the size of the convolution kernel can be set according to the actual situation, and this application does not limit it.

[0070] like Figure 4 As shown, the result of three RDB operations is convolved once and then deconvolved once to obtain an image twice the size of the original image. Then, the high-frequency information of the bicubic interpolation 2x image of the original image is subjected to residual operation to obtain the reconstructed high-resolution 2x image.

[0071] The reconstructed high-resolution 2x image is then subjected to convolution and triple RDB operations. The result of the triple RDB operation is then subjected to a convolution operation and a deconvolution operation to obtain an image four times the size of the original image. This image is then subjected to residual operations with the high-frequency information of the bicubic interpolation 4x image of the input original image and the high-frequency information of the bicubic interpolation 2x image of the high-resolution 2x image to obtain the reconstructed high-resolution 4x image.

[0072] For example, the high-frequency information of the original image bicubic interpolation 2x image can be obtained through the following steps: Step 1: Perform bicubic interpolation on the original image to convert it into a 2x image, and use wavelet to denoise the 2x image obtained in Step 1. The purpose is to remove some noise obtained from the bicubic interpolation. Step 3: Use a high-pass filter to enhance the image edges of the denoised 2x image obtained in Step 2, while preserving high-frequency information. The steps for obtaining the high-frequency information of the original image bicubic interpolation 4x image and the high-frequency information of the high-resolution 2x image bicubic interpolation 2x image are the same as the above steps, and will not be repeated here.

[0073] The license plate information is located by performing a convolution operation on a high-resolution 4x image, and then the license plate information is extracted by performing a convolution operation.

[0074] Based on this, in this embodiment of the application, extracting the license plate information of the vehicle violating the traffic rules from the video includes:

[0075] Perform super-resolution reconstruction on the first image, which is a frame from the video.

[0076] Based on the first image after super-resolution reconstruction, the license plate information is extracted; wherein, the super-resolution reconstruction operation includes:

[0077] Perform a cubic residual dense block RDB operation on the first image to reconstruct a 2x image of the first image; perform a residual operation on the high-frequency information of the 2x image and the bicubic interpolation of the first image to obtain a high-resolution 2x image;

[0078] Perform three RDB operations on the high-resolution 2x image to reconstruct a 4x image of the first image; perform residual operations on the 4x image, the high-frequency information of the first image bicubic interpolated 2x image, and the high-frequency information of the first image bicubic interpolated 4x image to obtain a high-resolution 4x image; wherein, the RDB operation includes: multi-scale convolution operation.

[0079] This application introduces multi-scale convolution operations into the RDB (Real-Time Deposition Model). Multi-scale convolution layers, through convolution operations with different kernels, enrich the image features, enabling the RDB to extract more details and improve image resolution. Interpolation, denoising, and edge enhancement are sequentially performed on the violation image to extract high-frequency components. High-resolution 2x and 4x images are gradually reconstructed by fully utilizing the original image information. The 4x image reconstruction also utilizes high-frequency information from the reconstructed 2x image, allowing for a gradual improvement in resolution by fully leveraging the high-frequency information from both the original and reconstructed images. The reconstructed image is then used to locate and extract license plate information, improving the accuracy of information extraction.

[0080] Edge nodes can also receive vehicle information from the cloud server and then send the vehicle information to their corresponding dashcams for vehicle search services. When the dashcam determines that the vehicle has been found, it sends the video, the location where the video was captured, and the time when the video was captured to the edge node. After receiving the video, the edge node uses a more accurate neural network to determine whether it is the target vehicle. If it finds that it is not the target vehicle, it does not perform any further processing. If it is the target vehicle, it sends a message to the cloud server to inform the cloud server that the target vehicle has been found.

[0081] Based on this, the information processing method provided in the embodiments of this application further includes:

[0082] Receive vehicle information sent by the cloud server;

[0083] The vehicle information is sent to at least one corresponding dashcam.

[0084] Receive fourth information sent by the dashcam; the fourth information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured;

[0085] Based on the fourth information, determine whether it is the target vehicle; if the determination result indicates that it is the target vehicle, then send the fifth information to the cloud server; the fifth information indicates that the target vehicle has been found.

[0086] refer to Figure 6 , Figure 6 Implementation flow of the information processing method provided in the embodiments of this application Figure 3 ,like Figure 6 As shown, the information processing method provided in this application embodiment includes:

[0087] The dashcam uses a lightweight CNN network to initially determine whether the vehicle in front has committed a traffic violation or to receive instructions from the edge node to search for a specific vehicle. If the dashcam detects a traffic violation or finds a specific vehicle, it sends the relevant information about the violation or the specific vehicle to the edge node.

[0088] Edge nodes receive instructions from the cloud to search for a specific vehicle and then forward these instructions to their corresponding dashcams. The edge nodes receive relevant information from the dashcams to further determine if a traffic violation has occurred or if the vehicle is the specific one being searched for. If a violation is confirmed or the specific vehicle is found, the edge nodes then send the relevant information to the cloud server for processing.

[0089] The cloud sends information about the specific vehicle to be searched to the edge node. The edge node receives information about vehicle violations or the specific vehicle that has been found and performs the appropriate processing.

[0090] The information processing method provided in this application utilizes cloud video recorded by a dashcam and edge computing to determine whether a vehicle has committed a traffic violation. A lightweight convolutional neural network is built into the dashcam to roughly determine the occurrence of a violation, giving the dashcam simple detection functions and the ability to detect special vehicles, automatically identifying traffic violations by vehicles ahead.

[0091] This application also proposes a reporting selection algorithm that only reports traffic violations for which the minimum straight-line distance and offset are calculated. Then, edge nodes make detailed judgments on whether a violation has occurred, and the proposed convolutional neural network is used to perform super-resolution processing on the violation image and extract license plate information.

[0092] The cloud server can also propose searching for specific vehicles in video security scenarios. It sends the specified vehicle information to edge nodes, which then forward the information to connected dashcams, which function as cameras within the video security system. The dashcams have a built-in simple license plate recognition network for basic license plate matching. Once a match is successful, the information is sent to the edge nodes, which then confirm the information before sending it to the cloud server. This enables the search for specific vehicles in urban video security systems.

[0093] This application also provides a dashcam 700, see reference. Figure 7 The dashcam and edge node 700 in this embodiment include:

[0094] Judgment Unit 710: Used to determine whether the vehicle in the video has committed a traffic violation;

[0095] Sending unit 720: If the judgment result indicates that there is a violation, it is used to send the first information to the edge node corresponding to the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

[0096] In this embodiment of the application, when multiple dashcams determine that the same vehicle has committed a traffic violation within a first specific time period, the sending unit 720 is further configured to: send second information to all dashcams within a specific range; the second information indicates that the dashcam has captured the traffic violation of the violating vehicle; further configured to send third information to the first dashcam; the third information indicates the distance between the dashcam and the violating vehicle; further configured to send a return message to the dashcam with the smallest distance; the return message is used to instruct the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node.

[0097] In this embodiment of the application, the distance includes the straight-line distance and offset between the dashcam and the vehicle violating the traffic rules. The judgment unit 710 is further configured to calculate the distance between each dashcam and the vehicle violating the traffic rules based on the received straight-line distance and offset of each dashcam according to a preset weight.

[0098] In this embodiment of the application, the judgment unit 710 is further configured to receive vehicle information sent by the edge node and search for a target vehicle based on the vehicle information; when a target vehicle is found, the sending unit 720 is further configured to send fourth information to its corresponding edge node, the fourth information including at least one of the following: video, the location where the video was taken, and the time when the video was taken.

[0099] Those skilled in the art should understand that Figure 7The functions of each unit in the dashcam 700 shown can be understood by referring to the relevant description of the aforementioned method. Figure 7 The functions of each unit in the dashcam 700 shown can be implemented through a program running on a processor or through specific logic circuits.

[0100] This application embodiment also provides an edge node 800, see reference Figure 8 The dashcam and edge node 800 in this embodiment include:

[0101] Receiving unit 810: Used to receive first information sent by the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured;

[0102] Processing unit 820: used to extract the license plate information of the vehicle violating the traffic violation from the video and send the violation information to the cloud server; the violation information includes at least one of the following: license plate information, the location where the video was taken, and the time when the video was taken.

[0103] In this embodiment of the application, the processing unit 820 is further configured to: determine whether there is a traffic violation in the video through a second neural network; if the judgment result indicates that there is a traffic violation, then extract the license plate information of the vehicle violating the violation from the video; if the judgment result indicates that there is no traffic violation, then no further processing is performed; wherein, the dashcam has a built-in first neural network, and the accuracy of the second neural network is greater than the accuracy of the first neural network.

[0104] In this embodiment, the processing unit 820 is specifically used to perform a super-resolution reconstruction operation on a first image, the first image being a frame from the video; and to extract the license plate information based on the super-resolution reconstructed first image; wherein the super-resolution reconstruction operation includes: performing a cubic residual dense block (RDB) operation on the first image to reconstruct a 2x image of the first image; performing a residual operation on the 2x image and the high-frequency information of the bicubic interpolation 2x image of the first image to obtain a high-resolution 2x image; performing a cubic RDB operation on the high-resolution 2x image to reconstruct a 4x image of the first image; and performing a residual operation on the 4x image, the high-frequency information of the bicubic interpolation 2x image of the first image, and the high-frequency information of the bicubic interpolation 4x image of the first image to obtain a high-resolution 4x image; wherein the RDB operation includes a multi-scale convolution operation.

[0105] In this embodiment of the application, the processing unit 820 is further configured to: receive vehicle information sent by a cloud server; send the vehicle information to at least one corresponding dashcam; receive fourth information sent by the dashcam; the fourth information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured; determine whether it is a target vehicle based on the fourth information; if the determination result indicates that it is the target vehicle, send fifth information to the cloud server; the fifth information indicates that the target vehicle has been found.

[0106] Those skilled in the art should understand that Figure 8 The functionality of each unit in the edge node 800 shown can be understood by referring to the relevant description of the aforementioned method. Figure 8 The functions of each unit in the edge node 800 shown can be implemented by a program running on a processor or by specific logic circuits.

[0107] Figure 9 This is a schematic structural diagram of a communication device 900 provided in an embodiment of this application. Figure 9 The communication device 900 shown includes a processor 910, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0108] Optionally, such as Figure 9 As shown, the communication device 900 may further include a memory 920. The processor 910 can retrieve and run computer programs from the memory 920 to implement the methods described in this embodiment.

[0109] The memory 920 can be a separate device independent of the processor 910, or it can be integrated into the processor 910.

[0110] Optionally, such as Figure 9 As shown, the communication device 900 may also include a transceiver 930, which the processor 910 can control to communicate with other devices. Specifically, it can send information or data to other devices or receive information or data sent by other devices.

[0111] The transceiver 930 may include a transmitter and a receiver. The transceiver 930 may further include antennas, and the number of antennas may be one or more.

[0112] The communication device 900 may specifically be a dashcam or an edge node in the embodiments of this application, and the communication device 900 can implement the corresponding processes implemented by the dashcam and the edge node in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0113] Figure 10This is a schematic structural diagram of the chip according to an embodiment of this application. Figure 10 The chip 1000 shown includes a processor 1010, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0114] Optionally, such as Figure 10 As shown, chip 1000 may further include memory 1020. Processor 1010 can retrieve and run computer programs from memory 1020 to implement the methods described in this embodiment.

[0115] The memory 1020 can be a separate device independent of the processor 1010, or it can be integrated into the processor 1010.

[0116] Optionally, the chip 1000 may also include an input interface 1030. The processor 1010 can control the input interface 1030 to communicate with other devices or chips, specifically, to acquire information or data sent by other devices or chips.

[0117] Optionally, the chip 1000 may also include an output interface 1040. The processor 1010 can control the output interface 1040 to communicate with other devices or chips, specifically, to output information or data to other devices or chips.

[0118] This chip can be applied to the dashcam and edge node in the embodiments of this application, and the chip can implement the corresponding processes implemented by the dashcam and edge node in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0119] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0120] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0121] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0122] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0123] This application also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to the dashcam and edge node in the embodiments of this application, and the computer program causes the computer to execute the corresponding processes implemented by the dashcam and edge node in the various methods of the embodiments of this application. For the sake of brevity, further details are omitted here.

[0124] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0127] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0129] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or dashcam, edge node, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An information processing method, characterized in that, Applications in dashcams include: Determine whether the vehicles in the video have committed any traffic violations; When multiple dashcams determine that the same vehicle has committed a traffic violation within a specific time period, the first dashcam that calculates its distance from the violating vehicle sends a second message to all dashcams within a specific range; the second message indicates that the first dashcam has captured the traffic violation of the violating vehicle. If, within a second specific time period, the dashcam that received the second information captures the traffic violation of the offending vehicle, then the dashcam sends third information to the first dashcam; the third information represents the distance between the dashcam and the offending vehicle; the distance includes the straight-line distance and offset between the dashcam and the offending vehicle. The first dashcam calculates the distance between each dashcam and the violating vehicle based on the straight-line distance and offset received from each dashcam, according to a preset weight. The first dashcam sends a return message to the dashcam with the smallest distance; the return message is used to instruct the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

2. The information processing method according to claim 1, characterized in that, Also includes: Receive vehicle information sent by edge nodes; Search for the target vehicle based on the vehicle information; When a target vehicle is found, a fourth piece of information is sent to its corresponding edge node. The fourth piece of information includes at least one of the following: video, the location where the video was taken, and the time when the video was taken.

3. An information processing method, characterized in that, Applied to edge nodes, including: The system receives first information from a dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time the video was captured; the first information is generated when multiple dashcams determine that the same vehicle has committed a traffic violation within a first specific time period, and the first dashcam that calculates its distance from the violating vehicle sends second information to all dashcams within a specific range; the second information indicates that the first dashcam has captured the traffic violation of the violating vehicle; within a second specific time period, if a dashcam that received the second information has captured the traffic violation of the violating vehicle, then that dashcam sends third information to... The first dashcam; the third information represents the distance between the dashcam and the vehicle violating the traffic rules; the distance includes the straight-line distance and offset between the dashcam and the vehicle violating the traffic rules; the first dashcam calculates the distance between each dashcam and the vehicle violating the traffic rules based on the received straight-line distances and offsets from each dashcam, according to a preset weight; the first dashcam sends a return message to the dashcam with the smallest distance; the return message instructs the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node; the dashcam with the smallest distance responds to the return message and sends it to the edge node; The license plate information of the offending vehicle is extracted from the video, and the violation information is sent to the cloud server; the violation information includes at least one of the following: license plate information, the location where the video was taken, and the time when the video was taken.

4. The information processing method according to claim 3, characterized in that, Before extracting the license plate information of the offending vehicle from the video, the process also includes: The second neural network is used to determine whether there are any violations in the video; If the judgment result indicates that there is a violation, then the license plate information of the vehicle violating the violation is extracted from the video; If the judgment result indicates that there is no violation, no further processing will be performed; wherein, the dashcam has a built-in first neural network, and the accuracy of the second neural network is greater than that of the first neural network.

5. The information processing method according to claim 3, characterized in that, The extraction of license plate information of the offending vehicle from the video includes: Perform super-resolution reconstruction on the first image, which is a frame from the video. Based on the first image after super-resolution reconstruction, the license plate information is extracted; wherein, the super-resolution reconstruction operation includes: Perform a cubic residual dense block RDB operation on the first image to reconstruct a 2x image of the first image; perform a residual operation on the high-frequency information of the 2x image and the bicubic interpolation of the first image to obtain a high-resolution 2x image; Perform three RDB operations on the high-resolution 2x image to reconstruct a 4x image of the first image; perform residual operations on the 4x image, the high-frequency information of the first image bicubic interpolated 2x image, and the high-frequency information of the first image bicubic interpolated 4x image to obtain a high-resolution 4x image; wherein, the RDB operation includes: multi-scale convolution operation.

6. The information processing method according to claim 3, characterized in that, Also includes: Receive vehicle information sent by the cloud server; The vehicle information is sent to at least one corresponding dashcam. Receive fourth information sent by the dashcam; the fourth information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured; Based on the fourth piece of information, determine whether it is the target vehicle; If the result indicates that the target vehicle is identified, then the fifth piece of information is sent to the cloud server. The fifth piece of information indicates that the target vehicle has been located.

7. A dashcam, characterized in that, include: Judgment unit: Used to determine whether a vehicle in the video has committed a traffic violation; Sending unit: When multiple dashcams determine that the same vehicle has committed a traffic violation within a first specific time period, the first dashcam that calculates its distance to the violating vehicle sends second information to all dashcams within a specific range; the second information indicates that the first dashcam has captured the traffic violation of the violating vehicle; within a second specific time period, if a dashcam that receives the second information has captured the traffic violation of the violating vehicle, then that dashcam sends third information to the first dashcam; the third information indicates the distance between the dashcam and the violating vehicle; the distance includes the straight-line distance and offset between the dashcam and the violating vehicle; the first dashcam calculates the distance between each dashcam and the violating vehicle based on the received straight-line distance and offset of each dashcam according to a preset weight; the first dashcam sends a return message to the dashcam with the smallest distance; the return message is used to instruct the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured.

8. An edge node, characterized in that, include: Receiving unit: used to receive first information sent by the dashcam; the first information includes at least one of the following: video, the location where the video was captured, and the time when the video was captured; The first information is generated when multiple dashcams determine that the same vehicle has committed a traffic violation within a first specific time period. The first dashcam, which calculates its distance to the violating vehicle, sends a second information to all dashcams within a specific range. The second information indicates that the first dashcam has captured the traffic violation. Within a second specific time period, if a dashcam that received the second information also captured the traffic violation, it sends a third information to the first dashcam. The third information indicates the distance between the dashcam and the violating vehicle, including the straight-line distance and offset. The first dashcam calculates the distance between each dashcam and the violating vehicle based on the received straight-line distances and offsets from each dashcam, according to a preset weight. The first dashcam sends a return message to the dashcam with the smallest distance. The return message instructs the dashcam with the smallest distance to send its corresponding first information to its corresponding edge node. The dashcam with the smallest distance responds to the return message and sends it to the edge node. Processing unit: used to extract the license plate information of the offending vehicle from the video and send the violation information to the cloud server; the violation information includes at least one of the following: license plate information, video shooting location and video shooting time.

9. A communication device, characterized in that, include: A processor and a memory, the memory for storing computer programs, the processor for calling and running the computer programs stored in the memory to perform the information processing method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, Used to store computer programs that cause a computer to perform the information processing method as described in any one of claims 1-6.

Images