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

A method and device for counting people in pictures based on convolutional neural network

A convolutional neural network and human head technology, which is applied in the field of image head counting technology in deep learning, and can solve problems such as poor real-time performance and large number of parameters.

Active Publication Date: 2021-09-10
JIANGSU WISEDU INFORMATION TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

W. Liu used the method of multi-column convolutional neural network for crowd counting and achieved good results, but the number of parameters is too large and the real-time performance is not good, so the crowd counting method based on single-column convolutional neural network is still a crowd counting algorithm research hotspots

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 and device for counting people in pictures based on convolutional neural network
  • A method and device for counting people in pictures based on convolutional neural network
  • A method and device for counting people in pictures based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0096] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0097] This embodiment relates to a flow analysis system for people, such as Figure 4 As shown, it includes a server 100 set in the computer room and several front-end cameras 200 set at monitoring points. The front-end camera 200 is connected to the server 100 through the network 300 . The server 100 obtains the live scene real-time image of the monitoring point through the front-end camera 200, and then analyzes the obtained real-time image through a convolutional neural network-based picture head counting method of the present invention, counts the number of people, and then calculates the flow of people.

[0098] The picture head counting method based on the convolutional neural network of the present invention is a method realized by a software program. The method comprises the following steps: a model initialization step, a data initialization step, ...

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 and device for counting people in a picture based on a convolutional neural network. This method is a crowd counting technology based on a single-column feature fusion convolutional neural network, which solves the crowd counting difficulties such as crowd occlusion to a certain extent. The network uses the front-end network containing the first ten layers of VGG16 to obtain basic features, the middle-end network containing small-scale convolutional layers to obtain multi-scale features, and the back-end network containing dilated convolutional layers with different hole rates to obtain crowd density picture. Finally, the head count is obtained by accumulating the points of the crowd density map. Experiments show that the accuracy of the present invention is better than certain known methods in the general population density scene.

Description

technical field [0001] The invention relates to a picture head counting technology, in particular to a picture head counting technology based on deep learning of a convolutional neural network. Background technique [0002] With the improvement of computer hardware level and the enrichment of neural network-related theories, deep learning-related industries are booming. The development of computer vision-related knowledge and the popularity of cameras provide the technical prerequisites for the data sets required for deep learning. Therefore, the crowd counting method based on deep learning has the conditions that can be realized. [0003] Crowd counting is to count the number of people in a certain area, and it has a wide range of applications in public security incident management, precise management of specific scenarios, and automatic analysis of commercial marketing. At present, the mainstream method of crowd counting is to count the number of people in a picture thro...

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): G06K9/00G06K9/42G06N3/04G06N3/08
CPCG06N3/08G06V20/53G06V10/32G06N3/045
Inventor 王晓东张宜红章联军吴奇元郭超史鸣杰
Owner JIANGSU WISEDU INFORMATION TECH
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