Video monitoring system based on efficient video compression and video super-division technology

Abstract

The invention discloses a video monitoring system based on a high-efficiency video compression and video super-division technology. The video monitoring system comprises a video acquisition module, a high-efficiency compression module, a storage module, a transmission module, a super-division module and a monitoring display module. The efficient compression module adopts an advanced algorithm and prediction, transformation and entropy coding technologies to adaptively adjust parameters to reduce storage and transmission requirements, the storage module is of a distributed architecture to ensure data security, and the transmission module adopts a high-speed network technology to adjust parameters according to requirements of a network and a receiving end, so that the transmission efficiency is improved. The super-resolution module restores a low-resolution video to a high-resolution video by using a deep learning algorithm such as a convolutional neural network and a generative adversarial network, and the monitoring display module provides a clear monitoring picture and multiple playing functions. The storage and transmission cost is reduced through efficient video compression, the data security is ensured through distributed storage, the real-time performance is ensured through high-speed network transmission, the image quality is greatly improved through the deep learning algorithm, the monitoring display module is convenient to check and analyze, and the practicability, reliability and definition of the video monitoring system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of video monitoring systems, and in particular to a video monitoring system based on efficient video compression and video super-resolution technology. Background Art

[0002] With the continuous development of science and technology, video surveillance is increasingly used in various fields, such as public safety, traffic management, enterprise security, etc. However, traditional video surveillance systems often have some problems when facing large-scale video data.

[0003] On the one hand, the amount of video data is huge, and the storage and transmission costs are high. With the increase in the number of surveillance cameras and the improvement of video resolution, the amount of video data has exploded. Traditional video storage and transmission methods are difficult to meet the needs of large-scale video data, resulting in high storage costs and large transmission delays, which affect the real-time and effectiveness of video surveillance.

[0004] On the other hand, low-resolution videos have poor image quality and cannot meet the needs of high-definition surveillance. In some scenarios, due to low camera resolution and limited transmission bandwidth, the image quality of surveillance videos is poor, making it difficult to clearly identify target objects and detailed information. This brings great difficulties to the analysis and processing of video surveillance.

[0005] At the same time, traditional video surveillance systems are relatively backward in terms of video compression and super-resolution processing technology. The video compression algorithm is not efficient, which easily leads to video quality loss; and the super-resolution processing technology is not mature enough to effectively improve the clarity and quality of the video. Summary of the invention

[0006] The present invention proposes a video monitoring system based on high-efficiency video compression and video super-resolution technology to solve the problems mentioned in the above-mentioned prior art.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: a video monitoring system based on efficient video compression and video super-resolution technology, comprising:

[0008] Video acquisition module, used to collect video data of the monitoring area;

[0009] The efficient video compression module compresses the collected video data. This module uses advanced video compression algorithms and plays a key role in reducing the storage and transmission requirements of video data. The process can be mathematically described in the following way: let the original video data be V, the compressed video data be C(V), and the compression ratio be Where |V| represents the size of the original video data, and |C(V)| represents the size of the compressed video data.

[0010] The video frames are compressed efficiently by using predictive coding, transform coding and entropy coding techniques. In predictive coding, let the current frame be F t , the predicted frame is The prediction error is By encoding the prediction error, the amount of data can be reduced. Transform coding can be expressed as Where F is the input video frame, a i，j is the transformation coefficient, Ψ i，j is the basis function. Entropy coding models the probability distribution, such as Huffman coding or arithmetic coding, so that the average code length after encoding is close to the information entropy.

[0011] At the same time, the module adaptively adjusts the compression parameters according to the dynamic changes of the video content to improve the compression efficiency. Assuming the dynamic characteristics of the video content are D and the compression parameter is P, a functional relationship P = f(D) can be established, where the function f dynamically adjusts the compression parameters according to the dynamic changes of the video content to achieve the best compression effect. For example, when the video content changes greatly dynamically, the compression parameters such as the quantization parameter can be adjusted to minimize the amount of data while ensuring the video quality;

[0012] The video storage module stores compressed video data and adopts a distributed storage architecture, using data redundancy technology and backup strategies to prevent data loss;

[0013] The video transmission module transmits the compressed video data to the monitoring center or the designated receiving end. It uses high-speed network transmission technology to ensure the real-time transmission of video data. It adaptively adjusts the transmission parameters according to the network status and the needs of the receiving end to improve the transmission efficiency.

[0014] The video super-resolution module performs super-resolution processing on the received compressed video to significantly improve the video clarity and quality. This module uses a deep learning algorithm to build a super-resolution model by learning from a large number of high-resolution video samples and low-resolution video samples.

[0015] Let low resolution video be V LR , the high-resolution video obtained after super-resolution model processing is V SR The super-resolution model can be expressed as V SR =F(V LR , θ), where θ is the model parameter. During the training process, by minimizing the loss function L(V HR , V SR ) to optimize the model parameters. A common loss function can be the mean square error (MSE), that is, Where N is the number of samples, and are the i-th high-resolution and super-resolution video samples respectively. By continuously adjusting the model parameters, the super-resolution model can effectively restore the low-resolution video to the high-resolution video;

[0016] The monitoring display module is used to display the video after super-resolution processing, providing a clear and intuitive monitoring picture; it supports display on a monitor or large screen, and has the functions of video playback, pause, fast forward and slow motion.

[0017] Preferably, the video compression algorithm adopted by the high-efficiency video compression module includes the H.265 / HEVC or AV1 video coding standard.

[0018] Preferably, the distributed storage architecture adopted by the video storage module includes a distributed file system and a distributed database.

[0019] Preferably, the high-speed network transmission technology adopted by the video transmission module includes one or more of 5G network or fiber optic network.

[0020] Preferably, the deep learning algorithm adopted by the video super-resolution module includes a convolutional neural network or a generative adversarial network.

[0021] Preferably, a method of a video surveillance system based on efficient video compression and video super-resolution technology comprises the following steps:

[0022] S1. Collect video data of the monitoring area through the video acquisition module;

[0023] S2, compressing the collected video data using an efficient video compression module;

[0024] S3, storing the compressed video data into a video storage module;

[0025] S4, transmitting the compressed video data to the monitoring center or other designated receiving end through the video transmission module;

[0026] S5, performing super-resolution processing on the compressed video using a video super-resolution module at the receiving end;

[0027] S6. Display the super-resolution processed video through a monitoring display module.

[0028] Preferably, in the video compression step, a video compression algorithm is adopted, including H.265 / HEVC and AV1 video coding standards, and compression parameters are adaptively adjusted according to dynamic changes in video content.

[0029] Preferably, in the video transmission step, high-speed network transmission technology is adopted, including 5G network and fiber optic network, and the transmission parameters are adaptively adjusted according to the network conditions and the needs of the receiving end.

[0030] Preferably, in the video super-resolution processing step, a deep learning algorithm, including a convolutional neural network and a generative adversarial network, is used to establish a super-resolution model to restore the low-resolution video to a high-resolution video.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention brings significant beneficial effects to the video monitoring system by combining high-efficiency video compression and video super-resolution technology.

[0033] The present invention adopts advanced video compression algorithms, such as H.265 / HEVC, AV1, etc., to minimize the storage and transmission requirements of video data while ensuring video quality, reduce storage costs, improve transmission efficiency, and ensure the real-time nature of video surveillance.

[0034] The present invention improves the security and reliability of video data by utilizing a distributed storage architecture, prevents data loss, and provides a guarantee for the stable operation of a video monitoring system.

[0035] The present invention adopts high-speed network transmission technology, such as 5G network, optical fiber network, etc., to ensure that the compressed video data can be quickly and stably transmitted to the monitoring center or other designated receiving ends, thereby improving the response speed of video monitoring.

[0036] The present invention adopts a deep learning algorithm to perform video super-resolution processing, which can restore low-resolution video to high-resolution video, improve the clarity and image quality of the video, make the monitoring picture clearer and more intuitive, and help to better identify target objects and detailed information.

[0037] The present invention provides support for multiple display devices and rich video playback functions, making it convenient for users to view and analyze surveillance videos, thereby improving the usability and practicality of the video surveillance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention provides a schematic block diagram of a video monitoring system based on efficient video compression and video super-resolution technology. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0041] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0042] Reference Figure 1 :A video surveillance system based on efficient video compression and video super-resolution technology, comprising:

[0043] Video acquisition module, used to collect video data of the monitoring area;

[0044] The efficient video compression module compresses the collected video data. This module uses advanced video compression algorithms and plays a key role in reducing the storage and transmission requirements of video data. The process can be mathematically described in the following way: let the original video data be V, the compressed video data be C(V), and the compression ratio be Where |V| represents the size of the original video data, and |C(V)| represents the size of the compressed video data.

[0045] The video frames are compressed efficiently by using predictive coding, transform coding and entropy coding techniques. In predictive coding, let the current frame be F t , the predicted frame is The prediction error is By encoding the prediction error, the amount of data can be reduced. Transform coding can be expressed as Where F is the input video frame, a i，j is the transformation coefficient, Ψ i，j is the basis function. Entropy coding models the probability distribution, such as Huffman coding or arithmetic coding, so that the average code length after encoding is close to the information entropy.

[0046] At the same time, the module adaptively adjusts the compression parameters according to the dynamic changes of the video content to improve the compression efficiency. Assuming the dynamic characteristics of the video content are D and the compression parameter is P, a functional relationship P = f(D) can be established, where the function f dynamically adjusts the compression parameters according to the dynamic changes of the video content to achieve the best compression effect. For example, when the video content changes greatly dynamically, the compression parameters such as the quantization parameter can be adjusted to minimize the amount of data while ensuring the video quality;

[0047] The video storage module plays a vital role in the entire video surveillance system. It is responsible for storing video data processed by the efficient video compression module. In order to ensure the security and reliability of data, the module adopts an advanced distributed storage architecture.

[0048] The distributed storage architecture stores video data in multiple storage nodes, which can be located in different geographical locations and connected through the network. This architecture is highly scalable and fault-tolerant. When the system needs to store more video data, new storage nodes can be easily added without affecting the overall performance of the system. At the same time, if a storage node fails, the system can automatically redistribute the data to other normal nodes to ensure data availability.

[0049] To further prevent data loss, the video storage module also uses data redundancy technology and backup strategies. Data redundancy technology saves the same data copies on multiple storage nodes. Even if the data of a node is lost, the data can be restored from other nodes. Common data redundancy technologies include replica redundancy and erasure code redundancy. Replica redundancy refers to saving exactly the same copies of video data on multiple nodes, while erasure code redundancy encodes the data to generate multiple redundant data blocks. Even if some data blocks are lost, the original data can be restored from the remaining data blocks.

[0050] The backup strategy is to regularly back up video data to other storage media, such as external hard disks, tape libraries, etc. In this way, even if the entire distributed storage system fails, the data can be restored from the backup media. The backup strategy can be customized according to the needs of the system and the importance of the data, and different backup frequencies and retention periods can be set.

[0051] In addition, the video storage module also uses advanced data management technologies, such as data indexing, data retrieval, and data cleaning. Data indexing can quickly locate video data stored in the distributed storage system and improve data access efficiency. Data retrieval can quickly find and extract specific video data according to user needs. Data cleaning can regularly clean up expired video data, free up storage space, and improve the utilization of the storage system.

[0052] The video transmission module plays a key role in the entire video surveillance system. It is responsible for accurately and timely transmitting the efficiently compressed video data to the monitoring center or the designated receiving end.

[0053] The module uses advanced high-speed network transmission technology, such as 5G network technology, which has the characteristics of high bandwidth, low latency and large capacity. By using the millimeter wave frequency band and large-scale multiple input multiple output (MIMO) technology of the 5G network, it can achieve extremely fast data transmission speed and ensure the real-time transmission of high-definition video data. For optical fiber network transmission, it has the advantages of high stability and large bandwidth, and further improves the transmission capacity through technologies such as wavelength division multiplexing.

[0054] To ensure real-time transmission of video data, the video transmission module constantly monitors the network status. It accurately evaluates the current network's transmission capacity by collecting real-time information on parameters such as network delay, bandwidth utilization, and packet loss rate. When the network delay is high, the module can adopt an adaptive flow control strategy to reduce the amount of data sent to avoid further network congestion. If an increase in packet loss rate is detected, the module will activate error correction mechanisms such as automatic repeat request (ARQ) or forward error correction (FEC) to ensure data integrity.

[0055] At the same time, the video transmission module will also make adaptive adjustments based on the needs of the receiving end. If the receiving end device has low performance, the module can reduce the video resolution, frame rate or bit rate to adapt to the processing power of the receiving end. For example, when the receiving end is a mobile device, considering its limited battery life and processing power, the module can adjust the transmission parameters to reduce power consumption and computing burden. On the contrary, if the receiving end is a high-performance monitoring center device, the module can improve the quality parameters of the video to provide a clearer and more detailed monitoring picture.

[0056] In addition, the video transmission module may also use video stream adaptation technology. According to changes in network conditions, the video encoding parameters and transmission strategies are dynamically adjusted. For example, when the network bandwidth is sufficient, a high-bitrate video stream is transmitted; when the network bandwidth is limited, it automatically switches to a low-bitrate video stream to ensure continuous video playback. At the same time, the module can also use caching technology to pre-cache a certain amount of video data at the receiving end to cope with the impact of network fluctuations and ensure smooth video playback.

[0057] The video super-resolution module performs super-resolution processing on the received compressed video to significantly improve the video clarity and quality. This module uses a deep learning algorithm to build a super-resolution model by learning from a large number of high-resolution video samples and low-resolution video samples.

[0058] Let low resolution video be V LR , the high-resolution video obtained after super-resolution model processing is V SR The super-resolution model can be expressed as V SR =F(V LR , θ), where θ is the model parameter. During the training process, by minimizing the loss function L(V HR , V SR ) to optimize the model parameters. A common loss function can be the mean square error (MSE), that is, Where N is the number of samples, and are the i-th high-resolution and super-resolution video samples respectively. By continuously adjusting the model parameters, the super-resolution model can effectively restore the low-resolution video to the high-resolution video;

[0059] The monitoring display module is used to display the video after super-resolution processing, providing a clear and intuitive monitoring picture; it supports display on a monitor or large screen, and has the functions of video playback, pause, fast forward and slow motion.

[0060] In the present invention, the video compression algorithm adopted by the high-efficiency video compression module includes the H.265 / HEVC or AV1 video coding standard.

[0061] In the present invention, the distributed storage architecture adopted by the video storage module includes a distributed file system and a distributed database.

[0062] In the present invention, the high-speed network transmission technology adopted by the video transmission module includes one or more of 5G network or optical fiber network.

[0063] In the present invention, the deep learning algorithm adopted by the video super-resolution module includes a convolutional neural network or a generative adversarial network.

[0064] In the present invention, a method of a video monitoring system based on efficient video compression and video super-resolution technology comprises the following steps:

[0065] S1. Collect video data of the monitoring area through the video acquisition module;

[0066] S2, compressing the collected video data using an efficient video compression module;

[0067] S3, storing the compressed video data into a video storage module;

[0068] S4, transmitting the compressed video data to the monitoring center or other designated receiving end through the video transmission module;

[0069] S5, performing super-resolution processing on the compressed video using a video super-resolution module at the receiving end;

[0070] S6. Display the super-resolution processed video through a monitoring display module.

[0071] In the present invention, in the video compression step, a video compression algorithm is adopted, including H.265 / HEVC and AV1 video coding standards, and compression parameters are adaptively adjusted according to dynamic changes in video content.

[0072] In the present invention, the video transmission step is crucial. In this step, advanced high-speed network transmission technology is adopted, including 5G network and optical fiber network.

[0073] 5G networks have many advantages. First, the ultra-high bandwidth of 5G networks can meet the needs of fast transmission of large-scale high-definition video data. Its millimeter wave frequency band can provide a transmission rate of up to several Gbps, so that high-resolution video surveillance images can be transmitted to the monitoring center or the receiving end in real time. At the same time, the low latency characteristics of 5G networks are also one of the keys. By optimizing the network architecture and adopting advanced signal processing technology, the end-to-end delay of 5G networks can be controlled at the millisecond level to ensure the real-time nature of video surveillance. In addition, 5G networks also support large-scale device connections and can meet the needs of many surveillance cameras to transmit data at the same time. In terms of technical implementation, 5G networks use large-scale multiple-input multiple-output (MIMO) technology to improve the transmission quality and capacity of signals by deploying multiple antennas on base stations and terminal devices. At the same time, 5G networks also use network slicing technology, which can allocate independent network resources to video surveillance according to its specific needs to ensure the stability and reliability of transmission.

[0074] Optical fiber networks also play an important role in video transmission. Optical fiber has extremely high bandwidth and extremely low transmission loss, and can stably transmit large amounts of video data. It can support high-resolution, high-frame-rate video stream transmission to ensure the clarity and smoothness of the monitoring screen. In the architecture of the optical fiber network, wavelength division multiplexing (WDM) technology is used to greatly increase the transmission capacity by simultaneously transmitting multiple optical signals of different wavelengths in one optical fiber. In addition, the optical fiber network also has good anti-interference performance and is not affected by electromagnetic interference, which can ensure the transmission quality of video data.

[0075] In order to further improve the transmission efficiency, the present invention will adaptively adjust the transmission parameters according to the network conditions and the needs of the receiving end. In terms of monitoring the network conditions, the system will collect network parameters such as bandwidth, delay, and packet loss rate in real time. When the network bandwidth is sufficient, the system can increase the bit rate and resolution of the video to provide a higher quality monitoring screen. If the network delay is high, the system will reduce the frame rate of the video and reduce the amount of data transmitted to reduce the impact of the delay on the video playback. When the packet loss rate is detected to be rising, the system can use error correction coding technology, such as forward error correction (FEC), to increase the redundancy of the data and improve the reliability of data transmission.

[0076] The system will also make corresponding adjustments to the needs of the receiving end. If the performance of the receiving device is low, the system will reduce the resolution and bit rate of the video to adapt to the processing power of the receiving end. For example, when the receiving end is a mobile device, considering its limited battery life and processing power, the system can adjust the transmission parameters to reduce power consumption and computing burden. For high-performance monitoring center equipment, the system can provide high-resolution, high-frame-rate video streams to meet the needs of professional monitoring. At the same time, the system can also adjust the transmission strategy according to the network environment of the receiving end, such as Wi-Fi or mobile network, to ensure stable video transmission.

[0077] In the present invention, the video super-resolution processing step is a key step in improving the video quality. In this step, advanced deep learning algorithms are used, including Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN).

[0078] Convolutional neural networks play an important role in video super-resolution processing. It extracts features from low-resolution videos through multiple convolutional layers. In the convolutional layer, the convolution kernel is convolved with the input image to extract feature information at different levels. For example, the shallow convolutional layer can extract basic features such as edges and textures of the image, while the deep convolutional layer can capture more advanced semantic information. After being processed by multiple convolutional layers, a rich feature representation is obtained. Then, the low-resolution feature map is gradually restored to a high-resolution feature map through a deconvolution layer or an upsampling layer. In the upsampling process, interpolation algorithms such as bilinear interpolation or bicubic interpolation can be used to increase the resolution of the image. At the same time, in order to improve the effect of super-resolution, the residual learning method can also be introduced. By learning the residual between the low-resolution image and the high-resolution image, it is easier for the network to learn high-frequency detail information, thereby improving the quality of the restored high-resolution image.

[0079] Generative adversarial networks also have unique advantages in video super-resolution processing. It consists of two parts: a generator and a discriminator. The task of the generator is to convert low-resolution videos into high-resolution videos, while the discriminator is responsible for judging whether the input image is a real high-resolution image or a fake image generated by the generator. During the training process, the generator and the discriminator conduct adversarial learning. The generator continuously optimizes its parameters to generate more realistic high-resolution images in an attempt to deceive the discriminator; while the discriminator continuously improves its discriminative ability to distinguish between real images and generated images. Through this adversarial learning, the generator can gradually learn the distribution characteristics of high-resolution images, thereby generating clearer and more realistic high-resolution videos. For example, Deep Residual Generative Adversarial Networks (DRGAN) can be used to introduce a deep residual structure in the generator to further improve the quality of generated images.

[0080] By combining the advantages of convolutional neural networks and generative adversarial networks, a more effective super-resolution model can be established. First, a convolutional neural network is used to perform preliminary feature extraction and upsampling to obtain a preliminary high-resolution feature map. Then, the generated high-resolution feature map is input into the generator of the generative adversarial network for further optimization and refinement. The generator generates more realistic high-resolution videos by continuously learning the detailed features of high-resolution images. At the same time, the discriminator evaluates the generated videos and provides feedback information to help the generator continuously improve. After repeated training and optimization, the super-resolution model can effectively restore low-resolution videos to high-resolution videos, improve the clarity and quality of the videos, and provide clearer and more detailed image information for video surveillance systems.

[0081] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A video surveillance system based on efficient video compression and video super-resolution technology, characterized in that: include: Video acquisition module, used to collect video data of the monitoring area; The efficient video compression module compresses the collected video data and adopts video compression algorithms to reduce the storage and transmission requirements of video data. It uses predictive coding, transform coding and entropy coding technologies to efficiently compress video frames and adaptively adjusts compression parameters according to dynamic changes in video content to improve compression efficiency. The video storage module stores compressed video data and adopts a distributed storage architecture, using data redundancy technology and backup strategies to prevent data loss; The video transmission module transmits the compressed video data to the monitoring center or the designated receiving end. It uses high-speed network transmission technology to ensure the real-time transmission of video data. It adaptively adjusts the transmission parameters according to the network status and the needs of the receiving end to improve the transmission efficiency. The video super-resolution module performs super-resolution processing on the received compressed video to improve the video clarity and quality. It uses a deep learning algorithm to learn high-resolution and low-resolution video samples to establish a super-resolution model for restoring low-resolution video to high-resolution video. The monitoring display module is used to display the video after super-resolution processing, providing a clear and intuitive monitoring picture; it supports display on a monitor or large screen, and has the functions of video playback, pause, fast forward and slow motion.

2. The video surveillance system based on efficient video compression and video super-resolution technology according to claim 1 is characterized in that: The video compression algorithm adopted by the efficient video compression module includes H.265 / HEVC or AV1 video coding standards.

3. The video surveillance system based on efficient video compression and video super-resolution technology according to claim 1 is characterized in that: The distributed storage architecture adopted by the video storage module includes a distributed file system and a distributed database.

4. The video surveillance system based on efficient video compression and video super-resolution technology according to claim 1, characterized in that: The high-speed network transmission technology adopted by the video transmission module includes one or more of 5G network or optical fiber network.

5. The video surveillance system based on efficient video compression and video super-resolution technology according to claim 1 is characterized in that: The deep learning algorithm adopted by the video super-resolution module includes convolutional neural network or generative adversarial network.

6. A method for applying the video surveillance system based on efficient video compression and video super-resolution technology according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Collect video data of the monitoring area through the video acquisition module; S2, compressing the collected video data using an efficient video compression module; S3, storing the compressed video data into a video storage module; S4, transmitting the compressed video data to the monitoring center or other designated receiving end through the video transmission module; S5, performing super-resolution processing on the compressed video using a video super-resolution module at the receiving end; S6. Display the super-resolution processed video through a monitoring display module.

7. The video monitoring method based on efficient video compression and video super-resolution technology according to claim 6 is characterized in that: In the video compression step, video compression algorithms are used, including H.265 / HEVC and AV1 video coding standards, and compression parameters are adaptively adjusted according to dynamic changes in video content.

8. The video monitoring method based on efficient video compression and video super-resolution technology according to claim 6 is characterized in that: In the video transmission step, high-speed network transmission technology is used, including 5G network and fiber optic network, to adaptively adjust transmission parameters according to network conditions and the needs of the receiving end.

9. The video monitoring method based on efficient video compression and video super-resolution technology according to claim 6, characterized in that: In the video super-resolution processing step, deep learning algorithms, including convolutional neural networks and generative adversarial networks, are used to establish a super-resolution model to restore low-resolution videos to high-resolution videos.

Images