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

Crowd Quantity Estimation, Local Crowd Gathering State and Crowd Running State Detection Method Based on Video Stream

A video stream and crowd technology, applied in the field of image processing, can solve difficult problems such as occlusion, tracking, detection and segmentation failure

Active Publication Date: 2015-09-30
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when the scene is complex, these methods are difficult to deal with the occlusion problem, and all tracking, detection and segmentation will fail

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
  • Crowd Quantity Estimation, Local Crowd Gathering State and Crowd Running State Detection Method Based on Video Stream
  • Crowd Quantity Estimation, Local Crowd Gathering State and Crowd Running State Detection Method Based on Video Stream
  • Crowd Quantity Estimation, Local Crowd Gathering State and Crowd Running State Detection Method Based on Video Stream

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] Such as figure 1 As shown, it is a flow chart of a method for estimating the number of people based on video streams, and the method includes the following steps:

[0071] Step S110, preprocessing the video stream to obtain a foreground image, where the foreground image is a crowd image.

[0072] In the scene, the moving person is the foreground.

[0073] In this embodiment, the step of preprocessing the video stream to obtain the foreground image specifically includes:

[0074] Use the Gaussian mixture model to obtain the background of the currently processed frame;

[0075] The background is subtracted from the currently processed frame to obtain a foreground image.

[0076] Among them, the Gaussian mixture model is a model that uses Gaussian probability density functions to accurately quantify things, and decomposes a thing into several basic Gaussian probability density functions.

[0077] In this embodiment, after the step of preprocessing the video stream to o...

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 crowd quantity estimating method based on video stream. The method comprises the following steps of pre-treating video stream to obtain a foreground image, wherein the foreground image is a crowd image; calculating image potential energy Ep of the foreground image according to the following formula; in the formula, mij is pixel quality, and the value of mij is ranged from 0 to 1, if the pixel quality is 1, the pixel is the foreground, and if the pixel quality is 0, the pixel is the background; X is the width of the image, and the unit is pixel; Y is the height of the image, and the unit is pixel; gimg is a potential energy coefficient, gimg is a constant; yij is the y-axis coordinate of the pixel; H is the shortest distance of an object to a camera in a scene; and obtaining crowd estimated quantity by dividing the image potential energy Ep of the foreground image by average image potential energy of single pedestrian. In addition, the invention further provides a local crowd clustering state detection method and a crowd running state detection method.

Description

【Technical field】 [0001] The invention relates to image processing, and in particular to methods for estimating the number of crowds, gathering states of local crowds, and detecting crowds running states based on video streams. 【Background technique】 [0002] In recent years, due to the reduction in the price of video surveillance equipment, our cities have deployed thousands of cameras and generated a large amount of video data; however, we do not and cannot have enough people to handle the explosive growth video information. On the other hand, many effective new technologies have emerged in the field of image and vision, and are developing rapidly. Based on the above two reasons, researchers from all over the world began to use computer vision methods to analyze and process video data. [0003] Accurately estimating the crowd size in public scenes is crucial for intelligent video applications. For example, accurate and timely information about the number of people in a ...

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): G06M11/00G06K9/62
Inventor 吴新宇熊国刚陈彦伦梁国远徐扬生
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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