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

Classification method based on velocity vector human group clustering

A classification method and velocity vector technology, applied in the parts of color TV, parts of TV system, TV, etc., can solve the problems of subsequent analysis and forensics impact, poor description ability, lack of stress processing ability, etc.

Active Publication Date: 2019-12-03
成都电科慧安科技有限公司
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, different states of the crowd can be analyzed indiscriminately. In fact, the movement of sparse crowds has considerable randomness, while the movement of dense crowds has relatively strong regularity. Traditionally, a single feature has a relatively strong ability to describe sports crowds. In terms of many features, it is poor, and a single crowd classification algorithm is also difficult to adapt to the abnormal detection of complex sports crowds. In the face of unexpected accidents, such as fighting and crowd gathering within the monitoring range, the camera cannot focus and track the target in time. Lack of stress handling ability, which has a certain impact on the subsequent analysis and evidence collection of accidents or dangerous situations

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
  • Classification method based on velocity vector human group clustering
  • Classification method based on velocity vector human group clustering
  • Classification method based on velocity vector human group clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0113] A classification method based on velocity vector crowd clustering, comprising the following steps:

[0114] Step 1. Radar data collection. The radar samples the data of the quaternion (r, θ, v, α) for the individual targets in the crowd, where r is the distance, θ is the azimuth, v is the moving speed, and α is the moving direction;

[0115] When the number of individuals is n, the quadruple is (r 1 ,θ 1 ,v 1 ,α 1 ), (r 2 ,θ 2 ,v 2 ,α 2 )……(r n ,θ n ,v n ,α n );

[0116] Step 2, data correction, the r and θ data collected by the radar are converted into Cartesian coordinates, and the converted quadruple data is (x, y, v, α);

[0117] Step 3. KPCA, that is, kernel principal component analysis, centralizes and corrects the data-corrected quadruple data through the kernel matrix to obtain new quadruple data u, and uses the method of KPCA dimensionality reduction vector z to convert the quadruple The data u is reduced to 2 dimensions;

[0118] Step 4, cluster...

Embodiment 2

[0211] Such as figure 1 As shown, a classification method based on velocity vector crowd clustering, including the following steps:

[0212] First, the data returned by the camera shows that there are two individuals dividing each trajectory; the two individuals respectively include their respective quadruples (r 1 ,θ 1 ,v 1 ,α 1 ), (r 2 ,θ 2 ,v 2 ,α 2 ), where r is the distance, θ is the orientation, v is the moving speed, and α is the moving direction, the arrow on the triangle symbol in the figure indicates its moving direction, and the length of the arrow corresponds to its moving speed;

[0213] Second, data correction, through the direct data of distance and azimuth returned by the radar, it is converted into a Cartesian coordinate description, with the position of the radar as the origin, the conversion formula is as follows:

[0214] x 1 = r 1 Cosθ 1 x 2 = r 2 Cosθ 2

[0215] the y 1 = r 1 Sinθ 1 the y 2 = r 2 Sinθ 2

[0216] The converted data ...

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 classification method based on velocity vector human group clustering, which comprises the following steps of: 1, dividing each track feature of data returned by a camera according to the number of individuals; wherein the quadruple (r, theta, v, alpha) is included, r is the distance, theta is the orientation, v is the moving speed, and alpha is the moving direction; 2, converting the distance and orientation direct data returned by the radar into Cartesian coordinate description, and taking the position of the radar as an original point; and 3, selecting a Gaussian kernel function for generation through a kernel matrix. The spherical camera positioning assisted by the radar technology has remarkable advantages, and automatic patrol and rapid response of the camera are realized.

Description

technical field [0001] The invention belongs to the technical field of machine vision and image processing, and in particular relates to a classification method based on velocity vector crowd clustering. Background technique [0002] With the rapid development of social economy, large-scale crowd activities are increasing day by day. In certain environments, such as entertainment activities, sports events, religious ceremonies, celebrations, traffic intersections, etc., a large number of people often gather. The ensuing public safety issues have become increasingly prominent, and the possibility of sudden group abnormalities in public areas is increasing, which can easily lead to public safety accidents such as crowd disorder, congestion, and stampedes. In order to deal with the increasingly serious public places Crowd safety accidents, video surveillance is an effective means of public safety monitoring, and video surveillance has been widely used in traffic management, pub...

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): G06K9/62H04N5/232
CPCH04N23/67H04N23/64H04N23/695G06F18/23G06F18/2135G06F18/24Y02A90/10
Inventor 殷光强李耶游长江刘春辉
Owner 成都电科慧安科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com