Unlock instant, AI-driven research and patent intelligence for your innovation.

Underground personnel running abnormal behavior detection method based on trajectory analysis

A technology of trajectory analysis and detection methods, applied in the fields of instruments, character and pattern recognition, computer parts, etc.

Active Publication Date: 2020-06-16
华夏天信物联科技有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The invention provides a method for detecting abnormal running behavior of underground personnel based on trajectory analysis, and solves the problem of detecting abnormal running behavior of underground personnel by using computer vision technology to analyze the monitoring camera in real time

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
  • Underground personnel running abnormal behavior detection method based on trajectory analysis
  • Underground personnel running abnormal behavior detection method based on trajectory analysis
  • Underground personnel running abnormal behavior detection method based on trajectory analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The embodiments of the present invention are given below in conjunction with the drawings to describe the technical implementation of the present invention in detail.

[0039] Such as figure 1 As shown, the present invention is based on monocular vision (based on the video data of a camera), decodes the video stream data from the camera, reads the single frame image of the video frame by frame, and extracts the tracking target from the current image when the tracking target addition condition is met. Otherwise, update the target trajectory on the current image, perform statistical analysis on the target trajectory, and determine whether there is a person running according to the statistical characteristics of the trajectory. The process mainly involves four main steps: adding conditions for tracking targets, extracting tracking targets, updating target trajectories, and judging track running behavior.

[0040] 1. Add conditions for tracking targets. Since the pixel ch...

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 provides an underground personnel running abnormal behavior detection method based on trajectory analysis. The monitoring camera is analyzed in real time by adopting a computer vision technology; abnormal running behaviors of underground personnel are detected; according to the method, the moving target is extracted and tracked in real time through ORB image key point detection and Lucas-Kanade optical flow tracking technologies, statistical analysis is performed on the moving trajectory of the target, and the speed and trajectory fluctuation characteristics of the moving targetare extracted, so that the running behavior of personnel can be effectively judged. According to the method, the video does not need to be marked frame by frame, only a small amount of video data containing normal driving or pedestrians is needed to run the algorithm to determine the regularization coefficient, and deployment is quick and convenient.

Description

technical field [0001] The invention relates to a method for detecting human behavior, in particular to a method for detecting abnormal running behavior of underground personnel based on trajectory analysis. Background technique [0002] Underground personnel running in densely populated places such as driving and pedestrian passages and waiting passages may cause traffic accidents and pose a greater safety hazard. At present, the discovery and monitoring of underground running violations are all realized manually, and there is no application case solved by artificial intelligence technology. Existing technologies for identifying violations through computer vision technology mostly use supervised gesture recognition technology, behavior recognition technology, etc., rely on a large amount of video annotation data, and have high requirements for computer performance. Contents of the invention [0003] The invention provides a method for detecting abnormal running behavior ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/25G06V20/48G06V20/52
Inventor 黄鑫王静宜瞿开毅
Owner 华夏天信物联科技有限公司