CN210839843U - A warehouse video surveillance system based on edge computing - Google Patents

Abstract

The utility model discloses a warehouse video monitoring system based on edge computing, comprising a video monitoring system front end, an edge node unit, an intelligent storage unit, a network transmission unit, a terminal display unit and a power supply. The utility model constructs a video preprocessing technology based on edge computing, removes redundant information of video images, and makes part or all of the video analysis migrate to the edge, thereby reducing the computing, storage and network bandwidth requirements for the cloud center, and improving the analysis of video images. s efficiency.

Description

A warehouse video surveillance system based on edge computing

technical field

The utility model relates to the technical field of video surveillance, in particular to a warehouse video surveillance system based on edge computing.

Background technique

Video surveillance security systems for public security are mainly used to deal with public security issues. The existence of warehouse video surveillance systems is mainly to ensure the safety of important goods. Traditional warehouse video surveillance systems have shortcomings such as fewer built-in computing resources for front-end cameras, larger data volumes, higher transmission bandwidth delays, and limited computing capabilities of cloud computing center servers. Therefore, it is necessary to build a new type of warehouse video surveillance system based on edge computing. .

SUMMARY OF THE INVENTION

The utility model discloses a warehouse video monitoring system based on edge computing, which aims to solve the problem that the existing warehouse video monitoring system has fewer built-in computing resources of front-end cameras, larger data volume, higher transmission bandwidth delay, and cloud computing center server computing capability. limited and other issues.

In order to achieve the above object, the technical scheme adopted by the present utility model:

A warehouse video surveillance system based on edge computing, comprising a video surveillance system front end, an edge node unit, an intelligent storage unit, a network transmission unit and a terminal display unit connected in sequence;

The front end of the video surveillance system includes a camera and a video converter, and the video converter converts the analog video signal collected by the camera into a digital signal, and transmits the digital signal to the edge node unit;

The edge node unit has a high-performance DSP chip, and the high-performance DSP chip is used to screen and process the digital signal converted from the video converter in the front end of the video surveillance system, and compress the screened video;

The intelligent storage unit is used for buffering the compressed video;

The network transmission unit is configured to send the buffered video to the terminal display unit in time;

The terminal display unit is configured to receive the video stream sent by the network transmission unit, display the video, and notify the supervisor of the terminal control terminal.

Preferably, the system further includes a power source, which is connected to other units through wires and supplies power.

Preferably, the system is based on the video preprocessing technology of the edge node unit to remove redundant information of video images, so that part or all of the video analysis is migrated to the edge, thereby reducing the computing, storage and network bandwidth requirements for the cloud center, improving video Efficiency of Image Analysis.

Preferably, according to the processing results of the high-performance DSP chip, the video data is adjusted in real time, and only the changed video frames are retained, which not only reduces the storage of invalid videos, reduces the storage space, but also maximizes the storage of "in-the-fact" evidence video data, improving the video quality. Data storage space utilization.

Compared with the prior art, the beneficial effects of the present utility model are:

1. The present utility model constructs a video preprocessing technology based on edge computing, removes redundant information of video images, and makes part or all of video analysis migrate to the edge, thereby reducing the computing, storage and network bandwidth requirements of the cloud center, and improving video quality. Efficiency of image analysis;

2. According to the DSP processing results, adjust the video data in real time, and only keep the changed video frames, which not only reduces the storage of invalid videos, reduces the storage space, but also maximizes the storage of "in-the-fact" evidence video data and improves the utilization of video data storage space. Rate.

Description of drawings

The accompanying drawings constituting a part of the present application are used to provide further understanding of the present invention, and the schematic embodiments of the present invention and descriptions thereof are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

Fig. 1 is the structural representation of the utility model;

Figure 2 is a flow chart of the utility model use.

Detailed ways

It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present utility model will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only The embodiments are part of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of the present application.

As shown in Figure 1, a warehouse video surveillance system based on edge computing includes a video surveillance system front end 1, an edge node unit 2, an intelligent storage unit 3, a network transmission unit 4 and a terminal display unit 5 that are connected in sequence;

The front end 1 of the video surveillance system includes a camera 11 and a video converter 12, and the video converter 12 converts the analog video signal collected by the camera 11 into a digital signal, and transmits the digital signal to the edge node unit 2;

The edge node unit 2 has a high-performance DSP chip, and the high-performance DSP chip is used to screen and process the digital signal converted from the video converter 12 in the front end 1 of the video surveillance system, and to process the screened video. compression;

By migrating the analysis and processing tasks to the edge node unit 2, on the premise of ensuring data reliability, preprocessing a large amount of real-time edge data generated by the front end 1 of the video surveillance system in a short period of time, analyzing the characteristics of the video content in real time, and dynamically adjusting the video Stream parameters, reduce redundant video frames, reduce energy consumption of storage nodes, thereby reducing video streaming overhead and reducing the computational cost of video target recognition; in addition, in order to reduce the uploaded video data, only the changed video frames are stored. , adjust the video data in real time, not only reduce the storage of invalid video, reduce the storage space, but also reliably store the evidence video data on the warehouse site, enhance the credibility of the evidence information, and improve the storage space utilization of video data.

The intelligent storage unit 3 is used to cache the compressed video;

The network transmission unit 4 is used to send the cached video to the terminal display unit 5 in time;

The terminal display unit 5 is configured to receive the video stream sent by the network transmission unit 4, display the video, and notify the supervisor of the terminal control terminal.

The system also includes a power source 6, which is connected to and powered by wires to other units.

According to the processing results of the high-performance DSP chip, the video data is adjusted in real time, and only the changed video frames are retained, which not only reduces the storage of invalid video, reduces the storage space, but also maximizes the storage of "in-the-fact" evidence video data and improves the storage space of video data. utilization.

As shown in Figure 2, the use flow of the present utility model:

The front end 1 of the video surveillance system is the input end of the system. When the system obtains valid video (that is, the video that detects the intrusion of a moving target), the video converter 12 is used to realize the conversion of analog video signals to digital signals, and then enter the high-performance system. DSP chip processing, the algorithm processed in the high-performance DSP chip is cached in the intelligent storage unit 3, and the basis for judging whether the warehouse video is saved is based on the improved algorithm combining the two-frame difference method and the projection method, that is, judging the multi-angle of the current video frame. Compared with the multi-angle projection of the previous frame, whether the projection has changed, judge the difference between the two grayscale projection images, if it is 0, it will not be saved; if it is not 0, it will be cached in the data storage unit. Real-time adjustment of video data in the process of preprocessing can not only reduce the storage of invalid videos, reduce storage space, but also store evidence video data on the warehouse site, enhance the credibility of evidence information, and send the cached video to the terminal. By migrating the analysis and processing tasks to the edge node unit 2, on the premise of ensuring data reliability, a large amount of real-time edge data generated by the video capture terminal in a short period of time is preprocessed, which improves the video analysis speed and reduces the processing and transmission. The delay ensures the real-time performance of the monitoring video stream.

Compared with the traditional artificial monitoring video model, the present utility model proposes to add a moving target detection algorithm to the camera 11 to process the collected original video data, remove redundant information, and analyze the behavior in the video, so that only the most valuable video data is processed. The data is transmitted to the terminal display unit 5. The improved frame difference method is used to detect moving objects, which is more reliable than human detection, and only when a moving object is detected in the monitoring screen will it be stored, which not only reduces the storage of invalid videos, but also stores evidence videos on the warehouse site. data, enhance the credibility of evidence information, improve the storage space utilization of video data, and save a lot of storage space.

Compared with the cloud computing model, the video transmission and processing overhead is reduced. Considering the impact of transmission and processing delays, the system first selects valid video frames for uploading. The processed video is compressed and encoded to greatly reduce the space occupied, thereby improving the real-time performance and resource utilization of video streams.

The above descriptions are only preferred embodiments of the present utility model, and are not intended to limit the present utility model. For those skilled in the art, the present utility model may have various modifications and changes. Any modification, equivalent replacement, improvement, component splitting or combination, etc. made within the spirit and principle of the present utility model shall be included within the protection scope of the present utility model.

Claims (3)

1. a warehouse video surveillance system based on edge computing, is characterized in that, comprises the video surveillance system front end, edge node unit, intelligent storage unit, network transmission unit and terminal display unit connected in sequence; The front end of the video surveillance system includes a camera and a video converter, and the video converter converts the analog video signal collected by the camera into a digital signal, and transmits the digital signal to the edge node unit; The edge node unit has a high-performance DSP chip, and the high-performance DSP chip is used to screen and process the digital signal converted from the video converter in the front end of the video surveillance system, and compress the screened video; The intelligent storage unit is used for buffering the compressed video; The network transmission unit is configured to send the buffered video to the terminal display unit in time; The terminal display unit is configured to receive the video stream sent by the network transmission unit, display the video, and notify the supervisor of the terminal control terminal. 2. A warehouse video surveillance system based on edge computing according to claim 1, characterized in that, the system further comprises a power supply, and the power supply is respectively connected with the front end of the video surveillance system, the edge node unit, The intelligent storage unit, the network transmission unit and the terminal display unit are connected and powered. 3. a kind of warehouse video surveillance system based on edge computing according to claim 2, is characterized in that, this system is based on the video preprocessing technology of edge node unit, removes video image redundant information, makes part or all video analysis migration To the edge, thereby reducing the computing, storage and network bandwidth requirements of the cloud center, and improving the efficiency of video image analysis.

Images