A vehicle-road-cloud collaborative system based on 5G network
Through the vehicle-road cloud collaboration system based on 5G network, the vehicle-mounted camera and roadside information transmission module are used to calculate the distance between vehicles and issue early warnings when visibility is low, solving the problem of difficulty in obtaining information between vehicles under abnormal weather conditions and improving the problem of improving the Traffic safety and management efficiency are achieved.
Patent Information
- Application Number
- CN202411017768.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-07-29
AI Technical Summary
Under abnormal weather conditions, such as fog, rain, snow, etc., the reduction in visibility increases the risk of traffic accidents. It is difficult for the existing technology to obtain the relative position and distance information between vehicles in real time, resulting in preventing traffic accidents and improving road utilization efficiency. Difficulty.
Using a vehicle-road cloud collaboration system based on 5G network, 5G communication is established with vehicles through information transmission modules, combined with vehicle-mounted cameras and roadside information transmission modules, the vehicle distance between vehicles is calculated, and license plate recognition and ambiguity judgment is made when visibility is low. Issue an early warning.
Real-time and accurate vehicle distance information acquisition and visibility assessment have been achieved, traffic accident prevention and road safety have been improved, and traffic management has been optimized.
Smart Images

Figure CN118736893B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of traffic control technology, and in particular to a vehicle-road-cloud collaborative system based on a 5G network. Background Art
[0002] As a new generation of communication technology, 5G plays a vital role in many economic and social fields such as industrial Internet, smart life and information consumption with its key capabilities of high speed, low latency and large connection. In industries such as industry, agriculture, medical care, transportation, education, culture, sports and entertainment, the application of 5G has improved production efficiency, improved telemedicine services, and achieved the promotion of intelligent transportation systems.
[0003] In modern traffic systems, with the increasing number of vehicles and the complex and changeable road conditions, ensuring driving safety has become an increasingly prominent issue. Especially under abnormal weather conditions, such as fog, rain, snow, etc., the reduction in visibility greatly increases the risk of traffic accidents. Therefore, real-time and accurate acquisition of the relative position and visibility between vehicles is of great significance for preventing traffic accidents and improving road utilization efficiency. Based on this, the present invention proposes a vehicle-road-cloud collaborative system based on a 5G network. Summary of the invention
[0004] The purpose of the present invention is to provide a vehicle-road-cloud collaborative system based on a 5G network to solve the following technical problems:
[0005] Under abnormal weather conditions, such as fog, rain, and snow, the reduced visibility greatly increases the risk of traffic accidents. Therefore, real-time and accurate acquisition of relative position and distance information between vehicles is of great significance for preventing traffic accidents and improving road utilization efficiency.
[0006] The purpose of the present invention can be achieved by the following technical solutions:
[0007] A vehicle-road-cloud collaborative system based on a 5G network, comprising:
[0008] An information transmission module is used to establish 5G communication with the vehicle. The information transmission module is set beside the road. When a vehicle passes by the information transmission module, the vehicle's license plate information and current speed are sent to the information transmission module, and the real-time speed is continuously sent until it leaves the signal range;
[0009] The vehicle distance calculation module is used to mark the vehicle passing through the information transmission module at any time as Ci and the vehicle C i The vehicle that passes by is marked as C i+1 , when vehicle C i+1 When passing the information transmission module, according to the time difference between the two vehicles and vehicle C iThe speed data within the time difference is used to calculate the distance D between the two vehicles;
[0010] The license plate collection module is used to collect the license plate information of the vehicle C when the vehicle distance D is less than 2 times the preset safety distance. i+1 The on-board camera captures the front image and obtains the vehicle C i The system captures the license plate image and recognizes the license plate information, compares the recognized license plate information with the actual license plate information, determines the blurriness of the license plate, and marks the ratio of the blurriness of the license plate to the distance between the vehicles as the visibility index. When the visibility index is lower than the preset threshold, warnings are issued to both vehicles at the same time.
[0011] As a further solution of the present invention: in the license plate acquisition module, when the license plate acquisition module cannot acquire the vehicle C i When the license plate image is detected, a warning is issued directly to remind vehicle C i+1 Slow down.
[0012] As a further solution of the present invention: the specific process of calculating the vehicle distance in the vehicle distance calculation module is:
[0013] The information transmission module communicates with the vehicle C every unit time t. i Transmit the vehicle speed data, calculate the ratio of the time difference to the unit time difference and round it down to get n, and obtain the vehicle speed sequence v1, v2, ..., v n , then the calculation formula of vehicle distance D is:
[0014] As a further solution of the present invention: the license plate acquisition module also includes processing the front image:
[0015] The front image is converted into a grayscale image through grayscale processing, and the grayscale image is subjected to noise reduction processing. The grayscale image after noise reduction is subjected to edge detection based on an edge detection operator, and the grayscale image after edge detection is converted into a binary image.
[0016] As a further solution of the present invention: the process of the license plate acquisition module acquiring the license plate image is:
[0017] A rectangular edge frame is set, and the ratio of the horizontal side length to the vertical side length of the rectangular edge frame is 44±a:[14,22]±a, where a is the error value. The processed front image is traversed through the rectangular edge frame, and the black connected area in the binary image is selected to obtain several pending areas. The ratio of the number of white pixels to the number of black pixels in each pending area is calculated, and the pending area that meets the preset ratio threshold and the number of horizontal grayscale jumps is within [30,50] is selected, which is the acquired license plate image.
[0018] As a further solution of the present invention: the license plate collection module also includes ai When the number of license plate images that match the requirements is greater than one, the focal length f of the vehicle camera is obtained and the actual width of the license plate is marked as W. i The theoretical imaging width w in the camera sensor is fW / D, and the license plate images whose imaging width has a difference with the theoretical imaging width greater than a preset threshold are excluded.
[0019] As a further solution of the present invention: the process of the license plate acquisition module identifying the license plate information is:
[0020] Scan the license plate image horizontally, obtain the grayscale value of each column of pixels in turn, mark the white pixels as text pixels, and mark the black pixels as license plate background pixels. When the ratio of the number of text pixels to the total number of pixels in the current column is greater than the preset threshold, the column is the starting pixel column A1 of the text. Continue to scan the license plate image until the column is identified that the ratio of the number of text pixels to the total number of pixels in the current column is less than the preset threshold, which is the ending pixel column A2 of the first character. Calculate the pixel distance d between A2 and A1, where d is the pixel width of a single character. Continue to scan the license plate image, identify characters with a text pixel ratio greater than the preset threshold and a pixel width of w, and segment each single character area to obtain several character areas.
[0021] As a further solution of the present invention: in the license plate collection module, the process of judging the blur degree of the license plate is as follows:
[0022] According to the identified vehicle C i License plate information, generate a standard license plate image P1, according to the actual vehicle C i License plate information, generate a standard license plate image P2, obtain the ratio k1 and k2 of the character area to the total license plate area in the standard license plate image P1 and the standard license plate image P2 respectively, then the license plate blur degree Ac = |k1-k2| / k2.
[0023] Beneficial effects of the present invention:
[0024] The present invention utilizes the high-speed and low-latency characteristics of the 5G network, combined with the on-board camera and the roadside information transmission module, to realize the real-time collection and processing of vehicle information. By calculating the time difference between the two vehicles passing through the information transmission module and the vehicle speed data, the distance between the two vehicles can be accurately calculated. Based on this, the image information of the license plate of the front vehicle collected by the rear vehicle at the current distance is compared with the actual license plate to obtain the license plate recognition ambiguity, and the current visibility is judged according to the license plate recognition ambiguity, thereby obtaining real-time visibility data, and issuing a warning signal accordingly, so that the front and rear vehicles in motion can be reminded in real time according to the visibility; a set of efficient and real-time vehicle-road collaborative warning system is realized, which has significant beneficial effects on improving road safety and optimizing traffic management. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The present invention will be further described below in conjunction with the accompanying drawings.
[0026] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0028] See also Figure 1 As shown, the present invention is a vehicle-road-cloud collaborative system based on a 5G network, comprising:
[0029] An information transmission module is used to establish 5G communication with the vehicle. The information transmission module is set beside the road. When a vehicle passes by the information transmission module, the vehicle's license plate information and current speed are sent to the information transmission module, and the real-time speed is continuously sent until it leaves the signal range;
[0030] The vehicle distance calculation module is used to mark the vehicle passing through the information transmission module at any time as Ci and the vehicle C i The vehicle that passes by is marked as C i+1 , when vehicle C i+1 When passing the information transmission module, according to the time difference between the two vehicles and vehicle C i The speed data within the time difference is used to calculate the distance D between the two vehicles;
[0031] The license plate collection module is used to collect the license plate information of the vehicle C when the vehicle distance D is less than 2 times the preset safety distance. i+1 The on-board camera captures the front image and obtains the vehicle C i The system captures the license plate image and recognizes the license plate information, compares the recognized license plate information with the actual license plate information, determines the blurriness of the license plate, and marks the ratio of the blurriness of the license plate to the distance between the vehicles as the visibility index. When the visibility index is lower than the preset threshold, warnings are issued to both vehicles at the same time.
[0032] Traditional vehicle detection methods, such as geomagnetic induction and infrared sensing, are often limited by installation location and environmental factors and cannot provide continuous and accurate vehicle information. In addition, these methods can usually only collect data at fixed points, making it difficult to achieve large-scale, dynamic vehicle monitoring.
[0033] In recent years, camera-based vehicle monitoring technology has been widely used. Through cameras installed on the roadside or on vehicles, the location, speed and other information of the vehicle can be captured in real time. However, in bad weather conditions, the imaging quality of the camera will be seriously affected, resulting in problems such as difficulty in license plate recognition and inaccurate distance measurement. In addition, the camera's field of view is limited and may not cover all lanes, resulting in monitoring blind spots.
[0034] In order to overcome the above problems, the present invention proposes a vehicle-road-cloud collaborative system based on a 5G network. The system utilizes the high-speed and low-latency characteristics of the 5G network, combined with the on-board camera and the roadside information transmission module, to realize the real-time collection and processing of vehicle information. By calculating the time difference between the two vehicles passing through the information transmission module and the vehicle speed data, the distance between the two vehicles can be accurately calculated. At the same time, when the distance between the two vehicles is less than twice the preset safety distance, since the visibility in some areas may be lower than the predicted visibility, the system will identify and compare the license plate information based on the front image taken by the on-board camera, calculate the real-time license plate blur, and issue a warning signal accordingly.
[0035] In another preferred embodiment of the present invention, in the license plate collection module, when the vehicle C cannot be collected i When the license plate image is detected, a warning is issued directly to remind vehicle C i+1 Slow down.
[0036] In another preferred embodiment of the present invention, the specific process of calculating the vehicle distance in the vehicle distance calculation module is:
[0037] The information transmission module communicates with the vehicle C every unit time t. i Transmit the vehicle speed data, calculate the ratio of the time difference to the unit time difference and round it down to get n, and obtain the vehicle speed sequence v1, v2, ..., v n , then the calculation formula of vehicle distance D is:
[0038] By calculating the time difference and speed data of passing vehicles to calculate the distance between vehicles, the system can efficiently grasp the distance between vehicles. When the distance between vehicles is too small, the system will start the license plate acquisition module, evaluate visibility and issue a warning by processing the front image and recognizing the license plate. This series of actions provides drivers with timely safety warnings, increases reaction time to potential dangerous situations, and reduces accidents caused by obstructed vision.
[0039] In another preferred embodiment of the present invention, the license plate acquisition module further includes processing the front image:
[0040] The front image is converted into a grayscale image through grayscale processing, and the grayscale image is subjected to noise reduction processing. The grayscale image after noise reduction is subjected to edge detection based on an edge detection operator, and the grayscale image after edge detection is converted into a binary image.
[0041] The acquired front image is grayscale processed, denoised and binarized, and then the edge is extracted through the edge detection operator to finally identify the license plate. This image processing method improves the accuracy and speed of license plate recognition and can maintain efficient recognition even in complex environments.
[0042] In another preferred embodiment of the present invention, the process of the license plate acquisition module acquiring the license plate image is:
[0043] A rectangular edge frame is set, and the ratio of the horizontal side length to the vertical side length of the rectangular edge frame is 44±a:[14,22]±a, where a is the error value. The processed front image is traversed through the rectangular edge frame, and the black connected area in the binary image is selected to obtain several pending areas. The ratio of the number of white pixels to the number of black pixels in each pending area is calculated, and the pending area that meets the preset ratio threshold and the number of horizontal grayscale jumps is within [30,50] is selected, which is the acquired license plate image.
[0044] In another preferred embodiment of the present invention, the license plate collection module also includes a i When the number of license plate images that match the requirements is greater than one, the focal length f of the vehicle camera is obtained and the actual width of the license plate is marked as W. i The theoretical imaging width w in the camera sensor is fW / D, and the license plate images whose imaging width has a difference with the theoretical imaging width greater than a preset threshold are excluded.
[0045] The license plate recognition process is further optimized by calibrating and calculating the theoretical imaging width to eliminate erroneous license plate images and improve recognition accuracy.
[0046] In another preferred embodiment of the present invention, the process of the license plate acquisition module identifying the license plate information is:
[0047] Scan the license plate image horizontally, obtain the grayscale value of each column of pixels in turn, mark the white pixels as text pixels, and mark the black pixels as license plate background pixels. When the ratio of the number of text pixels to the total number of pixels in the current column is greater than the preset threshold, the column is the starting pixel column A1 of the text. Continue to scan the license plate image until the column is identified that the ratio of the number of text pixels to the total number of pixels in the current column is less than the preset threshold, which is the ending pixel column A2 of the first character. Calculate the pixel distance d between A2 and A1, where d is the pixel width of a single character. Continue to scan the license plate image, identify characters with a text pixel ratio greater than the preset threshold and a pixel width of w, and segment each single character area to obtain several character areas.
[0048] In another preferred embodiment of the present invention, in the license plate acquisition module, the process of determining the blur degree of the license plate is:
[0049] According to the identified vehicle C i License plate information, generate a standard license plate image P1, according to the actual vehicle C i License plate information, generate a standard license plate image P2, obtain the ratio k1 and k2 of the character area to the total license plate area in the standard license plate image P1 and the standard license plate image P2 respectively, then the license plate blur degree Ac = |k1-k2| / k2.
[0050] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. A vehicle-road-cloud collaborative system based on 5G network, characterized in that: include: An information transmission module is used to establish 5G communication with the vehicle. The information transmission module is set beside the road. When a vehicle passes by the information transmission module, the vehicle's license plate information and current speed are sent to the information transmission module, and the real-time speed is continuously sent until it leaves the signal range; The vehicle distance calculation module is used to mark the vehicle passing through the information transmission module at any time as Ci and the vehicle C i The vehicle that passes by is marked as C i+1 , when vehicle C i+1 When passing through the information transmission module, according to the time difference between the two vehicles and vehicle C i The speed data within the time difference is used to calculate the distance D between the two vehicles; The license plate collection module is used to collect the license plate information of the vehicle C when the vehicle distance D is less than 2 times the preset safety distance. i+1 The on-board camera captures the front image and obtains the vehicle C i The system captures the license plate image and recognizes the license plate information, compares the recognized license plate information with the actual license plate information, determines the blurriness of the license plate, and marks the ratio of the blurriness of the license plate to the distance between the vehicles as the visibility index. When the visibility index is lower than the preset threshold, warnings are issued to both vehicles at the same time.
2. According to the 5G network-based vehicle-road-cloud collaborative system according to claim 1, it is characterized in that: In the license plate collection module, when the vehicle C cannot be collected i When the license plate image is detected, a warning is issued directly to remind vehicle C i+1 Slow down.
3. The vehicle-road-cloud collaborative system based on 5G network according to claim 1, characterized in that: The specific process of calculating the vehicle distance in the vehicle distance calculation module is as follows: The information transmission module communicates with the vehicle C every unit time t. i Transmit the vehicle speed data, calculate the ratio of the time difference to the unit time difference and round it down to get n, and obtain the vehicle speed sequence v1, v2, ..., v n , then the calculation formula of vehicle distance D is:
4. The vehicle-road-cloud collaborative system based on 5G network according to claim 1, characterized in that: The license plate acquisition module also includes processing the front image: The front image is converted into a grayscale image through grayscale processing, and the grayscale image is subjected to noise reduction processing. The grayscale image after noise reduction is subjected to edge detection based on an edge detection operator, and the grayscale image after edge detection is converted into a binary image.
5. The vehicle-road-cloud collaborative system based on 5G network according to claim 4 is characterized in that: The process of the license plate acquisition module acquiring the license plate image is as follows: A rectangular edge frame is set, and the ratio of the horizontal side length to the vertical side length of the rectangular edge frame is 44±a:[14,22]±a, where a is the error value. The processed front image is traversed through the rectangular edge frame, and the black connected area in the binary image is selected to obtain several pending areas. The ratio of the number of white pixels to the number of black pixels in each pending area is calculated, and the pending area that meets the preset ratio threshold and the number of horizontal grayscale jumps is within [30,50] is selected, which is the acquired license plate image.
6. The vehicle-road-cloud collaborative system based on 5G network according to claim 5, characterized in that: The license plate collection module also includes a i When the number of license plate images that match the requirements is greater than one, the focal length f of the vehicle camera is obtained and the actual width of the license plate is marked as W. i The theoretical imaging width w in the camera sensor is fW / D, and the license plate images whose imaging width has a difference with the theoretical imaging width greater than a preset threshold are excluded.
7. The vehicle-road-cloud collaborative system based on 5G network according to claim 6, characterized in that: The process of the license plate acquisition module identifying the license plate information is as follows: Scan the license plate image horizontally, obtain the grayscale value of each column of pixels in turn, mark the white pixels as text pixels, and mark the black pixels as license plate background pixels. When the ratio of the number of text pixels to the total number of pixels in the current column is greater than the preset threshold, the column is the starting pixel column A1 of the text. Continue to scan the license plate image until the column is identified that the ratio of the number of text pixels to the total number of pixels in the current column is less than the preset threshold, which is the ending pixel column A2 of the first character. Calculate the pixel distance d between A2 and A1, where d is the pixel width of a single character. Continue to scan the license plate image, identify characters with a text pixel ratio greater than the preset threshold and a pixel width of w, and segment each single character area to obtain several character areas.
8. The vehicle-road-cloud collaborative system based on 5G network according to claim 1, characterized in that: In the license plate collection module, the process of determining the blurriness of the license plate is as follows: According to the identified vehicle C i License plate information, generate a standard license plate image P1, according to the actual vehicle C i License plate information, generate a standard license plate image P2, obtain the ratio k1 and k2 of the character area to the total license plate area in the standard license plate image P1 and the standard license plate image P2 respectively, then the license plate blur degree Ac = |k1-k2| / k2.
Citation Information
Patent Citations
Intelligent highway mist zone guiding system
CN105913662A
Vehicle Identification And / Or Monitoring System
CN106462791A
