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

Pedestrian Abnormal Behavior Detection Method

A pedestrian and abnormal technology, applied in image analysis, instrumentation, computing, etc., can solve problems such as complex process and low efficiency, and achieve the effect of improving efficiency, avoiding the process of model learning, and improving accuracy

Active Publication Date: 2020-05-19
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] It can be seen that most of the current abnormal behavior detection methods of pedestrians need to establish a model, and then carry out model learning, which is inefficient and complicated

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
  • Pedestrian Abnormal Behavior Detection Method
  • Pedestrian Abnormal Behavior Detection Method
  • Pedestrian Abnormal Behavior Detection Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Step S22: Calculate the number of blocks included in the tracked group within a period of time, detect whether an abnormality occurs according to the threshold and the weight, and update the detection threshold.

[0039] In the process of group tracking, the group structure of the group will dynamically change with the change of the number of people in the group, and the number of blocks contained in the group composed of blocks will also change accordingly. Therefore, the abnormal behavior of the group, which is a large change in the population of the group, can be detected by the number of blocks contained in the group. The specific process is as follows:

[0040] Since the change of the group structure in adjacent frames is very small, and the number of blocks contained in the group is relatively stable, every m frames, the number of blocks contained in the tracked group is calculated by the function f. Wherein, the function f may be the variance of the blocks included i...

Embodiment 2

[0042] Step S23: According to the group coordination value of each frame of the tracked group, calculate the group coordination value of the group within a certain period of time, and judge whether abnormal behavior occurs according to a preset threshold. Specific steps are as follows:

[0043] Every interval d frames, the function φ is used to calculate the group cooperativity value of the group in the d frame. In specific calculations, the function φ can calculate the average or variance of the group cooperativity value of the group in the d frame. Then make the difference with the φ value of the previous d frame, when the difference is greater than the preset threshold T, that is φ n -φ n-1 > At T, it is judged that an abnormality has occurred. If the difference is less than the preset threshold T, the above process is repeated until the group tracking ends. If the difference is still less than the preset threshold until the entire tracking process of the group is completed, ...

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 a pedestrian's abnormal behavior detection method comprising the steps as follows: estimating the pedestrian density in a video frame, and classifying the video frame as a high- and medium-density scene or a low-density scene according to the obtained pedestrian density; if the video scene is a high- and medium-density scene, grouping-tracking the pedestrians in the video frame and detecting whether there is an abnormal behavior using a group tracking method based on group structure dynamic evolution; and if the video scene is a low-density scene, tracking a target pedestrian in the video frame and detecting whether there is an abnormal behavior using a trajectory segment correlation method. The method is simple and convenient, avoids a complex model learning process, is of strong adaptability, and enables the monitoring staff to find the cause of a security problem more efficiently and saves manpower.

Description

Technical field [0001] The invention relates to a method for detecting abnormal pedestrian behavior. Background technique [0002] In recent years, as security issues have received increasing attention from the society, abnormal behavior detection in videos has become more and more important. Inconsistent with the behavior of surrounding pedestrians, there are behaviors of wandering or staying, and these behaviors may cause some safety issues. By analyzing the surveillance video, and then determining some abnormal behaviors that cause security problems, a large amount of information that is useless for security in the surveillance video can be filtered out, saving a lot of manpower. [0003] At present, due to the large size and density of the crowd, the abnormal behavior of the group is mostly studied from a macro perspective, that is, the group is treated as a whole. The main steps are as follows: detecting and tracking video moving targets; conducting crowd monitoring accordin...

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): G06K9/00G06T7/246
Inventor 董露李娜冯良炳
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI