A wireless communication-based monitoring video transmission method and system

Abstract

The application provides a kind of based on wireless communication monitoring video transmission method and system, it is related to monitoring video transmission technical field, comprising: obtaining network state data and preprocessing, the network state data includes bandwidth, delay and packet loss rate;Network state prediction model is established based on LSTM neural network, and future network state is predicted according to the network state prediction model;Based on the future network state, transmission path selection is carried out using multi-objective optimization algorithm;For selected transmission path, video encoding parameters are adjusted, the encoding parameters include code rate, resolution, frame rate, adaptive transmission protocol is used, and transmission rate is dynamically adjusted according to real-time network state.The application can dynamically select different paths, avoid network congestion or degradation, and adaptively adjust the quality and rate of video transmission according to the current network state to ensure stable transmission of video quality under different network conditions.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method and system for transmitting surveillance video based on wireless communication. Background Technology

[0002] Ensuring high-quality video transmission and a positive user experience in complex and ever-changing network environments is a significant challenge. Fluctuations and instability in network conditions can lead to degraded video transmission quality, resulting in stuttering, blurring, and other issues. Furthermore, the optimal video encoding parameters and transmission strategies vary depending on the network conditions. Accurately predicting changes in network conditions and dynamically optimizing transmission paths, encoding parameters, and transmission strategies accordingly is a crucial problem that urgently needs to be solved. Summary of the Invention

[0003] In view of the problems existing in the above-mentioned existing surveillance video transmission methods, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is how to provide a method for transmitting surveillance video based on wireless communication.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: acquiring and preprocessing network status data, the network status data including bandwidth, latency, and packet loss rate; establishing a network status prediction model based on an LSTM neural network, and predicting future network status based on the network status prediction model; selecting a transmission path using a multi-objective optimization algorithm based on the future network status, and adjusting video encoding parameters, including bitrate, resolution, and frame rate, for the selected transmission path; and employing an adaptive transmission protocol to dynamically adjust the transmission rate according to the real-time network status.

[0006] As a preferred embodiment of the wireless communication-based video transmission method of the present invention, the step of establishing a network state prediction model based on an LSTM neural network and predicting the future network state according to the network state prediction model includes: establishing a network state prediction model based on LSTM, wherein the network state prediction model includes an input layer, an LSTM layer, and a fully connected layer; integrating the preprocessed network state data to form a network state vector; inputting the network state vector into the input layer of the LSTM base model; adding one or more LSTM layers, each containing several memory units; and mapping the output of the LSTM layer to the predicted future network state after passing through a fully connected layer.

[0007] As a preferred embodiment of the wireless communication-based video transmission method of the present invention, the method includes: selecting transmission paths based on the future network state using a multi-objective optimization algorithm, including: minimizing latency, minimizing packet loss rate, and maximizing bandwidth as optimization objectives; using Dijkstra's algorithm to discover multiple feasible transmission paths based on network topology distribution, where each transmission path consists of transmission nodes and links; predicting the future network state of each feasible transmission path using the network state prediction model; mapping the future network state of each transmission path to an objective function value; evaluating the quality of the paths using the NSGA-III algorithm; randomly selecting several transmission paths as an initial population; calculating the fitness of each transmission path based on its future network state; selecting individuals from the current population for crossover and mutation based on the fitness value; and selecting a transmission path from the Pareto optimal solution set after reaching a preset number of iterations.

[0008] As a preferred embodiment of the wireless communication-based video transmission method of the present invention, the step of adjusting video encoding parameters for a selected transmission path includes: acquiring network status data of the selected transmission path; if the network latency exceeds a preset first threshold, reducing the frame rate of the video encoding by a preset first ratio; if the network packet loss rate exceeds a preset second threshold, reducing the bitrate of the video encoding by a preset second ratio; if the available network bandwidth is lower than the bitrate of the video encoding, simultaneously reducing the bitrate and resolution of the video encoding by a preset third ratio; and encoding the video source data according to the adjusted encoding parameter values ​​using a preset video encoding method to obtain encoded video data.

[0009] In a preferred embodiment of the wireless communication-based video transmission method of the present invention, if the network status data is detected to have changed and does not meet the preset video transmission quality requirements, the process returns to the step of adjusting the video encoding parameters, and the video encoding parameters are re-evaluated and adjusted based on the latest network status data.

[0010] As a preferred embodiment of the wireless communication-based surveillance video transmission method of the present invention, the step of adopting an adaptive transmission protocol to dynamically adjust the transmission rate according to the real-time network status includes: obtaining the real-time network status of the selected transmission path; inputting the real-time network status into a pre-constructed random forest model to obtain the health score of the network; if the health score is lower than a preset health threshold, triggering the rate adjustment mechanism of the adaptive transmission protocol to adjust the transmission rate.

[0011] As a preferred embodiment of the wireless communication-based video transmission method of the present invention, the rate adjustment mechanism of the adaptive transmission protocol includes: using the real-time network state as the state space and the transmission rate adjustment range as the action space, determining the optimal transmission rate through the Q-Learning algorithm; inputting historical network state parameters into the network state prediction model to predict the future network state within a certain period of time; and using the prediction result as one of the states of the Q-Learning algorithm to adjust the transmission rate in advance.

[0012] Secondly, embodiments of the present invention provide a monitoring video transmission method system based on wireless communication. The system includes: a data collection module for acquiring network status data and performing preprocessing; an LSTM network status prediction module for predicting future network status based on a network status prediction model; a path selection module for selecting a transmission path based on the future network status; and a parameter adjustment module for adjusting video encoding parameters and transmission rate.

[0013] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the wireless communication-based surveillance video transmission method described in the first aspect of the present invention.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the wireless communication-based surveillance video transmission method described in the first aspect of the present invention.

[0015] The technical solution provided by the embodiments of the present invention can include the following beneficial effects: by using a multi-objective optimization algorithm for transmission path selection, combined with the future network state predicted by the LSTM model, different paths can be dynamically selected to avoid network congestion or degradation, and the quality and rate of video transmission can be flexibly adjusted according to the current network state to ensure stable transmission of video quality under different network conditions. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a wireless communication-based video monitoring transmission method according to the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0020] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0021] like Figure 1 This embodiment discloses a method for transmitting surveillance video based on wireless communication, which includes the following steps:

[0022] Step S1: Obtain network status data and perform preprocessing.

[0023] Specifically, network interface cards (NICs) and wireless access points (APs) are used in conjunction to acquire network status data in real time. Data sources include the TCP / UDP layers in the network protocol stack and wireless channel monitoring information (such as CSI). A set collection frequency is used for data acquisition. The network status data includes bandwidth, latency, and packet loss rate. The preprocessing steps include using Python's Pandas library for data cleaning to remove missing and outlier values; and using the Min-Max normalization method to normalize the data, scaling it to the [0,1] range.

[0024] Step S2: Establish a network state prediction model based on the LSTM neural network, and predict the future network state according to the network state prediction model.

[0025] Step S201: Establish a network state prediction model based on LSTM. The network state prediction model includes an input layer, an LSTM layer, and a fully connected layer.

[0026] Step S202: Integrate the preprocessed network state data to form a network state vector. For example, at time t, the network state vector is: F(t)=[Bnorm(t),Dnorm(t),Pnorm(t),B(t),D(t),P(t)], where Bnorm(t),Dnorm(t), andPnorm(t) are the normalized bandwidth, latency, and packet loss rate at time t, respectively, and B(t),D(t), andP(t) are the bandwidth, latency, and packet loss rate at time t, respectively.

[0027] Step S203: Input the network state vector into the input layer of the LSTM base model. The input dimension is the number of features of the network state. In this embodiment, the number of features is 6.

[0028] Step S204: Add one or more LSTM layers, each containing a number of memory cells. In this embodiment, only one LSTM layer is used, containing 128 memory cells.

[0029] Step S205: After passing through a fully connected layer, the output of the LSTM layer is mapped to the predicted future network state. In this embodiment, the predicted network state at time T has an output dimension of 3 (bandwidth, latency, and packet loss rate), represented as follows:

[0030] ;

[0031] Among them, W o Let b be the weight matrix of the fully connected layer. o h is the bias term. T Xpred(T) represents the hidden state of the LSTM at the last time step, and Xpred(T) represents the network state at time T.

[0032] It is important to note that to ensure the prediction model accurately reflects changes in network state, it needs to be trained first, using the ReLU activation function and mean squared error as the loss function. The Adam optimization algorithm is employed to train the model, continuously adjusting its parameters to accurately predict trends in network state changes. Training data is derived from historical network state data; the specific training process can be achieved using existing techniques and will not be elaborated upon here.

[0033] Step S3: Based on the future network state, a multi-objective optimization algorithm is used to select the transmission path.

[0034] Step S301 sets the optimization objectives as minimizing latency, minimizing packet loss rate, and maximizing bandwidth.

[0035] Step S302: Generate a network topology map. Nodes in the map represent routers, switches, or base stations in the network, and links represent communication links between adjacent nodes. Based on the network topology map, use Dijkstra's algorithm to discover multiple feasible transmission paths, each consisting of transmission nodes and links. Dijkstra's algorithm is a commonly used shortest path algorithm that can calculate multiple feasible paths from the source node to the target node based on the weights of each link. In this embodiment, the weights can be calculated comprehensively based on indicators such as latency, packet loss rate, and bandwidth in the network topology; the specific calculation method is not limited.

[0036] It's worth noting that Dijkstra's algorithm can quickly find multiple feasible paths, ensuring that there are always multiple paths available in complex wireless network environments. Through network topology-based path identification, new transmission paths can be discovered in real time, avoiding bottlenecks or outages that might occur with a single path. This provides more options for subsequent multi-objective optimization, thereby better enabling adaptive path selection based on network conditions.

[0037] Step S303: Predict all feasible transmission paths using the network state prediction model to determine the future network state of each transmission path.

[0038] Step S304: Map the future network state of each transmission path to an objective function value. Each objective function corresponds to minimizing latency, minimizing packet loss rate, and maximizing bandwidth, respectively. Evaluate the quality of the paths using the NSGA-III algorithm, randomly select several transmission paths as the initial population, and calculate the fitness of each transmission path based on its future network state.

[0039] Step S305: Based on the fitness value, select individuals from the current population using the tournament selection method for crossover and mutation. The tournament selection method is a genetic algorithm selection mechanism that can randomly select several individuals (paths) from the current population and compete based on their fitness values ​​to select the best individual for crossover and mutation operations. The crossover operation generates a new path by combining two paths, and the mutation operation generates a new individual by making small-scale random modifications to the links on the path.

[0040] Step S306: After reaching the preset number of iterations, select a transmission path from the Pareto optimal solution set.

[0041] Step S4: For the selected transmission path, adjust the video encoding parameters, including bitrate, resolution, and frame rate. Adaptive transmission protocol is adopted to dynamically adjust the transmission rate according to the real-time network status.

[0042] Step S401: Obtain network status data for the selected transmission path.

[0043] Step S402: If the network latency exceeds a preset first threshold, the frame rate of the video encoding is reduced by a preset first percentage, where the first threshold is an important indicator for measuring the real-time performance of video transmission. Typically, the desired latency should be between 100-500 milliseconds (ms). It should be noted that the specific threshold can be set according to the usage scenario and requirements, and the first percentage can also be set according to requirements; generally, it is chosen to be between 10% and 30%.

[0044] Step S403: If the network packet loss rate exceeds a preset second threshold, the bitrate of the video encoding is reduced by a preset second percentage. Packet loss rate refers to the proportion of data packets lost during video transmission to the total number of data packets. For video transmission, a reasonable threshold for packet loss rate should generally be controlled between 1% and 5%.

[0045] Step S404: If the available network bandwidth is lower than the video encoding bitrate, then the video encoding bitrate and resolution are simultaneously reduced by a preset third percentage. Available bandwidth refers to the maximum data transmission rate available for video transmission on the current transmission path. When the available bandwidth is lower than the video encoding bitrate, the system needs to reduce the bitrate and resolution. When the available network bandwidth is lower than the video encoding bitrate, the video encoding bitrate and resolution are simultaneously reduced by 30%.

[0046] Step S405: Using a preset video encoding method, the video source data is encoded according to the adjusted encoding parameter values ​​to obtain encoded video data.

[0047] It is important to note that if the network status data changes and no longer meets the preset video transmission quality requirements, the process returns to the step of adjusting the video encoding parameters. The video encoding parameters are then re-evaluated and adjusted based on the latest network status data. For the encoding parameters requiring adjustment, dynamic adjustments are made within their respective ranges to obtain the adjusted values. Preferably, the video encoding frame rate ranges from 10 to 60 frames per second, the bitrate ranges from 100 to 8000 kbps, and the resolution ranges from 360P to 1080P. The video source data is encoded according to the adjusted encoding parameter values ​​to obtain encoded video data adapted to the current network transmission conditions. The encoded video data is transmitted through the selected transmission path, and the Ping command and Iperf tool are used to monitor changes in network latency, packet loss rate, and bandwidth in real time. When changes in network transmission conditions are detected and the video transmission quality requirements are no longer met, the video encoding parameters are re-evaluated and adjusted based on the latest network status information to dynamically adapt to changes in network transmission conditions and ensure video transmission quality.

[0048] The adoption of an adaptive transmission protocol, which dynamically adjusts the transmission rate based on real-time network conditions, includes:

[0049] Obtain the real-time network status of the selected transmission path.

[0050] The real-time network state is input into a pre-built random forest model to obtain the network's health score;

[0051] Specifically, the real-time network status parameters are obtained, and the network congestion level is determined using a random forest model to obtain a network health score. In this embodiment, the scoring formula can be:

[0052] ;

[0053] In the formula, This is represented as a network health score, where n is the number of decision trees (the number of feature vectors in the feature network state), and X... i Let represent the input feature vector of the i-th network state, and RF denotes the random forest model.

[0054] If the health score is lower than a preset health threshold, the rate adjustment mechanism of the adaptive transmission protocol is triggered to adjust the transmission rate.

[0055] The preset health threshold is set according to the situation, and the rate adjustment mechanism of the adaptive transmission protocol includes,

[0056] The real-time network status is used as the state space, which includes latency, packet loss rate, and bandwidth. The transmission rate adjustment range is used as the action space, which includes operations such as increasing the rate and decreasing the rate. The optimal transmission rate is determined by the Q-Learning algorithm.

[0057] Historical network state parameters are input into the network state prediction model to predict the future network state over a period of time.

[0058] The predicted results are used as one of the states of the Q-Learning algorithm to adjust the transmission rate in advance.

[0059] The Q-Learning algorithm dynamically adjusts the transmission rate, using network state parameters as the state space and the rate adjustment magnitude as the action space. Through continuous trial and error, it learns to find the optimal strategy, improving bandwidth utilization while ensuring QoS. During rate adjustment, the BBR congestion control algorithm is simultaneously employed. By estimating network bandwidth and RTT in real time, it dynamically adjusts the congestion window size, quickly converging to the optimal transmission rate. For application layer data with different priorities, the WFQ algorithm performs differentiated scheduling to ensure the transmission quality of critical data. To further improve the timeliness of rate adjustment, an LSTM neural network predicts bandwidth and latency trends over a future period. Historical network state parameters are used as input features, and the prediction results serve as one of the states in Q-Learning, guiding advance rate adjustments.

[0060] This embodiment also provides a monitoring video transmission method system based on wireless communication, which includes:

[0061] The data collection module is used to acquire network status data and perform preprocessing.

[0062] The LSTM network state prediction module is used to predict the future network state based on the network state prediction model.

[0063] The path selection module is used to select transmission paths based on future network conditions;

[0064] The parameter adjustment module is used to adjust video encoding parameters and transmission rate.

[0065] This invention employs a multi-objective optimization algorithm for transmission path selection, combined with the future network state predicted by the LSTM model. It can dynamically select different paths to avoid network congestion or degradation, and adaptively adjust the quality and rate of video transmission according to the current network state to ensure stable transmission of video quality under different network conditions.

[0066] This embodiment also provides a computer device applicable to a wireless communication-based surveillance video transmission method, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the wireless communication-based surveillance video transmission method proposed in the above embodiment.

[0067] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0068] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the wireless communication-based video transmission method as described in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0069] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for transmitting surveillance video based on wireless communication, characterized in that, include: The network status data is acquired and preprocessed, including bandwidth, latency, and packet loss rate. A network state prediction model is established based on an LSTM neural network, and the future network state is predicted based on the network state prediction model. Based on the future network state, a multi-objective optimization algorithm is used to select the transmission path; For the selected transmission path, adjust the video encoding parameters, including bitrate, resolution, and frame rate, and adopt an adaptive transmission protocol to dynamically adjust the transmission rate according to the real-time network status. Based on the future network state, a multi-objective optimization algorithm is used to select transmission paths, including: The optimization objectives are to minimize latency, minimize packet loss rate, and maximize bandwidth. Based on the network topology distribution, Dijkstra's algorithm is used to discover multiple feasible transmission paths, each of which consists of transmission nodes and links. The network state prediction model is used to predict all feasible transmission paths and determine the future network state of each transmission path. The future network state of each transmission path is mapped to the objective function value. The quality of the path is evaluated by the NSGA-III algorithm. Several transmission paths are randomly selected as the initial population. The fitness of each transmission path is calculated based on its future network state. Based on fitness values, individuals are selected from the current population for crossover and mutation using a tournament selection method. After reaching the preset number of iterations, a transmission path is selected from the Pareto optimal solution set; The adjustment of video encoding parameters for the selected transmission path includes: Obtain network status data for the selected transmission path; If the network latency exceeds a preset first threshold, the frame rate of the video encoding will be reduced by a preset first percentage. If the network packet loss rate exceeds a preset second threshold, the bitrate of the video encoding will be reduced by a preset second ratio. If the available network bandwidth is lower than the bitrate of the video encoding, then the bitrate and resolution of the video encoding are simultaneously reduced by a preset third ratio. The video source data is encoded using a preset video encoding method according to the adjusted encoding parameter values ​​to obtain encoded video data. If the network status data changes and no longer meets the preset video transmission quality requirements, the process returns to the step of adjusting video encoding parameters. Based on the latest network status data, the video encoding parameters are reassessed and adjusted. For the encoding parameters that need adjustment, dynamic adjustments are made within their value range to obtain adjusted encoding parameter values. The video source data is then encoded according to the adjusted encoding parameter values ​​to obtain encoded video data adapted to the current network transmission conditions. The encoded video data is transmitted through the selected transmission path, and changes in network latency, packet loss rate, and bandwidth parameters are monitored in real time. When changes in network transmission conditions are detected and no longer meet the video transmission quality requirements, the video encoding parameters are reassessed and adjusted based on the latest network status information. The adoption of an adaptive transmission protocol, which dynamically adjusts the transmission rate based on real-time network conditions, includes: Obtain the real-time network status of the selected transmission path; The real-time network state is input into a pre-built random forest model to obtain the network's health score; If the health score is lower than the preset health threshold, the rate adjustment mechanism of the adaptive transmission protocol is triggered to adjust the transmission rate. The rate adjustment mechanism of the adaptive transmission protocol includes, Using the real-time network state as the state space and the transmission rate adjustment range as the action space, the optimal transmission rate is determined by the Q-Learning algorithm. Historical network state parameters are input into the network state prediction model to predict the future network state over a period of time. The prediction results are used as one of the states of the Q-Learning algorithm to adjust the transmission rate in advance.

2. The video monitoring transmission method based on wireless communication according to claim 1, characterized in that, The process of establishing a network state prediction model based on an LSTM neural network and predicting future network states based on the network state prediction model includes: A network state prediction model is established based on LSTM, which includes an input layer, an LSTM layer, and a fully connected layer. The preprocessed network state data are integrated to form a network state vector; The network state vector is input into the input layer of the LSTM base model; Add one or more LSTM layers, each containing several memory units; The output of the LSTM layer is mapped to the predicted future network state after passing through a fully connected layer.

3. A system for transmitting surveillance video based on wireless communication, implementing the method described in 1 or 2, characterized in that, include: The data collection module is used to acquire network status data and perform preprocessing. The LSTM network state prediction module is used to predict the future network state based on the network state prediction model. The path selection module is used to select transmission paths based on future network conditions; The parameter adjustment module is used to adjust video encoding parameters and transmission rate.

Images