Box abnormal state recognition method based on computer vision

A technology of computer vision and abnormal state, applied in computer parts, computing, neural learning methods, etc., can solve problems such as inability to intelligently recognize scenes, low work efficiency, and easy damage to door magnetic components, so as to ensure richness of samples and optimization Samples, the effect of improving the training effect

Pending Publication Date: 2022-05-03
中煤科工集团重庆智慧城市科技研究院有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The common solution for monitoring abnormal door opening at home and abroad is to use door magnetic sensors. This monitoring solution can only realize the monitoring of the opening and closing state of the cabinet door, and cannot realize real-time analysis of the door opening scene, which has great limitations.
For example, the cabinet may not have the conditions for door sensor installation, or the door sensor data cannot be uploaded to the remote control center; the scene cannot be intelligently identified, and it is impossible to identify whether it is opened normally or abnormally; the door sensor components are easily damaged and the box cannot be monitored normally. open the door, etc.
[0004] In other solutions, video equipment linkage will be carried out, and video surveillance equipment will be installed to monitor the cabinet 24 hours a day. When the door magnetic sensor detects that the cabinet is abnormally opened, an alarm message will be sent, and then the management personnel will open the corresponding video surveillance. The device browses or plays back historical video data in real time, but this monitoring method requires manual processing, and the work efficiency is low

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Box abnormal state recognition method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Such as figure 1 As shown, the method for identifying an abnormal state of a box based on computer vision in this embodiment includes the following steps:

[0038] S1. Obtain and decode video data in a preset format. In this embodiment, the preset format is the H.264 format, which is decoded by FFMpeg. In order to reduce the volume of the video and reduce the bandwidth consumption during transmission, the video will be encoded and compressed to reduce the volume. In the H.264 format, the encoding algorithm is intra-frame compression and inter-frame compression. Intra-frame compression is an algorithm for generating I frames, and inter-frame compression is an algorithm for generating B frames and P frames. Among them, I frames are key frames, and P The information recorded in a frame is the difference between this frame and a previous key frame (or P frame), and the B frame is a two-way difference frame, and the recorded information is the difference between this frame...

Embodiment 2

[0046] The difference between this embodiment and Embodiment 1 is that in S5 of this embodiment, it is also judged by the face recognition module whether there is a person in the monitoring area; when there is a person in the monitoring area, face recognition is performed to determine whether the person is on record If it has not been filed, mark the corresponding video data as high-priority video data, and if it has been filed, mark the corresponding video data as low-priority video data. During frame processing, the high-priority video data corresponding to the camera in the preset area is prioritized for frame processing.

[0047]When there is no person in the monitoring area, the possibility of abnormal opening of the box door is small. Every preset time, the pictures are extracted and input into the neural network model for judgment, instead of judging the pictures in real time, which can reduce the neural network. Network models deal with stress. By collecting the face ...

Embodiment 3

[0049] The difference between this embodiment and Embodiment 1 is that in S5 in this embodiment, when there is no person in the monitoring area, the pictures are extracted every preset time, and the pictures are input into the trained neural network model for judgment. In this embodiment, one picture is extracted.

[0050] When there are people in the monitoring area, the number of preset pictures input to the neural network model is determined according to the high priority video data and the low priority video data, and the pictures corresponding to the high priority video data are input into the neural network model for judgment. Wherein, the number of preset pictures corresponding to high-priority video data is greater than the number of preset pictures corresponding to low-priority video data. In this embodiment, when the analysis module inputs pictures into the neural network model, it extracts a preset number of pictures at intervals and inputs them into the neural netw...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of video monitoring, and particularly discloses a box abnormal state recognition method based on computer vision, which comprises the following steps: S1, acquiring video data in a preset format and decoding; the method comprises the following steps: S1, decoding video data, S2, framing the decoded video data to generate a plurality of pictures, S3, preprocessing the pictures, classifying and marking, and constructing a training picture set; the marks comprise door opening and door non-opening; s4, inputting the training picture set into the neural network model for training; s5, performing judgment by using the trained neural network model, and outputting a judgment result; and S6, when the judgment result is that the door is opened, judging whether the door is opened abnormally based on the operation log, and if yes, generating alarm information. According to the technical scheme, abnormal door opening can be automatically recognized.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a computer vision-based identification method for an abnormal state of a box. Background technique [0002] In the construction of smart cities, ordinary personnel are not allowed to enter some dangerous areas and important places, such as box-type transformer stations with high-voltage electricity, computer rooms where important equipment is deployed, etc., in order to avoid accidents caused by abnormal opening of the box Personnel safety accidents or loss of public equipment require real-time monitoring and alarming of the abnormal door opening status of the cabinet. [0003] The commonly used solution for monitoring abnormal door opening at home and abroad is to use door magnetic sensors. This monitoring solution can only monitor the opening and closing status of the box door, but cannot realize real-time analysis of the door opening scene, which has great limitations...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06V20/52G06V40/16G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 戴书球孙维孙中光张建鑫谭一川梁帅韩麟之文学峰冉昆鹏于乐泉
Owner 中煤科工集团重庆智慧城市科技研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap