Intelligent traffic monitoring image transmission method and system based on 5G technology

Abstract

This application relates to the field of surveillance image transmission technology, specifically to a method and system for transmitting intelligent traffic surveillance images based on 5G technology. Specifically, it includes: synchronously analyzing traffic conditions and congestion in intelligent traffic surveillance video frames to calculate the content key coefficients of each image block and determine the transmission priority of each image block within the same video frame; constructing the time slot interference characteristics during 5G uplink channel transmission by considering signal interference and channel occupancy overlap caused by cross-time slot interference between different base stations in the traffic surveillance video data packets; and adjusting the upload order of video frame content in the intelligent traffic surveillance image based on the transmission priority and the time slot interference characteristics. This effectively reduces the risk of increased latency jitter and packet loss during 5G transmission of traffic surveillance images, ensuring the 5G transmission quality of intelligent traffic surveillance images.

Description

Technical Field

[0001] This application relates to the field of surveillance image transmission technology, specifically to a method and system for transmitting intelligent traffic surveillance images based on 5G technology. Background Technology

[0002] With the acceleration of urbanization and the surge in traffic flow, traditional traffic monitoring methods face bottlenecks such as complex wiring, limited coverage, and high data transmission latency, making it difficult to meet the needs of modern traffic management. Smart transportation has become an inevitable trend in future traffic development. With its high speed, low latency, and massive connectivity, 5G technology has reconstructed the technical paradigm of smart traffic monitoring image transmission, providing strong technical support for promoting the shift of traffic management from experience-driven to data-driven, and laying a solid foundation for the intelligent management of future traffic.

[0003] In traditional TDD (Time Division Duplexing) communication technology, the demand for network bandwidth is mainly concentrated in the downlink, resulting in uplink resources accounting for only 20-30% of the overall bandwidth. Although the time slot allocation method can allocate more resources to the uplink and improve the uplink peak rate and capacity, it is prone to cross-time slot interference. That is, when adjacent base stations occupy the same frequency band, different base stations may use the same time slot to transmit downlink data and uplink data respectively, which will cause interference between the downlink signals and uplink signals of different base stations. In the 5G transmission of intelligent traffic monitoring images, this will cause a decrease in video quality and an increase in latency jitter and packet loss rate. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a method and system for transmitting intelligent traffic monitoring images based on 5G technology. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of this application provide a method for transmitting intelligent traffic monitoring images based on 5G technology, the method comprising the following steps:

[0006] To acquire intelligent traffic monitoring images, within the transmission segment, collect SINR data, transmission delay data, and channel occupancy rate data for each uplink channel at each time point during image uplink transmission, and construct SINR data sequences, transmission delay data sequences, and channel occupancy rate data sequences.

[0007] The video frames in the image are divided into image blocks; the vehicle congestion degree of each image block in each video frame is calculated based on the vehicle displacement change between each video frame and the corresponding image block in the previous video frame; combined with the vehicle speed in the image block, the content key coefficient of each image block is calculated to determine the transmission priority of each image block in the same video frame.

[0008] Based on the sharp peak characteristics of each peak in the fitted curve of the channel occupancy rate data sequence and the degree of data disorder in the transmission delay data sequence, the occupancy delay of each uplink channel is constructed; based on the difference between adjacent elements in the SINR data sequence, the signal quality interference of each uplink channel is constructed; based on the occupancy delay and the signal quality interference, the slot perturbation of each uplink channel is constructed.

[0009] The upload order of video frames in intelligent traffic monitoring images is adjusted based on the transmission priority and the time slot disturbance.

[0010] In one embodiment, the process of obtaining the vehicle congestion level for each image block in each video frame is as follows:

[0011] Cluster the gray values ​​of all pixels in the grayscale image of each image block to obtain each cluster and the cluster center of each cluster in each image block; use image recognition technology to obtain the number of identical vehicles between any cluster in the a-th image block of the current video frame and any cluster in the a-th image block of the previous video frame.

[0012] If the number of identical vehicles is greater than or equal to a preset quantity threshold, then the two corresponding clusters will be grouped into a cluster group in the same region.

[0013] Calculate the metric distance between the cluster centers of two clusters in the same region, denoted as the first distance. Take the sum of the first distances between the a-th image block of the current video frame and the a-th image block of the previous video frame and all the clusters in the same region as the vehicle congestion degree of the a-th image block of the current video frame.

[0014] In one embodiment, the process of obtaining the content key coefficients of each image block is as follows:

[0015] Calculate the difference between the vehicle speed and the lane speed limit for each vehicle in the current video frame, and denote it as the first difference; the expression for the content key coefficient is:

[0016]

[0017] In the formula, The content key coefficient of the a-th image block in the i-th video frame of a traffic monitoring video; It is the sum of the first differences in the vehicle speeds of all vehicles within the a-th image block of the i-th video frame in the traffic monitoring video. Let be the vehicle congestion degree of the a-th image block in the i-th video frame of the traffic monitoring video; It is an exponential function with the natural constant e as its base; It is a preset minimum positive number.

[0018] In one embodiment, the process of obtaining the transmission priority of each image block in the same video frame is as follows:

[0019] The transmission priority of all image blocks in each video frame is determined in descending order. The higher the content criticality coefficient, the higher the transmission priority of the image block.

[0020] In one embodiment, the process of obtaining the occupancy delay during the transmission of each uplink channel is as follows:

[0021] For the fitted curve of the channel occupancy data sequence of each uplink channel, calculate the curvature at the peak of each peak in the fitted curve; obtain the peak period fluctuation coefficient of each peak based on the time interval between adjacent peaks.

[0022] Calculate the sum of the curvatures at all peaks on the fitted curve, denoted as the first sum; calculate the sum of the peak period fluctuation coefficients of all peaks on the fitted curve, denoted as the second sum; calculate the Shannon entropy of all data in the transmission delay data sequence of each uplink channel; multiply the first sum of each uplink channel by the Shannon entropy, divide by the second sum, and use the calculated result as the occupancy delay during the transmission process of each uplink channel.

[0023] In one embodiment, the process of obtaining the peak periodic fluctuation coefficient is as follows:

[0024] Calculate the time interval between the peak of each peak and the peak of the next peak in the fitted curve, and denote it as the first time interval; denote the absolute value of the difference between the mean of the first time intervals of all peaks and the first time interval of each peak as the peak period fluctuation coefficient of each peak.

[0025] In one embodiment, the process of obtaining the signal quality interference level during the transmission of each uplink channel is as follows:

[0026] Calculate the difference between each data point and its next data point in the SINR data sequence of each uplink channel, and denote it as the first difference. Use the sum of the first differences of all data points in the SINR data sequence as the signal quality interference degree during the transmission process of each uplink channel.

[0027] In one embodiment, the time slot perturbation during the transmission process of each uplink channel is the product of the occupancy delay of each uplink channel and the signal quality interference.

[0028] In one embodiment, adjusting the upload order of video frames in the intelligent traffic monitoring imagery specifically involves:

[0029] When the time slot interference of the uplink channel in which the intelligent traffic monitoring video data packet is transmitted is greater than or equal to the preset time slot interference assessment threshold Q, all uplink channels are prioritized according to the time slot interference. The lower the time slot interference, the higher the priority of the uplink channel to be selected. The data packets of each image block of the traffic monitoring video frame are transmitted to the 5G base station in order of priority through the uplink channels from high to low priority.

[0030] Secondly, embodiments of this application also provide a smart traffic monitoring image transmission system based on 5G technology, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0031] The embodiments of this application have at least the following beneficial effects:

[0032] This application synchronously analyzes traffic conditions and congestion in intelligent traffic monitoring video frames, calculates the key coefficients of each image block, and determines the transmission priority of each image block in the same video frame. This achieves a key division of the intelligent traffic monitoring video data content to be transmitted via 5G uplink, effectively improving the flexibility and accuracy of intelligent traffic monitoring video transmission. Furthermore, by considering signal interference and channel occupancy overlap caused by cross-time slot interference between different base stations during 5G uplink transmission, this application constructs a time slot perturbation mechanism for each uplink channel, further providing a time slot priority allocation method for intelligent traffic monitoring video 5G transmission. Based on the transmission priority and time slot perturbation, the upload order of video frame content in intelligent traffic monitoring video is adjusted, effectively reducing the risk of increased latency jitter and packet loss during 5G transmission of traffic monitoring video, and ensuring the quality of intelligent traffic monitoring video 5G transmission. Attached Figure Description

[0033] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating the steps of a smart traffic monitoring image transmission method based on 5G technology provided in one embodiment of this application;

[0035] Figure 2 This is a schematic diagram illustrating the process of obtaining the occupancy delay. Detailed Implementation

[0036] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the intelligent traffic monitoring image transmission method and system based on 5G technology proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0038] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent traffic monitoring image transmission method and system based on 5G technology provided in this application.

[0039] Please see Figure 1 The diagram illustrates a flowchart of a smart traffic monitoring image transmission method based on 5G technology according to an embodiment of this application. The method includes the following steps:

[0040] Step S1: Acquire intelligent traffic monitoring images. Within the transmission segment, collect SINR data, transmission delay data, and channel occupancy rate data for each uplink channel at each time during image uplink transmission, and construct SINR data sequence, transmission delay data sequence, and channel occupancy rate data sequence.

[0041] By deploying N high-definition cameras supporting 1080P or higher resolution, 25fps frame rate, and 5G at different traffic intersections on the road to be detected, monitoring videos of the road are acquired. A Gaussian filtering algorithm is used to eliminate vehicle motion blur and high-frequency noise in the monitoring videos, improving video quality. OSD information is embedded in the video stream, and digital watermarking technology ensures the integrity of the traffic monitoring image data and guarantees the security of intelligent traffic monitoring videos. The embedded OSD information in this application includes time, lane number, and lane speed limit. Preferably, in this embodiment, the value of N is set to 3. As other embodiments of this application, implementers can set the value of N according to actual conditions.

[0042] The acquired surveillance video data is compressed into H.265 / HEVC format to reduce the data volume, and the surveillance video frame size is uniformly set to... It should be noted that implementers can set the video frame size themselves according to the actual situation, and this application does not impose specific restrictions.

[0043] To improve the transmission efficiency of intelligent traffic monitoring images, the aforementioned image denoising and monitoring video compression processing can employ edge computing. A transmission segment is defined as every 30 minutes. When transmitting the monitoring video for each segment, the gateway RF module acquires SINR (Signal to Interference plus Noise Ratio) data for each uplink channel at a sampling frequency of 30Hz, and the transmission delay data for each uplink channel at each time point is acquired using Ping (Packet Internet Groper) based probe packets at a sampling frequency of 30Hz. The time series of SINR data for each uplink channel is recorded as the SINR data sequence for each uplink channel, and the time series of transmission delay data for each uplink channel is recorded as the transmission delay data sequence for each uplink channel. The gateway RF module and Ping-based probe packets are well-known technologies, and their specific processes are not detailed here. It should be noted that the implementer can set the acquisition frequency of SINR data and transmission delay data according to actual conditions; this application does not impose specific restrictions.

[0044] The signal power of each uplink channel during video transmission in each transmission segment was measured using a spectrum analyzer. A signal threshold of -60 dBm was set, and signals with power greater than the threshold in each uplink channel were considered effectively occupied. For each uplink channel, the percentage of the duration of the effectively occupied signal before the current moment to the total time before the current moment was taken as the channel occupancy rate at the current moment. The sequence of channel occupancy rates for each uplink channel at all moments was recorded as the channel occupancy rate data sequence for each uplink channel. The measurement of channel signal power using a spectrum analyzer is a well-known technique, and the specific process will not be detailed here.

[0045] Step S2: Divide each video frame in the image into image blocks; calculate the vehicle congestion degree of each image block in each video frame based on the vehicle displacement change between each video frame and the corresponding image block in the previous video frame; combine the vehicle speed in the image block to calculate the content key coefficient of each image block and determine the transmission priority of each image block in the same video frame.

[0046] During the 5G uplink transmission of intelligent traffic monitoring images, when traffic congestion or traffic accidents occur at traffic intersections, the higher the priority of the 5G transmission task of the corresponding video monitoring equipment at the traffic intersection, the more priority should be given to ensuring the 5G uplink transmission of key content of traffic monitoring video. This will effectively improve the quality of intelligent traffic monitoring video, assist relevant personnel or departments in obtaining traffic conditions in a timely manner, and thus respond quickly.

[0047] Specifically, the more severe the speeding of vehicles in a video frame, the higher the possibility of traffic congestion and traffic accidents, and the higher the priority of video frame data should be, prioritizing 5G uplink transmission; furthermore, when the positional deviation of the vehicle gathering area between adjacent video frames and corresponding monitoring images is small, it indicates that the vehicle gathering situation at the traffic intersection has not been significantly improved, and the traffic congestion is aggravated.

[0048] In traffic monitoring video footage awaiting 5G uplink transmission, the H.265 (HEVC) image encoding method is used to divide each video frame into 32... 32 image blocks. To analyze the criticality of the content of each image block in each video frame of the traffic monitoring images to be transmitted via 5G uplink, the content criticality coefficients of each video frame are constructed, specifically as follows:

[0049] First, the traffic monitoring video images corresponding to each transmission segment are converted from the video screen coordinate system to the road surface coordinate system. The parameters are calibrated using the length and spacing of the lane lines, and the edge pixels of static objects are extracted. Moving targets are identified using a Gaussian mixture model and the Canny edge detection algorithm, and the position of the moving targets in adjacent frames is determined. The speed of each vehicle in each video frame image is obtained through displacement deviation and time information. The process of obtaining the speed of each vehicle in each video frame image is a known existing technology, and the specific process will not be described in detail.

[0050] Furthermore, to obtain the positional deviation between vehicle clustering areas in adjacent video frames, each image block in each video frame image is grayscaled to obtain a grayscale image of each image block. The grayscale values ​​of all pixels in the grayscale image are used as input to the K-mediods clustering algorithm to obtain each cluster in the image block and the cluster center of the cluster. The license plate numbers of each vehicle in each cluster in each image block are obtained by using YOLO (You Only Look Once) image recognition technology. For any cluster in the a-th image block of the current video frame, the license plate numbers of the vehicles in the two clusters are compared with any cluster in the a-th image block of the previous video frame to determine the number of identical vehicles between the two clusters.

[0051] If the number of identical vehicles between two clusters is greater than or equal to a preset threshold, then the vehicle clustering areas in these two clusters are determined to belong to the same vehicle clustering area, and these two clusters are grouped into a co-regional cluster group. Preferably, in this embodiment, the threshold is the average of the total number of vehicles in the two clusters. As other embodiments of this application, implementers can set the threshold according to actual conditions. The K-mediods clustering algorithm and YOLO-based image recognition technology are well-known technologies, and the specific acquisition process will not be described in detail.

[0052] Furthermore, the Euclidean distance between the cluster centers of two clusters in the same region is calculated and denoted as the first distance. The sum of the first distances between the a-th image block of the current video frame and the a-th image block of the previous video frame in all the same region clusters is taken as the vehicle congestion degree of the a-th image block of the current video frame.

[0053] Calculate the difference between the vehicle speed and the lane speed limit in the current video frame, and record it as the first difference.

[0054] Finally, based on the above analysis, the content key coefficient of each image block in each video frame of the traffic monitoring video is calculated, and the expression is as follows:

[0055]

[0056] In the formula, The content key coefficient of the a-th image block in the i-th video frame of a traffic monitoring video; It is the sum of the first differences in the vehicle speeds of all vehicles within the a-th image block of the i-th video frame in the traffic monitoring video. Let be the vehicle congestion degree of the a-th image block in the i-th video frame of the traffic monitoring video; It is an exponential function with the natural constant e as its base; This is a preset, extremely small positive number. Among them, The purpose is to prevent the denominator from being 0. Preferably, in the embodiments of this application, The value is set to 0.1. As another embodiment of this application, the implementer may set the value according to the actual situation. The value of .

[0057] The content criticality coefficient reflects the criticality of content in each image block of the traffic monitoring video frame to be transmitted via 5G uplink; vehicle congestion reflects the displacement and changes of vehicle aggregation areas within the image block; the more obvious the vehicle congestion or speeding in an image block, the more critical the image block should be as key content for priority 5G uplink transmission. (Calculation indicators...) The larger the value, the more subtle the displacement change in the same vehicle cluster area between adjacent video frames, and the higher the calculated index. It gets smaller.

[0058] The content criticality coefficient of each image block is calculated using the above method. The transmission priority of all image blocks in each video frame is determined by ranking them from largest to smallest; the larger the content criticality coefficient, the higher the transmission priority. Compressed data packets of each image block in each traffic monitoring video frame within the transmission segment are obtained, and 5G uplink transmission requests are simultaneously sent to the 5G base station.

[0059] Step S3: Based on the sharp peak characteristics of each peak in the fitted curve of the channel occupancy rate data sequence and the degree of data disorder in the transmission delay data sequence, construct the occupancy delay of each uplink channel during transmission; construct the signal quality interference degree of each uplink channel during transmission based on the difference between adjacent elements in the SINR data sequence; and construct the time slot disturbance of each uplink channel during transmission based on the occupancy delay and the signal quality interference degree.

[0060] During 5G transmission of intelligent traffic monitoring video using TDD communication technology, base stations used in different traffic monitoring areas may occupy the same frequency band. This causes different base stations to use the same time slot to transmit downlink and uplink data separately, resulting in cross-time slot interference. This not only affects the transmission quality of intelligent traffic monitoring video but also exacerbates the data packet loss rate.

[0061] During the transmission of intelligent traffic monitoring video, the more severe the cross-slot interference experienced by the monitoring video in the 5G uplink channel, the more significant the decrease in SINR of the monitoring video data packets due to the disruption of signal orthogonality caused by slot interference. At the same time, the uplink and downlink signals are transmitted through the same slot, causing the channel occupancy rate to overlap and exhibit a periodic spike phenomenon. The uplink signal cannot be transmitted to the 5G base station in a timely manner, and the more obvious the transmission delay fluctuation of traffic monitoring video data packets becomes.

[0062] Taking the j-th 5G uplink channel used for traffic monitoring video data transmission in the current transmission segment as an example, in order to analyze the cross-slot interference situation encountered during the 5G uplink transmission of intelligent traffic monitoring images, the slot interference during the transmission process of each 5G uplink channel is constructed, specifically as follows:

[0063] First, the channel occupancy rate data sequence of each 5G uplink channel is used as input to the least squares fitting algorithm, and the output is a fitted curve of the channel occupancy rate for each channel. Then, the AMPD (Automatic Multiscale-based Peak Detection) algorithm is used to obtain all peaks in the fitted curve of the channel occupancy rate, and the curvature of the fitted curve at the peak of each peak is calculated. The least squares method, the AMPD multiscale peak detection algorithm, and the curvature calculation are all well-known techniques, and the specific process will not be elaborated further.

[0064] Furthermore, the time interval between the peak value of each peak in the channel occupancy fitting curve and the peak value of the next peak is calculated and denoted as the first time interval. The time interval between the peak value of the last peak and the peak value of the previous peak is taken as the first time interval of the last peak. The absolute value of the difference between the average first time interval of all peaks in the fitting curve and the first time interval of each peak is denoted as the peak period fluctuation coefficient of each peak. The larger the peak period fluctuation coefficient, the greater the difference between the time interval of the peak and the next peak compared with the average time interval, and the less obvious the periodic spike of the channel occupancy rate.

[0065] Furthermore, the sum of the curvatures at all peaks on the channel occupancy fitting curve for each 5G uplink channel is calculated, denoted as the first sum; the sum of the peak periodic fluctuation coefficients of all peaks on the channel occupancy fitting curve for each 5G uplink channel is calculated, denoted as the second sum; the Shannon entropy of all data in the transmission delay data sequence for each 5G uplink channel is calculated; the product of the first sum and the Shannon entropy is divided by the second sum, and the calculated result is used as the occupancy delay during the transmission process of each 5G uplink channel. A larger curvature and a smaller peak periodic fluctuation coefficient indicate a more pronounced periodic spike in channel occupancy, resulting in greater occupancy delay; a larger Shannon entropy indicates more severe fluctuations in the transmission delay data sequence, indicating more severe interference, and also greater occupancy delay.

[0066] Furthermore, the difference between each data point in the SINR data sequence of each 5G uplink channel and its next data point is calculated and denoted as the first difference. The sum of the first differences of all data points in the SINR data sequence is used as the signal quality interference degree during the transmission process of the 5G uplink channel.

[0067] Furthermore, the time slot perturbation during the transmission process of each 5G uplink channel is calculated, and the expression is as follows:

[0068]

[0069] In the formula, The time slot interference of traffic monitoring video data packets during the j-th 5G uplink channel transmission process; The signal quality interference of traffic monitoring video data packets during the j-th 5G uplink channel transmission process; This refers to the occupancy delay of traffic monitoring video data packets during the transmission of the j-th 5G uplink channel.

[0070] Time slot interference reflects the cross-time slot interference experienced by traffic monitoring video data packets during 5G uplink transmission; signal quality interference reflects the SINR decreasing trend of monitoring video data packets during 5G uplink transmission. The more significant the SINR decreasing trend, the more severe the cross-time slot interference.

[0071] Occupancy delay characterizes the periodic peaks in occupancy of the 5G uplink channel and the transmission delay fluctuations of traffic monitoring video data packets. The greater the occupancy delay, the more severe the cross-slot interference experienced by the traffic monitoring video data packets in the 5G uplink channel.

[0072] Step S4: Adjust the upload order of video frame content in the intelligent traffic monitoring image based on the transmission priority and the time slot interference.

[0073] A time slot interference assessment threshold Q is set. Preferably, in this embodiment, the value of Q is set to 0.6. In other embodiments of this application, the implementer can set the value of Q according to actual conditions. When the time slot interference of the 5G uplink channel where the intelligent traffic monitoring video data packet transmission is located is less than the time slot interference assessment threshold Q, it is determined that during the transmission of the intelligent traffic monitoring video data packet, the video quality degradation, latency jitter, and packet loss rate caused by cross-time slot interference between uplink and downlink signals from different base stations are minor. The 5G transmission quality of the higher-priority traffic monitoring video data packets is better and no adjustment is needed.

[0074] Conversely, when the time slot interference of the 5G uplink channel where the intelligent traffic monitoring video data packets are transmitted is greater than or equal to the time slot interference assessment threshold Q, it is determined that the cross-time slot interference between different base stations during the transmission of intelligent traffic monitoring video data packets has caused a decrease in the quality of the monitoring video transmission, increased latency jitter, and increased packet loss rate, making it impossible to transmit traffic monitoring video data with high quality via 5G. Therefore, it is necessary to adjust the data packet transmission order in a timely manner to ensure the transmission quality of key content in the traffic monitoring video. The specific adjustment methods are as follows:

[0075] In step S2, the data packets corresponding to each image block in the intelligent traffic monitoring video frame have been prioritized for transmission. Further, all 5G uplink channels are prioritized according to the time slot interference. The lower the time slot interference, the higher the priority of the 5G uplink channel to be selected. The traffic monitoring video frame data packets with the above priority are transmitted to the 5G base station in order of priority through the 5G uplink channels from high to low priority. This helps relevant personnel or departments to understand traffic conditions in a timely manner, thereby enabling rapid response and decision-making, and laying the foundation for large-scale intelligent traffic monitoring.

[0076] A schematic diagram of the process for obtaining the occupancy delay is shown below. Figure 2As shown.

[0077] Based on the same inventive concept as the above methods, this application also provides a smart traffic monitoring image transmission system based on 5G technology, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described smart traffic monitoring image transmission methods based on 5G technology.

[0078] In summary, this application provides a method for transmitting intelligent traffic monitoring images based on 5G technology. By synchronously analyzing traffic conditions and congestion in intelligent traffic monitoring video frames, the method calculates the content key coefficients of each image block and determines the transmission priority of each image block in the same video frame. This achieves the key division of the video data content of intelligent traffic monitoring images to be transmitted via 5G uplink, effectively improving the flexibility and accuracy of intelligent traffic monitoring video transmission. Furthermore, by considering the signal interference and channel occupancy overlap caused by cross-time slot interference between different base stations during 5G uplink channel transmission, the method constructs the time slot perturbation characteristics of each uplink channel transmission process. This further provides a time slot priority allocation method during the 5G transmission of intelligent traffic monitoring images. Based on the transmission priority and the time slot perturbation characteristics, the method adjusts the upload order of video frame content in intelligent traffic monitoring images, effectively reducing the risk of increased latency jitter and packet loss during 5G transmission of traffic monitoring images, and ensuring the 5G transmission quality of intelligent traffic monitoring images.

[0079] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0080] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0081] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for transmitting intelligent transportation monitoring image based on 5G technology, characterized in that, The method includes the following steps: To acquire intelligent traffic monitoring images, within the transmission segment, collect SINR data, transmission delay data, and channel occupancy rate data for each uplink channel at each time point during image uplink transmission, and construct SINR data sequences, transmission delay data sequences, and channel occupancy rate data sequences. The video frames in the image are divided into image blocks. Based on the vehicle displacement changes between each video frame and the corresponding image block in the previous video frame, the vehicle congestion degree of each image block in each video frame is calculated. Combined with the vehicle speed in the image block, the content key coefficient of each image block is calculated to determine the transmission priority of each image block in the same video frame. Among them, the transmission priority of all image blocks in each video frame is determined in descending order. The larger the content key coefficient, the higher the transmission priority of the image block. Based on the sharp peak characteristics of each peak in the fitted curve of the channel occupancy rate data sequence and the degree of data disorder in the transmission delay data sequence, the occupancy delay of each uplink channel is constructed; based on the difference between adjacent elements in the SINR data sequence, the signal quality interference of each uplink channel is constructed; based on the occupancy delay and the signal quality interference, the slot perturbation of each uplink channel is constructed. The upload order of video frame content in intelligent traffic monitoring images is adjusted based on the transmission priority and the time slot interference. The process of obtaining the vehicle congestion level for each image block in each video frame is as follows: Cluster the gray values ​​of all pixels in the grayscale image of each image block to obtain each cluster and the cluster center of each cluster in each image block; use image recognition technology to obtain the number of identical vehicles between any cluster in the a-th image block of the current video frame and any cluster in the a-th image block of the previous video frame. If the number of identical vehicles is greater than or equal to a preset quantity threshold, then the two corresponding clusters will be grouped into a cluster group in the same region. Calculate the metric distance between the cluster centers of two clusters in the same region, and denote it as the first distance. Take the sum of the first distances between the a-th image block of the current video frame and the a-th image block of the previous video frame of all the same region clusters as the vehicle congestion degree of the a-th image block of the current video frame. The process for obtaining the content key coefficients of each image block is as follows: Calculate the difference between the vehicle speed and the lane speed limit for each vehicle in the current video frame, and denote it as the first difference; the expression for the content key coefficient is: In the formula, The content key coefficient of the a-th image block in the i-th video frame of a traffic monitoring video; It is the sum of the first differences in the vehicle speeds of all vehicles within the a-th image block of the i-th video frame in the traffic monitoring video. Let be the vehicle congestion degree of the a-th image block in the i-th video frame of the traffic monitoring video; It is an exponential function with the natural constant e as its base; It is a preset minimum positive number; The process for obtaining the occupancy delay during the transmission of each uplink channel is as follows: For the fitted curve of the channel occupancy data sequence of each uplink channel, calculate the curvature at the peak of each peak in the fitted curve; obtain the peak period fluctuation coefficient of each peak based on the time interval between adjacent peaks. Calculate the sum of the curvatures at all peaks on the fitted curve, denoted as the first sum; calculate the sum of the peak period fluctuation coefficients of all peaks on the fitted curve, denoted as the second sum; calculate the Shannon entropy of all data in the transmission delay data sequence of each uplink channel; multiply the first sum of each uplink channel by the Shannon entropy, divide by the second sum, and use the calculated result as the occupancy delay during the transmission process of each uplink channel; The process of obtaining the signal quality interference level during the transmission of each uplink channel is as follows: Calculate the difference between each data point and its next data point in the SINR data sequence of each uplink channel, and denote it as the first difference. Use the sum of the first differences of all data in the SINR data sequence as the signal quality interference degree during the transmission process of each uplink channel. The time slot interference during the transmission process of each uplink channel is the product of the occupancy delay of each uplink channel and the signal quality interference level. The adjustment of the upload order of video frames in the intelligent traffic monitoring images is specifically as follows: When the time slot interference of the uplink channel where the intelligent traffic monitoring video data packet is transmitted is less than the preset time slot interference assessment threshold Q, no adjustment is required; when the time slot interference of the uplink channel where the intelligent traffic monitoring video data packet is transmitted is greater than or equal to the preset time slot interference assessment threshold Q, all uplink channels are prioritized according to the time slot interference, and the lower the time slot interference, the higher the priority of the uplink channel to be selected; the data packets of each image block of the traffic monitoring video frame are transmitted to the 5G base station in order of priority through the uplink channels from high to low priority.

2. The intelligent traffic monitoring image transmission method based on 5G technology as described in claim 1, characterized in that, The process for obtaining the peak periodic fluctuation coefficient is as follows: Calculate the time interval between the peak of each peak and the peak of the next peak in the fitted curve, and denote it as the first time interval; denote the absolute value of the difference between the mean of the first time intervals of all peaks and the first time interval of each peak as the peak period fluctuation coefficient of each peak.

3. A smart traffic monitoring image transmission system based on 5G technology, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-2.

Images