Monitoring video data processing method, system, electronic device and storage medium

Abstract

The embodiment of the present invention provides a method, system, electronic device and storage medium for processing monitoring video data, which belongs to the field of monitoring. The method includes: using a signaling agent to pronounce video signaling to a camera, and when the camera receives the audio and video signaling, using a media stream agent to transmit the audio and video to obtain the audio and video; wherein, in the process of using the signaling agent to pronounce video signaling to the camera, the audio and video signaling stream is subjected to a signaling legitimacy detection to discard non-compliant data; in the process of using the media stream agent to transmit audio and video to obtain audio and video, the audio and video media stream is subjected to data cleaning, wherein data cleaning includes but is not limited to steganography detection. Through the above technical scheme, the real-time data cleaning function of the video terminal media data transmission is realized, and the accuracy of data cleaning is improved by using the linkage detection of signaling data and media data and the independent steganography detection means of audio and video data.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a method, system, electronic device and storage medium for processing monitoring video data. Background Art

[0002] Thanks to the vigorous development of Internet applications, the evolution of image compression coding and streaming media technology, and the substantial improvement in system processing capabilities, network video surveillance services have developed rapidly.

[0003] The monitoring network and the office network are usually two physically isolated networks. Physical isolation can make the office network have a higher level of confidentiality and security, and minimize the impact of the complex Internet network environment. The video surveillance data transmitted from the monitoring network may contain virus files and encrypted files that are steganographic, which will undoubtedly seriously impact the security of the office network. The hazards include:

[0004] 1) Leakage of sensitive data: Video steganography can hide sensitive information in video files, such as confidential documents, passwords, and communication content. When these steganographic videos are transmitted from the Internet to a confidential network, they may be decoded within the confidential network, resulting in the leakage of sensitive data. 2) Malware propagation: Attackers can use video steganography to hide malware such as Trojans and viruses in video files. When these videos are transmitted to an office network and decoded or played in a system within the office network, the malware may be activated, causing the computer system within the network to be infected. This will not only endanger the security of the confidential network, but may also cause large-scale network paralysis or data destruction. 3) Backdoors and espionage: Steganography can be used to hide backdoor programs or spyware in videos. Once these programs are activated in a confidential network, they can provide attackers with remote access rights to continuously monitor or steal sensitive information within the confidential network, resulting in serious security vulnerabilities. Therefore, how to detect and clean video surveillance data transmitted across networks has become increasingly important. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method, system, electronic device and storage medium for processing surveillance video data, which are used to completely or at least partially solve the technical problems existing in the above-mentioned prior art.

[0006] In order to achieve the above object, an embodiment of the present invention provides a method for processing surveillance video data, comprising:

[0007] The signaling agent is used to send audio and video signals to the camera. When the camera receives the audio and video signals, the media stream agent is used to transmit the audio and video to obtain the audio and video.

[0008] Among them, when using the signaling agent to send audio and video signaling to the camera, the signaling legitimacy is checked for the audio and video signaling stream to discard non-compliant data;

[0009] In the process of using a media stream proxy to transmit audio and video to obtain audio and video, data cleaning is performed on the audio and video media stream, wherein the cleaning includes but is not limited to steganography detection.

[0010] Optionally, when using the signaling proxy to send audio and video signaling to the camera, a signaling legitimacy check is performed on the audio and video signaling stream to discard non-compliant data, including:

[0011] Send on-demand signaling;

[0012] The audio and video signaling agent receives on-demand signaling and performs signaling compliance checks, discarding non-compliant data to reduce the risk of introducing attack data and illegal data;

[0013] The audio and video signaling proxy receiving point will decode the on-demand signaling and match the payload content with the content filtering keywords of the management end. If a match is found, the on-demand signaling will be discarded;

[0014] The audio and video signaling proxy receiving point forwards the on-demand signaling to the video source, so that the video source starts streaming according to the media description information in the on-demand signaling after receiving the on-demand signaling.

[0015] Optionally, in the process of using a media stream proxy to transmit audio and video to obtain audio and video, before cleaning the audio and video media stream, the method for processing monitoring video data further includes: a general processing process of an audio and video media stream proxy:

[0016] The audio and video media stream proxy receives and parses the header information of the real-time transport protocol of the media stream data, and extracts key information. The load type value extracted by the audio and video media stream proxy must be consistent with the load value provided during signaling negotiation.

[0017] During the transmission of the same media stream, the consistency of the load type extracted from the media data is checked in real time, and whether the encoding format of the media data has changed and the source consistency are detected in real time. If the load type changes, it means that there is tampering or entrained data. If the encoding format or source changes, it is considered that there is tampering or entrained data, and non-key frames are dropped to blindly wash the audio and video media stream data.

[0018] Optionally, in the process of using a media stream proxy to transmit audio and video to obtain audio and video, a steganographic detection is performed on the audio and video media stream to clean the data of the sent audio and video, including:

[0019] Extracting characteristic data of the media stream data and classifying the characteristic data according to the transmission rate and the load size to obtain low-rate audio data and high-rate video data;

[0020] For low-rate audio data, the LSB steganalysis detection method is used for detection;

[0021] For high-rate video data, discrete cosine transform coefficient analysis method is used for steganalysis detection.

[0022] Optionally, for low-rate audio data, an LSB steganalysis detection method is used for detection, including:

[0023] Segmentation step: segmenting the low-rate audio data into pixels to obtain multiple pixel groups;

[0024] Positive flipping step: using the discriminant function to solve the corresponding real value for each pixel group, and performing positive flipping on each pixel group to solve the real value corresponding to each pixel group after the positive flipping;

[0025] The first comparison step: compare the real value corresponding to each pixel group after positive flipping with the real value corresponding to each pixel group before positive flipping. If the real value corresponding to each pixel group after positive flipping is greater than the real value corresponding to each pixel group before positive flipping, then classify each pixel group into R class; if less than, then classify into S class; if equal, then classify into U class;

[0026] Negative flipping step: negatively flip each pixel group and solve the real value corresponding to each pixel group after negative flipping;

[0027] The second comparison step: compare the real value corresponding to each pixel group after the negative flip with the real value corresponding to each pixel group before the negative flip. If the real value corresponding to each pixel group after the negative flip is greater than the real value corresponding to each pixel group before the negative flip, then classify each pixel group into the R class; if less than, then classify into the S class; if equal, then classify into the U class;

[0028] The low-rate audio data is flipped as a whole, and a segmentation step, a positive flipping step, a first comparison step, a negative flipping step, and a second comparison step are sequentially performed to obtain the numbers corresponding to the R class and the S class respectively, and the length of the embedded information is determined based on the number. If the length is greater than a preset threshold, it indicates that the low-rate audio data contains hidden information.

[0029] Optionally, the discriminant function formula is as follows:

[0030]

[0031] In the formula, represents the discrimination function, Represents n groups of low-rate audio data after pixel segmentation.

[0032] On the other hand, the present invention also provides a monitoring video data processing system applied to the monitoring video data processing method, comprising:

[0033] The video surveillance protocol proxy subsystem includes a signaling proxy module and a media stream proxy module. The signaling proxy module is used to receive, process, and forward signaling messages and perform compliance checks and content checks on the signaling; the media stream proxy module is used to receive, parse, and forward media streams;

[0034] The media stream proxy module includes a header parsing submodule, a general detection submodule, and a blind wash submodule; wherein the parsing submodule is used to parse the RTP header field to extract key information; the general detection submodule is used for load type consistency check, encoding format consistency check and source consistency check; the blind wash submodule is used to perform frame loss processing on non-key frames;

[0035] Audio and video data cleaning subsystem, including but not limited to audio LSB steganalysis detection and video DCT coefficient analysis detection, is used to implement the steganalysis detection function for media data;

[0036] The management subsystem is used for policy configuration and log management.

[0037] Optional, the management subsystem configuration mainly includes:

[0038] Access configuration: configure the IP information of devices in the non-trusted domain that are allowed to access;

[0039] Content filtering configuration: The user configures keywords to filter the signaling content. When the keywords are matched, the audio and video data transmission corresponding to the signaling is interrupted.

[0040] Camera control strategy configuration: configure whether to filter control signals for each task, and perform different strategy controls based on the authority of the management personnel;

[0041] Audio and video format blacklist and whitelist configuration: Configure the audio and video format blacklist and whitelist for each task, allowing audio and video traffic in preset formats to be transmitted across the network to filter out illegal data.

[0042] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for processing surveillance video data when executing the program.

[0043] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for processing surveillance video data are implemented.

[0044] Through the above technical solution, the real-time data cleaning function of the video terminal media data transmission is realized, and the accuracy of data cleaning is improved by using signaling data and media data linkage detection and independent steganography detection of audio and video data.

[0045] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0047] Figure 1 is a flowchart of an implementation method of a monitoring video data processing method provided by an embodiment of the present invention;

[0048] Figure 2 It is a flow chart of audio and video proxy signaling processing and transmission provided by an embodiment of the present invention;

[0049] Figure 3 This is a general processing flow chart of an audio and video media stream proxy provided by an embodiment of the present invention;

[0050] Figure 4 It is a flow chart of audio and video steganography checking provided by an embodiment of the present invention;

[0051] Figure 5 It is a structural schematic diagram of a monitoring data processing system applied to a monitoring video data processing method provided by an embodiment of the present invention;

[0052] Figure 6 It is a schematic diagram of a management subsystem configuration provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0054] See also Figure 1 As shown, it is a flowchart of an implementation method of a monitoring video data processing method provided by an embodiment of the present invention, including the following execution steps:

[0055] Step 100: Use a signaling agent to send an audio and video signal to the camera. When the camera receives the audio and video signal, use a media stream agent to transmit the audio and video to obtain the audio and video.

[0056] Step 101: When using a signaling agent to send audio and video signaling to a camera, a signaling legitimacy check is performed on the audio and video signaling stream to discard non-compliant data.

[0057] Specifically, when executing step 101, the following steps may be specifically performed:

[0058] S1010: Sending on-demand signaling.

[0059] S1011: The audio and video signaling agent receives the on-demand signaling and performs a signaling compliance check, discarding non-compliant data to reduce the risk of introducing attack data and illegal data.

[0060] S1012: The audio and video signaling proxy receiving point decodes the on-demand signaling and matches the payload content with the content filtering keywords of the management end. If a match is found, the on-demand signaling is discarded.

[0061] S1013: The audio and video signaling proxy receiving point forwards the on-demand signaling to the video source, so that the video source starts streaming according to the media description information in the on-demand signaling after receiving the on-demand signaling.

[0062] In some embodiments, see Figure 2 As shown, it is a flow chart of audio and video proxy signaling processing and transmission provided by an embodiment of the present invention, including a video on demand platform sending a video on demand signaling, a signaling proxy receiving and performing a compliance check, signaling content cleaning, a signaling proxy forwarding the video on demand signaling, and a video source receiving the video on demand signaling and pushing the stream.

[0063] Step 102: In the process of using the media stream proxy to transmit audio and video to obtain audio and video, data cleaning is performed on the audio and video media stream, wherein the data cleaning includes but is not limited to steganography detection.

[0064] In some implementations, before executing step 102, a general processing procedure for an audio and video media stream proxy is also executed:

[0065] The audio and video media stream proxy receives and parses the header information of the real-time transport protocol of the media stream data, and extracts key information. The load type value extracted by the audio and video media stream proxy must be consistent with the load value provided during signaling negotiation.

[0066] During the transmission of the same media stream, the consistency of the load type extracted from the media data is checked in real time, and whether the encoding format of the media data has changed and the source consistency are detected in real time. If the load type changes, it means that there is tampering or entrained data. If the encoding format or source changes, it is considered that there is tampering or entrained data, and non-key frames are dropped to blindly wash the audio and video media stream data.

[0067] In some embodiments, see Figure 3 As shown, a general processing flow chart of an audio and video media stream proxy provided by an embodiment of the present invention includes media stream reception and RTP header analysis, followed by load type characteristic check, load type consistency check, encoding format consistency check and source consistency check, data blind washing, and finally media stream forwarding.

[0068] Specifically, when executing step 102, the following steps may be specifically performed:

[0069] S1020: Extract characteristic data of the media stream data and classify the characteristic data according to the transmission rate and the load size to obtain low-rate audio data and high-rate video data.

[0070] S1021: For low-rate audio data, LSB steganography detection method is used for detection.

[0071] Specifically, when executing step S1021, the following steps may be specifically performed:

[0072] Segmentation step: segmenting the low-rate audio data into pixels to obtain multiple pixel groups;

[0073] Positive flipping step: using the discriminant function to solve the corresponding real value for each pixel group, and performing positive flipping on each pixel group to solve the real value corresponding to each pixel group after the positive flipping;

[0074] The positive flip rule is: if the pixel value is even, its value is increased by 1; if the pixel value is odd, its value is decreased by 1.

[0075] The first comparison step: compare the real value corresponding to each pixel group after positive flipping with the real value corresponding to each pixel group before positive flipping. If the real value corresponding to each pixel group after positive flipping is greater than the real value corresponding to each pixel group before positive flipping, then classify each pixel group into R class; if less than, then classify into S class; if equal, then classify into U class;

[0076] Negative flipping step: negatively flip each pixel group and solve the real value corresponding to each pixel group after negative flipping;

[0077] The negative flip rule is: if the pixel value is an even number, subtract 1; if it is an odd number, add 1.

[0078] The second comparison step: compare the real value corresponding to each pixel group after the negative flip with the real value corresponding to each pixel group before the negative flip. If the real value corresponding to each pixel group after the negative flip is greater than the real value corresponding to each pixel group before the negative flip, then classify each pixel group into the R class; if less than, then classify into the S class; if equal, then classify into the U class;

[0079] The low-rate audio data is flipped as a whole, and a segmentation step, a positive flipping step, a first comparison step, a negative flipping step, and a second comparison step are sequentially performed to obtain the numbers corresponding to the R class and the S class respectively, and the length of the embedded information is determined based on the number. If the length is greater than a preset threshold, it indicates that the low-rate audio data contains hidden information.

[0080] The overall flipping rule is that if the pixel value is an even number, add 1, and if it is an odd number, subtract 1.

[0081] Specifically, the discriminant function formula is as follows:

[0082]

[0083] In the formula, represents the discrimination function, Represents n groups of low-rate audio data after pixel segmentation.

[0084] S1022: For high-rate video data, a discrete cosine transform coefficient analysis method is used to perform steganalysis detection.

[0085] In some embodiments, see Figure 4As shown, it is a flow chart of audio and video steganography inspection provided by an embodiment of the present invention. Different sliding time windows will be set according to different audio and video encoding formats. For audio streams with slower transmission rates, every 200 packets are a time window. After 200 packets, the basic feature data is composed of a feature object and sent to the corresponding matching model for matching. For video streams with faster transmission rates, every 300 packets are a time window. Steganography detection model matching. Differences in transmission rate and load size usually have different data steganography methods and rules. Sending audio streams and video streams to different detection models can achieve better detection results. The audio and video encodings commonly used in the field of video surveillance are relatively fixed, and are more suitable for matching and detecting different encoding types using different detection models. This system adopts the LSB steganography detection method for audio data with relatively low rates, and adopts a fusion method based on RS and histogram frequency domain moment features for detection. For the high-speed green video coding format H.264 / H.265, the DCT coefficient analysis method is used for steganalysis detection. DCT (discrete cosine transform) converts the video or image from the time domain to the frequency domain, and detects the steganalysis information by analyzing the anomalies of the DCT coefficients (especially the medium and high frequency coefficients).

[0086] Step 103: Fuse the video sources that have been subjected to signaling legitimacy detection and steganography detection to obtain target surveillance video data.

[0087] Through the above technical solution, the real-time data cleaning function of the video terminal media data transmission is realized, and the accuracy of data cleaning is improved by using signaling data and media data linkage detection and independent steganography detection of audio and video data.

[0088] See also Figure 5 FIG. 1 is a schematic diagram of a structure of a monitoring data processing system for a monitoring video data processing method provided by an embodiment of the present invention, including:

[0089] The video surveillance protocol proxy subsystem includes a signaling proxy module and a media stream proxy module. The signaling proxy module is used to receive, process, and forward signaling messages and perform compliance checks and content checks on the signaling; the media stream proxy module is used to receive, parse, and forward media streams;

[0090] The media stream proxy module includes a header parsing submodule, a general detection submodule, and a blind wash submodule; wherein the parsing submodule is used to parse the RTP header field to extract key information; the general detection submodule is used for load type consistency check, encoding format consistency check and source consistency check; the blind wash submodule is used to perform frame loss processing on non-key frames;

[0091] The audio and video data cleaning subsystem includes, but is not limited to, feature extraction, audio LSB steganalysis detection, and video DCT coefficient analysis detection, which is used to implement the steganalysis detection function for media data;

[0092] The management subsystem (i.e., management platform configuration and video-on-demand platform) is used for policy configuration delivery and log management.

[0093] In some embodiments, see Figure 6 As shown in the figure, the management subsystem configuration mainly includes:

[0094] Access configuration: configure the IP information of devices in the non-trusted domain that are allowed to access;

[0095] Content filtering configuration: The user configures keywords to filter the signaling content. When the keywords are matched, the audio and video data transmission corresponding to the signaling is interrupted.

[0096] Camera control strategy configuration: configure whether to filter control signals for each task, and perform different strategy controls based on the authority of the management personnel;

[0097] Audio and video format blacklist and whitelist configuration: Configure the audio and video format blacklist and whitelist for each task, allowing audio and video traffic in preset formats to be transmitted across the network to filter out illegal data.

[0098] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for processing surveillance video data described in any one of the above embodiments when executing the program.

[0099] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for processing surveillance video data described in any of the above embodiments are implemented.

[0100] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0101] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0108] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for processing surveillance video data, characterized in that: include: The signaling agent is used to send audio and video signals to the camera. When the camera receives the audio and video signals, the media stream agent is used to transmit the audio and video to obtain the audio and video. Among them, when using the signaling agent to send audio and video signaling to the camera, the signaling legitimacy is checked for the audio and video signaling stream to discard non-compliant data; In the process of using a media stream proxy to transmit audio and video to obtain audio and video, data cleaning is performed on the audio and video media stream, wherein the data cleaning includes but is not limited to steganalysis detection; In the process of using the signaling proxy to send audio and video signaling to the camera, the signaling legitimacy is checked for the audio and video signaling stream to discard non-compliant data, including: Send on-demand signaling; The audio and video signaling agent receives on-demand signaling and performs signaling compliance checks, discarding non-compliant data to reduce the risk of introducing attack data and illegal data; The audio and video signaling proxy receiving point will decode the on-demand signaling and match the payload content with the content filtering keywords of the management end. If a match is found, the on-demand signaling will be discarded; The audio and video signaling proxy receiving point forwards the on-demand signaling to the video source, so that the video source starts streaming according to the media description information in the on-demand signaling after receiving the on-demand signaling; Wherein, in the process of using the media stream proxy to transmit audio and video to obtain audio and video, before data cleaning is performed on the audio and video media stream, the method for processing monitoring video data also includes: a general processing process of the media stream proxy: The media stream proxy receives and parses the header information of the real-time transport protocol of the media stream data and extracts key information. The load type value extracted by the media stream proxy must be consistent with the load value provided during signaling negotiation. During the transmission of the same media stream, the consistency of the load type extracted from the media data is checked in real time, and whether the encoding format of the media data has changed and the source consistency are detected in real time. If the load type changes, it means that there is tampering or entrained data. If the encoding format or source changes, it is considered that there is tampering or entrained data, and non-key frames are dropped to blindly wash the audio and video media stream data.

2. The method for processing surveillance video data according to claim 1, characterized in that: In the process of using the media stream proxy to transmit audio and video to obtain audio and video, steganography detection is performed on the audio and video media stream to clean the data of the sent audio and video, including: Extracting characteristic data of the media stream data and classifying the characteristic data according to the transmission rate and the load size to obtain low-rate audio data and high-rate video data; For low-rate audio data, the LSB steganalysis detection method is used for detection; For high-rate video data, discrete cosine transform coefficient analysis method is used for steganalysis detection.

3. The method for processing surveillance video data according to claim 2, characterized in that: For low-rate audio data, the LSB steganalysis detection method is used for detection, including: Segmentation step: segmenting the low-rate audio data into pixels to obtain multiple pixel groups; Positive flipping step: using the discriminant function to solve the corresponding real value for each pixel group, and performing positive flipping on each pixel group to solve the real value corresponding to each pixel group after the positive flipping; The first comparison step: compare the real value corresponding to each pixel group after positive flipping with the real value corresponding to each pixel group before positive flipping. If the real value corresponding to each pixel group after positive flipping is greater than the real value corresponding to each pixel group before positive flipping, then classify each pixel group into R class; if less than, then classify into S class; if equal, then classify into U class; Negative flipping step: negatively flip each pixel group and solve the real value corresponding to each pixel group after negative flipping; The second comparison step: compare the real value corresponding to each pixel group after the negative flip with the real value corresponding to each pixel group before the negative flip. If the real value corresponding to each pixel group after the negative flip is greater than the real value corresponding to each pixel group before the negative flip, then classify each pixel group into the R class; if less than, then classify into the S class; if equal, then classify into the U class; The low-rate audio data is flipped as a whole, and a segmentation step, a positive flipping step, a first comparison step, a negative flipping step, and a second comparison step are sequentially performed to obtain the numbers corresponding to the R class and the S class respectively, and the length of the embedded information is determined based on the number. If the length is greater than a preset threshold, it indicates that the low-rate audio data contains hidden information.

4. The method for processing surveillance video data according to claim 3, characterized in that: The discriminant function formula is as follows: In the formula, represents the discrimination function, Represents n groups of low-rate audio data after pixel segmentation.

5. A monitoring video data processing system applied to the monitoring video data processing method according to any one of claims 1 to 4, characterized in that: include: The video surveillance protocol proxy subsystem includes a signaling proxy module and a media stream proxy module. The signaling proxy module is used to receive, process, and forward signaling messages and perform compliance checks and content checks on the signaling; the media stream proxy module is used to receive, parse, and forward media streams; The media stream proxy module includes a header parsing submodule, a general detection submodule, and a blind wash submodule; wherein the parsing submodule is used to parse the RTP header field to extract key information; the general detection submodule is used for load type consistency check, encoding format consistency check and source consistency check; the blind wash submodule is used to perform frame loss processing on non-key frames; Audio and video data cleaning subsystem, including but not limited to audio LSB steganalysis detection and video DCT coefficient analysis detection, is used to implement the steganalysis detection function for media data; The management subsystem is used for policy configuration and log management.

6. The monitoring video data processing system according to claim 5, characterized in that: The management subsystem configuration mainly includes: Access configuration: configure the IP information of devices in the non-trusted domain that are allowed to access; Content filtering configuration: The user configures keywords to filter the signaling content. When the keywords are matched, the audio and video data transmission corresponding to the signaling is interrupted. Camera control strategy configuration: configure whether to filter control signals for each task, and perform different strategy controls based on the authority of the management personnel; Audio and video format blacklist and whitelist configuration: Configure the audio and video format blacklist and whitelist for each task, allowing audio and video traffic in preset formats to be transmitted across the network to filter out illegal data.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for processing surveillance video data as described in any one of claims 1 to 4 are implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for processing surveillance video data as described in any one of claims 1 to 4 are implemented.

Images