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

A method for detecting violent behavior in an elevator car

A technology for elevator cars and detection methods, applied in image data processing, instruments, calculations, etc., can solve problems such as unsatisfactory efficiency, failure to promote elevator systems, and detection methods that cannot be practically applied, and achieve good robustness , the effect of high detection rate

Active Publication Date: 2016-04-27
JIANGNAN UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional video surveillance cannot automatically detect violent behavior, and requires manual participation. The efficiency is unsatisfactory. Therefore, anti-violence monitoring in elevators based on dynamic image understanding has become one of the current urgent needs.
[0003] However, at present, most studies are based on statistical features to detect abnormal behavior, which requires the establishment of a training and learning mechanism, and the establishment of this learning mechanism requires more training samples, so that the existing statistics-based Feature detection methods cannot be practically applied
In addition, even if a multi-sample database can be established, it cannot be promoted in the actual elevator system due to the high cost and workload of collecting more training samples.

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
  • A method for detecting violent behavior in an elevator car
  • A method for detecting violent behavior in an elevator car
  • A method for detecting violent behavior in an elevator car

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described below in conjunction with drawings and embodiments.

[0015] Such as figure 1 As shown, a method for detecting violence in an elevator car includes the following steps:

[0016] 1) The mixed Gaussian model extracts the moving foreground target. The change of each pixel of the image in the time domain is simulated by K multidimensional Gaussian distributions, {X 1 , X 2 ,...,X t} represents the observation value sequence of the pixel point P(x, y), and the value of the pixel point at time t is X t The probability of

[0017] P ( X t ) = Σ i = 1 K w i , t N ( X t , ...

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 a method of detecting violence in an elevator car. The method includes: extracting motion foreground by a Gaussian mixture model and marking a motion area; detecting angular points in the motion area by Harris operators; calculating optical flow information of the angular points in the motion area by a pyramid Lucas-Kanade optical flow algorithm; counting an entropy of the optical flow information of angular points, comparing the entropy to a set threshold, and judging existence of abnormal behaviors. Through the application of the method, the problem that current elevator monitoring relies on manual distinguishing of violence is well solved; the method has good practicability and high detection rate.

Description

technical field [0001] The invention relates to the field of behavior recognition, in particular to a method for detecting violent behavior in an elevator car. Background technique [0002] With the development of society, there are more and more high-rise buildings, and the use of elevators is becoming more and more common. At the same time, due to the relatively closed nature of elevators, violence in elevator cars is increasing, and its safety issues have received widespread attention. Traditional video surveillance cannot automatically detect violent behavior, and requires manual participation. The efficiency is not satisfactory. Therefore, anti-violence monitoring in elevators based on dynamic image understanding has become one of the current urgent needs. [0003] However, at present, most studies are based on statistical features to detect abnormal behavior, which requires the establishment of a training and learning mechanism, and the establishment of this learning m...

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 Patents(China)
IPC IPC(8): G06T7/20
Inventor 王呈柳絮青王宪宋书林秦磊
Owner JIANGNAN UNIV