Crowd counting method and system based on cGAN network

A crowd counting and network technology, applied in the field of computer vision, achieves the effect of simple training, fast training speed and short training time

Active Publication Date: 2017-11-07
SHANGHAI JIAO TONG UNIV
View PDF4 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods face various training problems brought about by deep networks

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 counting method and system based on cGAN network
  • Crowd counting method and system based on cGAN network
  • Crowd counting method and system based on cGAN network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The images used in this implementation come from the crowd scene images in the database Shanghaitech. The crowd counting scene picture sequence is provided by (In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR2016) for the analysis and comparison of crowd counting methods.

[0037] This embodiment relates to the crowd counting method of the cGAN network, including the following specific steps:

[0038] Step 1: Label the training pictures and mark the point x on the head of the corresponding pedestrian i , to scale the coordinate position, the scaling ratio is the ratio of the length and width of the original image to 256. Of course, in other embodiments, the scaling ratio can also be selected according to actual needs.

[0039] Step 2: Calculate the crowd density distribution map of the entire image, centering on the coordinates of each pedestrian point, construct a Gaussian kernel function matrix block δ(x-x i )*G σ , and then t...

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 and system based on a cGAN network. The crowd counting method comprises the steps of generating a crowd density distribution diagram by using an accumulated Gaussian kernel function matrix; extracting semantic attribute information of an input picture by using a generator coding network, and generating a crowd density distribution diagram sample by using a generator decoding network; discriminating whether a density map is generated by a generator or belongs to a real sample by using a discriminator; alternately training the generator and the discriminator; inputting a scene picture by using the trained generator to obtain a corresponding scene picture density map; and representing the total number of people in the picture by using accumulation of pixel values of the scene picture. The crowd counting method adopts a generative model, requires less data, and is higher in training speed and more suitable for actual application requirements; and meanwhile, the crowd counting method adopts a deeper neural network, thereby being capable of better eliminating background interference, generating the high-quality crowd density distribution map and playing a better decision-making support role for further crowd analysis and video surveillance.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and specifically relates to a method and system for counting the number of people based on a cGAN network, in particular to a crowd counting scheme suitable for fast training and obtaining a clearer density distribution map. Background technique [0002] Large-scale activities have become an important carrier of economic development and cultural exchanges, and group management has also become an important aspect of social management. The number of crowds is an important attribute of crowds, which can provide managers with important decision-making information, and has received extensive attention and research in the field of computer vision applications in recent years. Crowd counting can be defined as: given a corresponding picture to count the total number of people in the picture. It is an automatic crowd counting technology, which can quickly obtain the number of crowds in the scene ...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V20/53G06F18/214
Inventor 杨华李嘉文
Owner SHANGHAI JIAO TONG UNIV
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