Method and device for detecting crowd gathering expressed in convex hull based on angular points

A corner detection and crowd technology, which is applied to instruments, computing, character and pattern recognition, etc., can solve the problems of false alarms of single-person opposite pedestrians, crowd shape does not have a fixed shape, high complexity, etc., and achieves crowd event probability. Accurate, reduce the number of intersections, avoid the effect of inaccuracy

Active Publication Date: 2014-03-26
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this system is only suitable for small-scale indoor scenes, and it is easily affected by factors such as crowd occlusion in the segmentation of crowd individuals, and the accuracy of crowd count calculation cannot be guaranteed.
Although the crowd gathering detection system based on the intersection of motion vectors proposed in recent years can solve the problem of inaccurate statistics of crowd numbers, the calculation of the intersection of motion vecto

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

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0029] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0030] The crowd gathering detection based on the convex hull representation of the corner points of the present invention comprises the following steps:

[0031] A. Obtain video frame images through the camera.

[0032] B. Frame difference method to obtain the crowd motion foreground area. The frame difference method calculates the difference image of two adjacent frames of the video sequence. The obtained difference image is binarized, and the binarization threshold is 50 to obtain the crowd movement area. Because the foreground area obtained by the frame difference method has a "hole" phenomenon, the foreground image is expanded to obtain more crowd corners as a corner mask algorithm.

[0033] C. Harris corner detection. In view of the fact that the Harris corner detection algorithm is simple to calculate, and the extracted corner features

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 and device for detecting crowd gathering by describing crowds by using a convex hull (a convex polygon) and further simplifying the crowds by using a secondary clustering method. Inaccuracy of crowd individual segmentation is avoided by using angular points to describe the crowds; event detection is made to rise to cluster judgment instead of individual behavior judgment by using the convex hull for expressing the crowds close to one another and similar in moving state; through the fact that second clustering is carried out on the convex hull of the crowds, the number of points of intersection of motion vectors of the crowds in the same direction is reduced, and the calculated probability of occurrence of the crowds is more accurate.

Description

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

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
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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