An intelligent optimization system for video surveillance traffic

Abstract

The present invention relates to the technical field of traffic management, and specifically provides an intelligent optimization system for video surveillance traffic. The system includes a timing segment evaluation module, a path priority adjustment module, a traffic scheduling optimization module, and a buffer strategy adaptation module. In the present invention, by analyzing the video stream in real time and adjusting the frame rate and compression rate, the transmission efficiency and quality of video surveillance data are improved. By evaluating the importance of each timing segment in the video stream and adjusting the frame rate accordingly, it is ensured that important events receive more resources and unnecessary data transmission is reduced, effectively reducing network congestion. By monitoring the network transmission path in real time and adjusting the data transmission ratio, the video stream is made to pass through a network path with higher quality more preferentially, enhancing the stability and speed of video transmission. By dynamically adjusting the priority and bandwidth allocation, high-priority video streams are protected to ensure that the video quality in key surveillance areas is not affected by network fluctuations.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular, to an intelligent optimization system for video surveillance traffic. Background Art

[0002] The technical field of traffic management involves the scheduling, optimization, and control of data transmission in various network systems. The main objective of this field is to improve the utilization efficiency of network resources, ensure the stability and speed of data transmission, reduce congestion, and improve service quality. Traffic management technologies include strategies such as bandwidth allocation, priority setting, traffic shaping, and traffic scheduling. The technology can be applied to various network types, including wired and wireless networks, enterprise networks and the Internet, as well as wide area networks across data centers. By monitoring and analyzing data packets, traffic management technologies can adjust network behavior in real time, optimize data flow and processing, especially in data-intensive application scenarios such as video transmission and cloud computing platforms.

[0003] Among them, the intelligent optimization system for video surveillance traffic is a system specifically designed to optimize video surveillance data streams. The system analyzes and manages video data streams in real time to reduce network congestion and improve video transmission quality. The purpose of the system is to ensure the continuity and efficiency of video surveillance, especially in environments with limited bandwidth or unstable network conditions. By dynamically adjusting video encoding parameters, selecting the best transmission route, and adjusting the priority of data packets according to the current network conditions, the performance of the entire video surveillance network is optimized. The monitoring effect is improved, the pressure on network facilities is reduced, and a smoother and clearer video surveillance experience is provided for users.

[0004] Traditional management systems face problems of uneven bandwidth resource allocation and network congestion. Especially in data-intensive applications such as video surveillance, traditional systems cannot effectively adapt to dynamically changing network conditions. For example, in a monitoring system with multiple video sources, when multiple video streams are transmitted simultaneously, due to the lack of real-time path optimization and frame rate adjustment mechanisms, the transmission of key video data will be delayed or interrupted, affecting the monitoring effect and response speed. In the process of video data compression and transmission, traditional systems adopt fixed encoding and transmission strategies, ignoring the impact of real-time network conditions, resulting in serious impacts on the continuity and efficiency of video surveillance in an environment with large fluctuations in network quality. This limits the applicability and efficiency of video surveillance systems in complex network environments, increasing the operation and maintenance difficulty and cost of the systems. Summary of the Invention

[0005] The objective of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent optimization system for video surveillance traffic.

[0006] To achieve the above objective, the present invention adopts the following technical solution: An intelligent optimization system for video surveillance traffic, the system includes:

[0007] Based on the monitored video stream, at preset time intervals, the video stream is segmented into time periods, the frame change data within each time period is analyzed, and by statistically calculating the pixel difference rate between frames, the importance of each time series segment is evaluated. According to the degree of importance, the frame rate of each time series segment is adjusted, and the video compression code rate of each time series segment is adjusted to obtain the processing result of the video stream segment;

[0008] Based on the transmission environment of the monitored video stream, the path priority adjustment module monitors the network transmission path in real time, collects the load data, latency, and packet loss data of the path, evaluates the transmission priority of each path, and adjusts the data transmission ratio of each path according to the transmission priority and bandwidth size of the path to obtain the transmission ratio allocation result;

[0009] Based on the processing result of the video stream segment and the transmission ratio allocation result, the traffic scheduling optimization module extracts the priority of the corresponding location according to the monitoring location of each monitored video stream, constructs an upload priority queue for the video stream, implements the video stream transmission, and monitors the network traffic in real time. When network congestion is detected, the bandwidth allocation of low-priority video streams is dynamically adjusted to obtain the traffic dynamic adjustment information;

[0010] Based on the traffic dynamic adjustment information, the buffer strategy adaptation module monitors the size of each monitored video stream in real time, analyzes the video traffic change trend within the time window, and dynamically adjusts the buffer pool capacity of the video stream according to the video traffic change trend to obtain the buffer capacity adjustment information.

[0011] The improvement of the present invention is that the step of evaluating the importance of each time series segment is as follows:

[0012] Based on the monitored video stream, at preset time intervals, the video stream is segmented into time periods to obtain a list of video time periods;

[0013] Based on the list of video time periods, the frame data in each video time period is analyzed, the number of different pixels between two frames is calculated, and the total amount of different pixels within the entire time period is statistically calculated to obtain the different pixel statistical data;

[0014] Based on the different pixel statistical data, through the formula:

[0015] ;

[0016] Calculate the importance score of each time series segment to obtain the time series segment importance evaluation result;

[0017] Among them, represents the total amount of different pixels within the time period, is the total amount of pixels within the time period, is the influence coefficient, is the importance score of the time sequence segment.

[0018] The improvement of the present invention is that the step of obtaining the processing result of the video stream segment is as follows:

[0019] Based on the importance evaluation result of the time sequence segment, collect the acquisition data of each monitored video stream, including the video frame rate and the benchmark compression bit rate set by the user, to obtain the segment processing correlation data;

[0020] Based on the segment processing correlation data, through the formula:

[0021] ;

[0022] and

[0023] ;

[0024] Calculate the adjusted frame rate and video compression bit rate of each time sequence segment;

[0025] Wherein, is the initial frame rate, is the benchmark compression bit rate, is the importance score of the time sequence segment, is the scaling coefficient of frame rate adjustment, is the scaling coefficient of compression bit rate adjustment, is the allowed minimum frame rate, is the allowed minimum compression bit rate, is the adjusted frame rate, is the adjusted video compression bit rate;

[0026] Based on the adjusted frame rate and video compression bit rate of each time sequence segment, perform frame rate adjustment and video compression processing on each time sequence segment to obtain the processing result of the video stream segment.

[0027] The improvement of the present invention is that the step of evaluating the transmission priority of each path is as follows:

[0028] Based on the transmission environment of the monitored video stream, perform real-time monitoring on each network transmission path, collect the load data, delay and packet loss data of the path to obtain the network status information;

[0029] Based on the network status information, through the formula:

[0030] ;

[0031] Calculate the transmission priority score of each path;

[0032] Wherein, is the transmission priority score of the path, Indicates the current actual load of the path, Indicates the maximum load capacity of the path, Indicates the actual latency of the path, Is the packet loss rate of the path, , And Are weight coefficients;

[0033] Based on the transmission priority scores of each path, each transmission path is prioritized to obtain a path priority list.

[0034] The improvement of the present invention is that the step of obtaining the transmission ratio allocation result is:

[0035] Based on the path priority list, the priority scores of each path are extracted, and the maximum bandwidth data of each path is collected to obtain transmission ratio correlation information;

[0036] Based on the transmission ratio correlation information, through the formula:

[0037]

[0038] Calculate the adjusted data transmission ratio of each path, adjust the data stream of each path, and obtain the transmission ratio allocation result;

[0039] Among them, Is the transmission priority score of path , Is the transmission priority score of path , Is the maximum bandwidth of path , Is the maximum bandwidth of path , Is the adjusted data transmission ratio of path , Is the total number of paths.

[0040] The improvement of the present invention is that the step of obtaining the traffic dynamic adjustment information is:

[0041] Based on the video stream segment processing result and the transmission ratio allocation result, the monitoring position data of each video stream is extracted, the priority of the corresponding position is extracted, and an upload priority queue of the video stream is constructed;

[0042] Based on the upload priority queue of the video stream and the transmission ratio allocation result, the transmission order of the video stream is adjusted according to the priority list, the video stream is transmitted, and the network traffic is monitored in real time to detect the current network state and traffic distribution, and obtain the network state information during the transmission process;

[0043] Based on the network status information of the transmission process, when network congestion is detected, through the formula:

[0044] ;

[0045] Calculate the bandwidth limit ratio of the low-priority video stream, and limit the transmission of each video stream in ascending order according to the upload priority of the video stream to obtain traffic dynamic adjustment information;

[0046] Among them, represents the original bandwidth allocation of the video stream, is the total bandwidth used by the current network, is the maximum bearing bandwidth of the network, is the adjusted bandwidth allocation amount.

[0047] The improvement of the present invention is that the step of analyzing the video traffic change trend within the analysis time window is:

[0048] Based on the traffic dynamic adjustment information, monitor the data size of each video stream in real time, record the video stream size at each detection time point, and obtain the video stream real-time monitoring data;

[0049] Based on the video stream real-time monitoring data, according to the preset time window size, count the size change of each video stream within the time window to obtain the video traffic change data within the time window;

[0050] Based on the video traffic change data within the time window, through the formula:

[0051] ;

[0052] Calculate the increase and decrease rate of the video traffic, evaluate the video traffic change trend, and obtain the trend evaluation result;

[0053] Among them, is the increase and decrease rate of the video traffic, represents the change amount of the video traffic within the time window, is the length of the time window.

[0054] The improvement of the present invention is that the step of obtaining the buffer capacity adjustment information is:

[0055] Based on the trend evaluation result, extract the increase and decrease rate of the video traffic and the current video traffic size to obtain buffer correlation data;

[0056] Based on the buffer correlation data, through the formula:

[0057] ;

[0058] Calculate the adjusted buffer pool capacity;

[0059] Among them, is the increase and decrease rate of video traffic, is the traffic size of the current video stream, is the reference capacity of the buffer pool, is the adjustment coefficient, is the adjusted buffer pool capacity;

[0060] Based on the adjusted buffer pool capacity, update the buffer strategy for monitoring video stream transmission to obtain buffer capacity adjustment information.

[0061] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0062] In the present invention, by analyzing the video stream in real time and adjusting the frame rate and compression rate, the transmission efficiency and quality of video surveillance data are improved. By evaluating the importance of each time series segment in the video stream and adjusting the frame rate accordingly, it is ensured that important events receive more resources and unnecessary data transmission is reduced, effectively reducing network congestion. By real-time monitoring the network transmission path and adjusting the data transmission ratio, the video stream preferentially passes through the network path with higher quality, enhancing the stability and speed of video transmission. By dynamically adjusting the priority and bandwidth allocation, protecting the video stream with high priority to ensure that the video quality of the key monitoring area is not affected by network fluctuations, reducing the pressure on network facilities and providing users with a smoother and clearer video surveillance experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is the system flow chart of the present invention;

[0064] Figure 2 is the flow chart of the present invention for evaluating the importance of each time series segment;

[0065] Figure 3 is the flow chart of the present invention for obtaining the processing result of the video stream segment;

[0066] Figure 4 is the flow chart of the present invention for evaluating the transmission priority of each path;

[0067] Figure 5 is the flow chart of the present invention for obtaining the transmission ratio allocation result;

[0068] Figure 6 is the flow chart of the present invention for obtaining the traffic dynamic adjustment information;

[0069] Figure 7 is the flow chart of the present invention for analyzing the video traffic change trend within the time window;

[0070] Figure 8Flowchart for obtaining buffer capacity adjustment information in the present invention. Detailed implementation manners

[0071] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0072] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0073] Please refer to Figure 1 , the present invention provides a technical solution: a video surveillance traffic intelligent optimization system, the system includes:

[0074] The timing segment evaluation module divides the video stream into time segments at a preset time interval based on the surveillance video stream, analyzes the frame change data in each time segment, evaluates the importance of each timing segment by statistically calculating the inter-frame pixel difference rate, adjusts the frame rate of each timing segment according to the importance level, and adjusts the video compression bit rate of each timing segment to obtain the processing result of the video stream segment;

[0075] The path priority adjustment module monitors the network transmission path in real time based on the transmission environment of the surveillance video stream, collects the load data, delay and packet loss data of the path, evaluates the transmission priority of each path, and adjusts the data transmission ratio of each path according to the transmission priority and bandwidth size of the path to obtain the transmission ratio allocation result;

[0076] The traffic scheduling and optimization module extracts the priority of the corresponding location based on the processing result of the video stream segment and the transmission ratio allocation result according to the monitoring location of each surveillance video stream, constructs an upload priority queue for the video stream, implements the video stream transmission, and monitors the network traffic in real time. When network congestion is detected, the bandwidth allocation of low-priority video streams is dynamically adjusted to obtain traffic dynamic adjustment information;

[0077] The buffer policy adaptation module monitors the size of each surveillance video stream in real time based on the traffic dynamic adjustment information, analyzes the video traffic change trend within the time window, and dynamically adjusts the buffer pool capacity of the video stream according to the video traffic change trend to obtain the buffer capacity adjustment information.

[0078] The processing results of video stream segments include the compressed frame sequence, the compressed frame rate value, and the reserved key frames. The transmission ratio allocation results include path load data and packet allocation information. The traffic dynamic adjustment information includes queue allocation rules, bandwidth allocation policies, and peak traffic response mechanisms. The buffer capacity adjustment information includes traffic demand information, buffer pool adjustment parameters, and video stream stability indicators.

[0079] Please refer to Figure 2 , the steps to evaluate the importance of each time series segment are as follows:

[0080] Based on the monitored video stream, segment the video stream at a preset time interval to obtain a list of video time periods.

[0081] According to the set preset time interval, for example, setting to cut every ten minutes in a one-hour video surveillance stream, six independent video segments can be generated. The determination of such time periods needs to be set according to the changes in video content and time sensitivity. For example, in high-traffic periods, a shorter time interval may be required to capture more details, while in static scenes, the time interval can be appropriately extended to reduce the amount of data processed. This process is automatically completed through video editing software or custom scripts to ensure that each segment is uniform and continuous without omission. The generation of the video time period list is the basis for subsequent video analysis and provides the necessary data support for analyzing each time period.

[0082] Based on the list of video time periods, analyze the frame data in each video time period, calculate the number of different pixels between two frames, and count the total number of different pixels within the entire time period to obtain different pixel statistical data.

[0083] Analyze the frame data in each video time period, calculate the number of different pixels between two frames, usually achieved through pixel-level comparison. The difference between frames within each time period is calculated by comparing the color and brightness differences of each pixel point through an algorithm to obtain the difference pixel value between every two frames. The data is accumulated to form the total number of different pixels within the time period. The statistics of different pixels not only help identify movements or changes in the video but also can be used for subsequent event detection and analysis, such as motion detection and scene change. The total number of different pixels is an intuitive indicator for evaluating the change of video content and provides a quantitative method to judge the dynamic situation in the video.

[0084] Based on the different pixel statistical data, through the formula:

[0085] ;

[0086] Calculate the importance score of each time series segment to obtain the evaluation result of the importance of the time series segment.

[0087] Among them, represents the total difference pixel amount within a time period, is the total pixel amount within the time period, is the influence coefficient, is the importance score of the timing segment;

[0088] Formula:

[0089] ;

[0090] The advantage of the formula is that by adjusting the coefficient, the sensitivity of the importance score can be flexibly controlled to meet the requirements for the sensitivity of dynamic changes in different scenarios.

[0091] Detailed explanation of the formula and the derivation process of formula calculation:

[0092] In practical applications, represents the total difference pixel amount within a certain time period. For example, it is the total pixel change recorded by the monitoring system in the past minute. represents the total pixel amount within this time period, which is assumed to be the video resolution multiplied by the number of frames. is the influence coefficient, and its value is adjusted according to the scene complexity or the accuracy requirement of the analysis. For example, in an environment with a more complex or rapidly changing scene, a larger value may be required to amplify the influence of the difference, so as to ensure that important events are not overlooked. Based on specific monitoring data, let , , , then the calculation process is:

[0093] ;

[0094] This result indicates a high degree of dynamic change, and its association with the step result is to provide a quantitative score to analyze which timing segments are key events, so as to optimize resource allocation and further processing.

[0095] Please refer to Figure 3 , the steps to obtain the processing result of the video stream segment are as follows:

[0096] Based on the importance evaluation result of the timing segment, collect the acquisition data of each monitored video stream, including the video frame rate and the benchmark compression bit rate set by the user, to obtain the segment processing association data;

[0097] Based on the evaluation results of the importance of time series segments, collect the acquisition data of each monitored video stream, including the video frame rate and the benchmark compression bit rate set by the user, and collect the associated data for segment processing. Synchronize information from multiple data sources to ensure that the data of each video segment reflects its true state. For example, the frame rate data can be directly extracted from the metadata of the video file, while the compression bit rate may need to be obtained from the log file of the video processing software. The data is crucial for subsequent video processing and directly affects the quality and storage requirements of the video. Based on the data, the specific requirements and possible optimization strategies for processing each video segment can be determined to optimize the storage and transmission costs and ensure the effective management of the video stream.

[0098] Based on the associated data for segment processing, through the formula:

[0099] ;

[0100] and

[0101] ;

[0102] Calculate the adjusted frame rate and video compression bit rate for each time series segment;

[0103] Among them, is the initial frame rate, is the benchmark compression bit rate, is the importance score of the time series segment, is the scaling factor for frame rate adjustment, is the scaling factor for compression bit rate adjustment, is the allowed minimum frame rate, is the allowed minimum compression bit rate, is the adjusted frame rate, is the adjusted video compression bit rate;

[0104] Formula:

[0105] ;

[0106] and

[0107] ;

[0108] The benefit of the formula is that by dynamically adjusting the video frame rate and compression rate, the optimal allocation of resources can be achieved according to the importance of the content, thereby reducing the requirements for storage and bandwidth without sacrificing the quality of key content.

[0109] Detailed explanation of the formula and the derivation process of formula calculation:

[0110] Let the original frame rate of a video segment be 30 frames per second, and the minimum frame rate is 15 frames per second, and the scaling factor for frame rate adjustment is 0.3, and the importance score of this timing segment is 0.8. Calculate the adjusted frame rate according to the formula:

[0111] ;

[0112] Similarly, assume the reference compression bitrate is 500 kbps, and the minimum compression bitrate is 250 kbps, and the scaling factor for compression bitrate adjustment is 0.2. Calculate the adjusted compression bitrate:

[0113] ;

[0114] The results show that the adjusted frame rate and compression rate can effectively optimize according to the importance of video content, ensure the quality of key content, and at the same time optimize resource usage.

[0115] Based on the adjusted frame rate and video compression bitrate of each timing segment, perform frame rate adjustment and video compression processing on each timing segment to obtain the processing results of the video stream segment;

[0116] The process of performing frame rate adjustment and video compression processing on each timing segment includes using the adjusted frame rate and compression rate parameters for video encoding, usually implemented through encoding software such as FFmpeg. First, import the video segment into the encoding tool and apply the new frame rate and compression parameters. The process involves technical means such as resampling frames or adjusting the key frame interval to ensure the coherence and quality of the video stream are not affected. The processed video segment passes quality control tests, including observing the clarity and smoothness of the video, to ensure that the adjustment achieves the expected effect. The generation of the processing results of the video stream segment is a key step in improving the efficiency and optimizing resources of the entire monitoring system. Through optimization, a large amount of video data can be processed and stored more efficiently, while ensuring the video quality of key events.

[0117] Please refer to Figure 4 , and the steps to evaluate the transmission priority of each path are as follows:

[0118] Based on the transmission environment of the monitored video stream, perform real-time monitoring on each network transmission path, collect the load data, latency, and packet loss data of the path to obtain network status information;

[0119] Based on the transmission environment of the surveillance video stream, each network transmission path is monitored in real time. Network performance monitoring tools are used to track the status of each path in real time, including key metrics such as load, latency, and packet loss. Data is collected by sensors deployed at various network nodes and aggregated and analyzed through a network management system. Monitoring tools such as Wireshark or NetFlow can provide a detailed view of network traffic and problems in real time, enabling network administrators to quickly identify and resolve issues that may affect the quality of video stream transmission. In this way, real-time monitoring not only helps maintain the stable operation of the network but also ensures optimal performance of video data during transmission.

[0120] Based on the network status information, through the formula:

[0121] ;

[0122] Calculate the transmission priority score for each path;

[0123] Where, is the transmission priority score of the path, represents the current actual load of the path, represents the maximum load capacity of the path, represents the actual latency of the path, is the packet loss rate of the path, , and are weight coefficients;

[0124] Formula:

[0125] ;

[0126] The benefit of the formula is that by comprehensively considering network load, latency, and packet loss rate, it can conduct a detailed scoring of the transmission priority of each path, thereby optimizing the allocation of network resources.

[0127] Detailed explanation of the formula and the derivation process of formula calculation:

[0128] Suppose the maximum load of a certain path is 1000 units, the current actual load is 600 units, the actual latency is 50 milliseconds, the packet loss rate is 0.02, and the weight coefficients , , and are set to 10, 0.05, and 2 respectively, and calculate according to the formula:

[0129] ;

[0130] The results show that under high load and large latency conditions, the transmission priority score of this path decreases, reflecting the actual situation of low transmission efficiency, indicating the need for network optimization or choosing other paths for data transmission.

[0131] Based on the transmission priority scores of each path, prioritize each transmission path to obtain a path priority list;

[0132] In the process of prioritizing each transmission path based on the transmission priority scores of each path, a sorting algorithm is used to adjust the path selection according to the scoring results. Use comparison sorting or more efficient sorting algorithms such as quicksort to ensure that data flows through the optimal path. This sorting process not only improves the utilization efficiency of network resources but also reduces video transmission latency and packet loss caused by path congestion or low quality. The obtained path priority list can be directly applied to routing decisions, support dynamic routing adjustment, and improve the data transmission performance of the entire network.

[0133] Please refer to Figure 5 , the steps to obtain the transmission ratio allocation result are as follows:

[0134] Based on the path priority list, extract the priority scores of each path and collect the maximum bandwidth data of each path to obtain transmission ratio correlation information;

[0135] Extract the priority scores of each path and collect the maximum bandwidth data of each path, which is obtained through the network management system or directly from the configuration interfaces of routers and switches. Bandwidth data is closely related to the capabilities of network devices and their configuration settings, usually set by network administrators during device deployment or adjusted during network optimization. The data reflects the actual performance and transmission capabilities of the network infrastructure.

[0136] Based on the transmission ratio correlation information, through the formula:

[0137] ;

[0138] Calculate the adjusted data transmission ratio for each path, adjust the data flow of each path to obtain the transmission ratio allocation result;

[0139] Among them, is the transmission priority score of path , is the transmission priority score of path , is the maximum bandwidth of path , is the maximum bandwidth of path , is the maximum bandwidth of path the adjusted data transmission ratio of path is the total number of paths;

[0140] Formula:

[0141] ;

[0142] The advantage of the formula is that by combining the priority score of each path with the maximum bandwidth, it can dynamically adjust the data flow of each path, thereby optimizing the overall network load distribution.

[0143] Detailed explanation of the formula and the derivation process of formula calculation: Suppose there are three paths, and their priority scores , , are 0.5, 0.3, and 0.2 respectively. The maximum bandwidth of each path , , are 100Mbps, 150Mbps, and 50Mbps respectively.

[0144] Use the formula to calculate the data transmission ratio of each path:

[0145] ;

[0146] ;

[0147] ;

[0148] The results show that according to the priority and bandwidth capabilities of the paths, Path 1 and Path 2 will undertake most of the data transmission tasks in the network. Due to bandwidth limitations and a lower priority score, the data transmission ratio of Path 3 is the smallest. This adjustment of the ratio helps to balance the network load and improve the transmission efficiency of critical tasks.

[0149] In the actual application of network control, configure the calculated data transmission ratio into the network devices, and adjust the load balancers and router settings on each network path to ensure that each path receives and transmits data according to the calculated ratio, including technical measures such as adjusting the queue management strategy and changing the weight settings of the routing protocol. After the implementation of the adjustment, monitor the consistency between the actual traffic and the predetermined ratio, and make necessary fine-tuning to ensure the optimization of network performance. In this way, the data flow of the network is precisely controlled and managed, improving the utilization rate of network resources and the reliability of data transmission.

[0150] Please refer to Figure 6 , the steps to obtain the traffic dynamic adjustment information are as follows:

[0151] Based on the video stream segment processing results and the transmission ratio allocation results, extract the monitoring location data of each video stream, extract the priority of the corresponding location, and construct the upload priority queue of the video stream;

[0152] Based on the video stream segment processing results and the transmission ratio allocation results, collect the specific monitoring point information of each monitored video stream, which is completed by accessing the database of video management. The database stores the correspondence between each video stream and its corresponding monitoring location. Through the location data, the priority information of each location can be identified and extracted. The priority data is usually determined by security requirements and the importance of the monitoring area and has been pre-set in the system. The extraction of the information is to construct the upload priority queue of the video stream. The construction of the queue depends on these data to ensure that high-priority video streams can be uploaded first to meet the monitoring requirements of possible security events or key activities.

[0153] Based on the upload priority queue of the video stream and the transmission ratio allocation results, adjust the transmission order of the video stream according to the priority list, implement the video stream transmission, and monitor the network traffic in real time to detect the current network status and traffic distribution, and obtain the network status information during the transmission process;

[0154] Based on the upload priority queue of the video stream and the transmission ratio allocation results, arrange the sending order of the data packets according to the upload priority queue, and monitor the current network status and traffic distribution through network monitoring tools such as NetFlow. The tool can provide detailed information on network usage in real time and detect any network conditions that may affect video transmission, such as bandwidth bottlenecks or abnormal traffic behavior, thus allowing network administrators to respond quickly, adjust network configurations or routing policies to maintain the balance of network traffic and the smoothness of video transmission.

[0155] Based on the network status information during the transmission process, when network congestion is detected, through the formula:

[0156] ;

[0157] Calculate the bandwidth limit ratio of low-priority video streams , and limit the transmission of each video stream in order from low to high according to the upload priority of the video stream to obtain the traffic dynamic adjustment information;

[0158] Among them, represents the original bandwidth allocation of the video stream, is the total bandwidth used by the current network, is the maximum bearing bandwidth of the network, is the adjusted bandwidth allocation amount;

[0159] Formula:

[0160] ;

[0161] The benefit of the formula is that by dynamically adjusting the bandwidth allocation according to the network congestion level, network overload can be effectively prevented, ensuring the stable transmission of important video streams.

[0162] Detailed explanation of the formula and the derivation process of formula calculation:

[0163] Let the original bandwidth of a certain video stream be 100 Mbps, and the total bandwidth currently used by the network be 80 Mbps, and the maximum bearable bandwidth of the network be 120 Mbps.

[0164] Calculate the adjusted bandwidth according to the formula:

[0165] ;

[0166] The result shows that under the current network congestion situation, the bandwidth of this video stream should be adjusted to 33.33 Mbps to avoid putting too much pressure on the network and ensure the continuity of data transmission. This dynamic adjustment mechanism helps to flexibly meet the needs of different network condition changes while maintaining network performance.

[0167] Please refer to Figure 7 for the steps to analyze the video traffic change trend within the time window:

[0168] Based on the traffic dynamic adjustment information, monitor the data size of each video stream in real time, record the video stream size at each detection time point, and obtain the real-time monitoring data of the video stream;

[0169] Based on the traffic dynamic adjustment information, monitor the data size of each video stream in real time, collect the data stream statistical information from network devices such as routers and switches. The information usually includes the size and timestamp of each data packet. Monitoring tools such as Wireshark or custom scripts are used to capture the data traffic passing through the device and record it in chronological order for subsequent analysis. Real-time monitoring allows administrators to understand the status of data streams in the network at any given time point. The monitoring data is used to build a real-time database, which records the video stream size at each detection time point and provides support for further data processing and decision-making.

[0170] Based on the real-time monitoring data of the video stream, according to the preset time window size, count the size change of each video stream within the time window, and obtain the video traffic change data within the time window;

[0171] The operation of statistically analyzing the size change of each video stream within a preset time window based on real-time monitoring data of the video stream involves using time series analysis techniques to process the collected data. These techniques can help determine the changing trend of the video data stream over time. Analysis tools such as time series databases or stream processing frameworks can automatically process the data, calculate the total traffic within a specified time window, and identify traffic peaks or abnormal patterns. This statistics not only helps network administrators understand the network load during a specific period but also provides a basis for optimizing network transmission strategies and resource allocation.

[0172] Based on the video traffic change data within the time window, through the formula:

[0173] ;

[0174] Calculate the increase and decrease rate of the video traffic, evaluate the changing trend of the video traffic, and obtain the trend evaluation result;

[0175] Among them, is the increase and decrease rate of the video traffic, represents the change amount of the video traffic within the time window, is the length of the time window;

[0176] Formula:

[0177] ;

[0178] The benefit of the formula is that by calculating the increase and decrease rate of the video traffic within a regular time window, the changing trend of the traffic can be effectively evaluated, thus providing decision support for network traffic management and optimization.

[0179] Detailed explanation of the formula and the derivation process of the formula calculation:

[0180] Set the length of a time window to be 10 minutes. If the video traffic increases from 100MB to 150MB within this time window, the change amount is 50MB, then the increase and decrease rate of the video traffic is calculated as follows:

[0181] ;

[0182] The calculation result shows that within 10 minutes, the video traffic increases by an average of 5MB per minute. This rate indicator helps network administrators quickly understand the expansion or contraction of the network traffic and is particularly important for predicting network congestion and capacity planning. Especially in a high-demand video surveillance system, monitoring the increase and decrease rate of traffic can prevent network overload and ensure the continuity and efficiency of video surveillance.

[0183] Please refer toFigure 8 , the steps for obtaining the buffer capacity adjustment information are as follows:

[0184] Based on the trend assessment result, extract the increase and decrease rate of video traffic and the current video traffic size to obtain buffer-related data;

[0185] Extract the increase and decrease rate of video traffic and the current video traffic size, and use the already integrated sensors and monitoring tools to continuously track the status of each video stream. The data capture function enables the system to receive the size information and change rate of the video stream in real time. The data reflects the smoothness of the video stream and the actual usage of network capacity, which is crucial for providing a basis for buffer pool adjustment, optimizing network performance, and ensuring video transmission quality, and ensuring that the video monitoring system can remain stable and efficient when network conditions change.

[0186] Based on the buffer-related data, through the formula:

[0187] ;

[0188] Calculate the adjusted buffer pool capacity;

[0189] Among them, is the increase and decrease rate of video traffic, is the traffic size of the current video stream, is the benchmark capacity of the buffer pool, is the adjustment coefficient, is the adjusted buffer pool capacity;

[0190] Formula:

[0191] ;

[0192] The advantage of the formula is that by considering the current size and increase and decrease rate of video traffic to dynamically adjust the buffer pool capacity, it can effectively cope with network fluctuations and ensure the continuity of video transmission and the integrity of data.

[0193] Detailed explanation of the formula and the derivation process of formula calculation:

[0194] Let the benchmark buffer pool capacity be 500MB, the adjustment coefficient be 0.05, the traffic size of the current video stream be 400MB, and the increase and decrease rate of video traffic be 10MB / min. Calculate the adjusted buffer pool capacity as follows:

[0195] ;

[0196] The calculation results show that under the given conditions, the adjusted buffer pool capacity needs to be increased to 700MB to adapt to the current video traffic demands and changes. This dynamic adjustment strategy helps to alleviate network congestion, optimize resource allocation, and thus improve the overall performance and response speed of the system.

[0197] Based on the adjusted buffer pool capacity, apply it to the network, update the buffer strategy for monitoring video stream transmission in the system, and obtain buffer capacity adjustment information;

[0198] Based on the adjusted buffer pool capacity, by configuring the buffer management strategies on network devices and servers, update the corresponding network configurations according to the new buffer capacity settings, including adjusting the queue management settings of routers and switches, as well as the storage allocation strategy on the server. Through technical operations, the network can manage a large amount of data streams more effectively, ensuring that data transmission does not cause video stream interruption or quality degradation under high-load conditions. The adjustment is also recorded in the system's operation log for easy problem tracking and future system optimization.

[0199] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A video surveillance traffic intelligent optimization system, characterized in that: The system comprises: The time segment evaluation module divides the video stream into time segments according to the preset time interval based on the monitoring video stream, analyzes the frame change data in each time segment, and evaluates the importance of each time segment by counting the pixel difference rate between frames. According to the importance, the frame rate of each time segment is adjusted, and the video compression bit rate of each time segment is adjusted to obtain the video stream segment processing result; The path priority adjustment module monitors the network transmission path in real time based on the transmission environment of the monitoring video stream, collects the load data, delay and packet loss data of the path, evaluates the transmission priority of each path, and adjusts the data transmission ratio of each path according to the transmission priority and bandwidth size of the path to obtain the transmission ratio allocation result; The traffic scheduling optimization module extracts the monitoring position of each monitoring video stream based on the video stream segment processing results and the transmission ratio allocation results, extracts the priority of the corresponding position, builds the upload priority queue of the video stream, implements video stream transmission, and monitors the network traffic in real time. When network congestion is detected, the bandwidth allocation of low-priority video streams is dynamically adjusted to obtain traffic dynamic adjustment information; The buffer strategy adaptation module monitors the size of each monitoring video stream in real time based on the traffic dynamic adjustment information, records the size of the video stream at each detection time point, obtains the real-time monitoring data of the video stream, and counts the size change of each video stream in the time window according to the preset time window size, obtains the video traffic change data in the time window, evaluates the video traffic change trend, and dynamically adjusts the buffer pool capacity of the video stream according to the video traffic change trend to obtain the buffer capacity adjustment information; The steps of evaluating the importance of each time series segment are: Based on the monitoring video stream, the video stream is divided into time periods according to the preset time intervals to obtain a video time period list; Based on the video time period list, the frame data in each video time period is analyzed, the number of difference pixels between two frames is calculated, and the total number of difference pixels in the entire time period is counted to obtain difference pixel statistics; Based on the difference pixel statistics, by the formula: ； Calculate the importance score of each time series segment to obtain the time series segment importance evaluation result; in, Represents the total amount of difference pixels within the time period, is the total number of pixels in the time period, is the influence coefficient, Rate the importance of the time sequence segments; The steps of obtaining the processing result of the video stream segment are as follows: Based on the time sequence segment importance evaluation result, the acquisition data of each monitoring video stream is collected, including the video frame rate and the user-set reference compression bit rate, to obtain segment processing related data; Process the associated data based on the fragment, by the formula: ； and ； Calculate the adjusted frame rate and video compression bit rate for each time sequence segment; in, is the initial frame rate, is the base compression bit rate, is the importance score of the time series segment, is the scaling factor for frame rate adjustment, is the scaling factor for compression bit rate adjustment, is the minimum frame rate allowed, is the minimum compression bitrate allowed, is the adjusted frame rate, is the adjusted video compression bitrate; Based on the adjusted frame rate and video compression bit rate of each time sequence segment, frame rate adjustment and video compression processing are performed on each time sequence segment to obtain a video stream segment processing result.

2. The video surveillance traffic intelligent optimization system according to claim 1 is characterized in that: The steps of evaluating the transmission priority of each path are: Based on the transmission environment of the surveillance video stream, each network transmission path is monitored in real time, and the load data, delay and packet loss data of the path are collected to obtain network status information; Based on the network status information, by formula: ； Calculate the transmission priority score for each path; in, Score the transmission priority of the path, Indicates the actual load of the path. represents the maximum load capacity of the path, represents the actual delay of the path, is the packet loss rate of the path, , and is the weight coefficient; Based on the transmission priority score of each path, each transmission path is prioritized to obtain a path priority list.

3. The video surveillance traffic intelligent optimization system according to claim 2 is characterized in that: The steps for obtaining the transmission ratio allocation result are: Based on the path priority list, extract the transmission priority score of each path, and collect the maximum bandwidth data of each path to obtain transmission ratio association information; Based on the transmission ratio association information, through the formula: ； Calculate the adjusted data transmission ratio of each path, adjust the data flow of each path, and obtain the transmission ratio allocation result; in, is the transmission priority score of path i, is the transmission priority score of path j, is the maximum bandwidth of path i, is the maximum bandwidth of path j, is the adjusted data transmission ratio of path i, is the total number of paths.

4. The video surveillance traffic intelligent optimization system according to claim 1 is characterized in that: The steps for obtaining the traffic dynamic adjustment information are as follows: Based on the video stream segment processing results and the transmission ratio allocation results, the monitoring location data of each video stream is extracted, the priority of the corresponding location is extracted, and the upload priority queue of the video stream is constructed; Based on the upload priority queue and the transmission ratio allocation result of the video stream, the sending order of the data packets is arranged according to the upload priority queue, the video stream transmission is implemented, and the network traffic is monitored in real time, the current network status and traffic distribution are detected, and the network status information of the transmission process is obtained; Based on the network status information of the transmission process, when network congestion is detected, the formula is used: ； Calculate the bandwidth limit ratio of low-priority video streams, and limit the transmission of each video stream in order from low to high according to the upload priority of the video stream, and obtain dynamic traffic adjustment information; in, Represents the original bandwidth allocation of the video stream, is the total bandwidth currently used by the network, is the maximum carrying bandwidth of the network, is the adjusted bandwidth allocation.

5. The video surveillance traffic intelligent optimization system according to claim 1 is characterized in that: The steps of evaluating the video traffic change trend are as follows: Based on the traffic dynamic adjustment information, the data size of each video stream is monitored in real time, the video stream size at each detection time point is recorded, and real-time monitoring data of the video stream is obtained; Based on the real-time monitoring data of the video stream, according to the preset time window size, the size change of each video stream in the time window is counted to obtain the video flow change data in the time window; Based on the video traffic change data within the time window, the formula is: ； Calculate the increase and decrease rate of video traffic, evaluate the video traffic change trend, and obtain the trend evaluation result; in, is the rate of increase or decrease of video traffic, Indicates the change in video traffic within the time window. is the length of the time window.

6. The video surveillance traffic intelligent optimization system according to claim 5 is characterized in that: The steps for obtaining the buffer capacity adjustment information are as follows: Based on the trend evaluation result, extract the video traffic increase / deceleration rate and the current video traffic size to obtain buffer association data; Based on the buffer association data, by the formula: ； Calculate the adjusted buffer pool capacity; in, is the rate of increase or decrease of video traffic, is the current video stream traffic size, is the base capacity of the buffer pool, is the adjustment factor, is the adjusted buffer pool capacity; Based on the adjusted buffer pool capacity, the buffer strategy for monitoring video stream transmission is updated to obtain buffer capacity adjustment information.

Images