Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Violation behavior evidence collection system and method in video identification

A technology of video recognition and acquisition system, which is applied in the field of generating evidence of violations of regulations, and can solve problems such as video caching

Pending Publication Date: 2020-10-30
XI AN MIKESI INTELLIGENT TECH CO LTD
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] A. Violations may occur in any section of the video, but due to capacity limitations or performance requirements, it is impossible to cache the entire video. How to support the generation of video evidence of arbitrary violations within a limited capacity;

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
  • Violation behavior evidence collection system and method in video identification
  • Violation behavior evidence collection system and method in video identification
  • Violation behavior evidence collection system and method in video identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Taking smoking in a no-smoking area as an example to illustrate the collection of video evidence for single violations.

[0056] Smoking detection is generally detected by means of deep learning. The method is to collect enough smoking videos of different people, different scenes, different angles, and different lights, etc., and mark the part with a cigarette in the mouth as smoking. Make these pictures It is a deep learning data set, which is used to train the target detection model. The method of target detection can use methods such as YOLO / SSD, which can be found in public information. The trained target detection model can be used to detect violations such as "smoking in no-smoking areas".

[0057] Assume that there is a camera aimed at a no-smoking area to monitor whether someone is smoking in the no-smoking area, and the video stream obtained by the camera is connected to the illegal behavior detection module and the video cache module through the network. The...

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 discloses a violation behavior evidence collection system and method in video identification. The method comprises: firstly, reading a video stream, segmenting the video stream into video clip files with fixed lengths, storing the video clip files, tracking and detecting violation behaviors in a video image, and recording video frame numbers at the starting and ending moments of theviolation behaviors and position information of the violation behaviors in video frames; obtaining a video clip file list corresponding to the violation behavior according to the video frame numbers at the starting moment and the ending moment of the violation behavior, and creating a video evidence generation task; periodically checking whether all video clip files in the video evidence generation task are generated or not; and when all the video clip files in the video evidence generation task are generated, splicing the video clip files to generate a video evidence file.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to the generation of illegal behavior evidence in video recognition, which is used as the basis for subsequent illegal processing. Background technique [0002] During production operations in construction, petroleum, coal, electric power and other industries, in order to avoid safety accidents, operators are required to operate in accordance with safety production operation regulations. If violations occur, the violations need to be recorded, and subsequent potential Different degrees of harm are imposed. [0003] The supervision of traditional production operations relies on on-site inspection and supervision by supervisors. With the development of monitoring systems in recent years, many production sites have installed monitoring systems. On-site operation videos can be collected and transmitted to the monitoring center through cameras, and the personnel in the monitoring c...

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): G06K9/00G08G1/017
CPCG08G1/0175G06V20/42G06V20/40G06V20/44
Inventor 邓少冬
Owner XI AN MIKESI INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products