A crowd counting method based on two-way fusion of elm

A people counting and crowd counting technology, which is applied in the field of two-way fusion crowd counting, can solve the problems of difficult fusion of crowd counting features and insufficient precision of crowd counting models, and achieve the effects of strong feature complementarity and improved accuracy

Active Publication Date: 2021-07-20
XIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a crowd counting method based on two-way fusion of ELM, which solves the problems that the existing crowd counting features are difficult to integrate and the precision of the crowd counting model is not high enough

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 crowd counting method based on two-way fusion of elm
  • A crowd counting method based on two-way fusion of elm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0027] The present invention provides a method for counting the number of people based on two-way fusion of ELM, the process of which is as follows figure 1 As shown, the specific steps are as follows:

[0028] Step 1. Establish training set images, specifically including collecting crowd video images, manually calibrate the number of people in each image, and use the obtained crowd video images and their corresponding crowd numbers as training set images.

[0029] Step 2, establish a crowd statistics model based on ELM-based two-way fusion, such as figure 2 As shown, it consists of three parts: one of them is ELM1, which has two inputs, which are the perimeter and area of ​​the crowd foreground target, one output, which is the number of people estimated by ELM1, one hidden layer, and the number of nodes is 50 ;The other way is ELM2, which...

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 crowd counting method based on two-way fusion of ELM, specifically: designing two-way ultra-limit learning machines ELM1 and ELM1 to respectively capture the relationship between the pixel features and texture features of the crowd number and the crowd number, and through the first Three extreme learning machines ELM3 realize the fusion of crowd numbers, thereby establishing a crowd statistics model based on ELM two-way fusion; then use the training set images to train the established crowd statistics models; finally use the trained crowd statistics model to analyze the video The number of people in the image is counted. By adopting the method of the invention, the organic fusion of the pixel features and texture features of the crowd can be realized, and it has the characteristics of strong feature complementarity and self-adaptive fusion, thereby greatly improving the accuracy of the crowd counting model.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and relates to a crowd counting method based on ELM-based two-way fusion. Background technique [0002] Due to the frequent occurrence of group incidents caused by crowd crowding, people have proposed the method of intelligently counting and managing the crowd numbers in public places through video surveillance to prevent safety problems caused by crowd crowding. [0003] In recent years, the research on crowd counting methods has made some progress. However, in the actual large-scale scene, there are problems such as complex crowd activity scenes and the influence of light changes on the collected video images, resulting in large crowd counting problems. error. The traditional crowd estimation method mainly considers the pixel or texture feature in the initial feature extraction, and does not fully consider the characteristics of the features and the features themselves, so that the fe...

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): G06K9/00G06K9/62G06N3/04G06N3/08G06T7/00G06T7/194G06T7/62
CPCG06N3/08G06T7/0002G06T7/194G06T7/62G06T2207/20036G06T2207/10016G06T2207/30242G06V20/53G06N3/045G06F18/254
Inventor 张二虎刘梦琨段敬红
Owner XIAN UNIV OF TECH
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