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

Crowd counting method based on convolutional neural network

A convolutional neural network and crowd counting technology, which is applied in the field of computer vision, can solve problems such as high requirements for picture clarity, deviation between the estimated value of the number of people and the real value, etc., to ensure accuracy, improve real-time performance, and reduce the number of parameters. Effect

Inactive Publication Date: 2018-11-23
ZHEJIANG UNIV
View PDF7 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has high requirements on the clarity of the picture, and there is a large deviation between the estimated number of people and the real value when the picture clarity decreases

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 based on convolutional neural network
  • Crowd counting method based on convolutional neural network
  • Crowd counting method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.

[0041] like figure 1 As shown, a crowd counting method based on convolutional neural network, including:

[0042] Step 1. After the training picture is marked, it is convolved with the Gaussian kernel to obtain the real crowd density map, which is used as the label for model training;

[0043] Step 2, input the training picture and the corresponding real crowd density map into the convolutional neural network model for training, and update the parameters for each optimization iteration until the model converges;

[0044] Step 3, create a new scene data set, use the model transfer method to fine-tune the obtained model, and the model training is completed;

[0045] Step 4, perform performance evaluation and test on the trained model.

[0046] First, the output of the model of the present invention is an estimated image density map. To comple...

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 a convolutional neural network. The method comprises the following steps of (1) after a training picture is marked, performing convolution operation with a Gaussian kernel to obtain a real crowd density diagram, and taking the real crowd density diagram as a label for model training; (2) inputting the training picture and the corresponding real crowd density diagram into a convolutional neural network model for performing training, and optimizing iterative updating parameters every time until the model is converged; (3) creating a new scene data set, and finely adjusting the obtained model by utilizing a model migration method, thereby finishing the model training; and (4) performing performance evaluation and testing on the trainedmodel. By utilizing the method, the number of parameters needed to be trained for the model is reduced; the model structure is simplified; the real-time performance of the model is improved on the premise that the accuracy is guaranteed; and the requirements of actual application are met.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a crowd counting method based on a convolutional neural network. Background technique [0002] The problem of people counting in public scenes is an important branch in the field of machine vision, and it is also a challenging problem. Crowd counting in the surveillance video of public places has important research value. For example, the public transportation system can use the people counting system to ensure the smooth flow of the road; when a large number of people gather, reasonable analysis of the crowd can reduce the insecurity among the crowd factors and prevent a stampede from happening. [0003] At present, the main methods of crowd counting are: counting methods based on pedestrian detectors, counting methods based on feature regression, and counting methods based on deep learning. [0004] Pedestrian detector-based counting method: This method is relatively ...

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
IPC IPC(8): G06T7/00G06N3/04G06N3/08
CPCG06T7/0002G06T2207/20081G06T2207/20084G06T2207/30242
Inventor 王曰海仝飞飞张肇阳欧岳枫王欢
Owner ZHEJIANG 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