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

A Method for Crowd Counting in Still Images

A crowd counting and static image technology, applied in neural learning methods, calculations, computer components, etc., can solve the problems of different scales and uneven crowd distribution, so as to improve accuracy, solve the problem of crowd scale differences, and improve the general The effect of the ability

Active Publication Date: 2021-04-27
CHANGZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deep learning-based crowd counting still has challenges such as uneven crowd distribution and different scales

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 Method for Crowd Counting in Still Images
  • A Method for Crowd Counting in Still Images
  • A Method for Crowd Counting in Still Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited thereto.

[0051] figure 1 The system flowchart of the crowd counting method for still images is given:

[0052] The crowd counting method proposed by the present invention divides the crowd image into several image sub-blocks, and each image sub-block is processed by up-sampling and down-sampling to obtain information of different scales. Features are then automatically extracted from image sub-patches at all scales by building a multi-scale CNN. These features estimate density maps, crowd density classes and background / foreground classifications in a multi-task learning manner. Finally, the combined density map of the crowd image is reconstructed according to the combined density map of all image sub-blocks, and the number of crowds is calculated by summing and integrating the values ​​of the combined d...

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 method for counting crowds on a static image. First, the inverse Gaussian density map is combined with the original Gaussian density map to form a combined density map; block and its corresponding real combined density map training network; overlapping sampling of the input image with the same amplitude, superimposing the combined density map of each image sub-block predicted by MMCNN, reconstructing the combined density map of the complete crowd image, and then realizing Crowd counting. In addition, aiming at the problem of crowd scale differences, the present invention uses a sub-scale loss function to measure the features learned by networks of different scales. At the same time, the network proposed by the present invention simultaneously predicts the crowd combination density map, density level, and foreground / background classification in a multi-task manner, thereby improving the estimation accuracy of the combined density map, thereby alleviating the problem of uneven crowd density.

Description

technical field [0001] The invention belongs to the field of intelligent monitoring, in particular to a method for counting crowds on still images. Background technique [0002] As an important part of intelligent video surveillance, crowd counting in public places has many applications, including crowd control, abnormal behavior detection, and pedestrian behavior analysis. Crowd counting can be used to detect potential risks and prevent overcrowding at religious or sporting events. Meanwhile, crowd counting can be extended to other fields, such as counting cells or bacteria from microscopic images. [0003] Existing crowd counting methods are generally divided into three categories, namely, counting by detection, counting by clustering, and counting by regression. Through the detection and counting method, crowd counting is realized according to the number of people in the detection scene. However, the detection process is time-consuming due to the thorough scanning of t...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/53G06N3/045G06F18/214
Inventor 杨彪曹金梦张御宇崔国增邹凌
Owner CHANGZHOU UNIV
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