Crowd density estimation method

A crowd density and crowd technology, applied in computing, computer components, instruments, etc., can solve problems such as blurred density maps, overestimation, and large differences in density maps, and achieve good robustness, good crowd density estimation characteristics, and improved Effects on Problems with Dissimilar Density Map Distributions

Pending Publication Date: 2020-03-31
SHANGHAI INSTITUTE OF TECHNOLOGY
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the deep learning algorithm, due to the influence of the loss function, the density map learned by the network is relativel

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 density estimation method
  • Crowd density estimation method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0027] In order to make the above objectives, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Such as figure 1 with 2 As shown, the present invention provides a crowd density estimation method, which includes:

[0029] Step S1: Construct a corresponding truth map according to the corresponding crowd position coordinates given by the crowd image data set with a density greater than a preset threshold, train the AlexNet network for image classification, and train the feature network of the fusion attention mechanism under dense conditions. Training the feature network of fusion hole convolution in the sparse case;

[0030] Step S2: Build the AlexNet network, the feature network integrated with the attention mechanism, and the feature network integrated with the hollow convolution into a final training network wi...

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 provides a crowd density estimation method. The method comprises the steps: enabling a crowd image data set to be divided into a dense image data set and a sparse image data set throughemploying an AlexNet network, and respectively transmitting the dense image data set and the sparse image data set to corresponding feature extraction networks according to the difference of density features of the two types of images, thereby obtaining better and more effective crowd density estimation features. The method is used for estimating the number of crowds in the high-density crowd picture, and can prevent accidents caused by excessive crowding of the crowds. The invention relates to a combined network crowd density estimation algorithm. Crowd density estimation is carried out on crowd density and sparseness. According to the method, effective crowd density estimation features can be better provided, the problem that density map distribution is not similar can be solved, and themethod has good robustness.

Description

technical field [0001] The invention relates to a crowd density estimation method. Background technique [0002] In recent years, video image analysis based on convolutional neural networks has become a hot topic in the field of machine vision, and its applications are very extensive. Among them, crowd density estimation is an important branch. Crowd density estimation refers to the process of outputting the corresponding crowd density map through the convolutional neural network for high-density crowd pictures, and summing all the pixels in the density map to obtain the total number of people. [0003] At present, in addition to traditional crowd counting algorithms, many crowd counting algorithms based on deep learning have been continuously proposed. For the deep learning algorithm, due to the influence of the loss function, the density map learned by the network is relatively blurred, which is quite different from the real corresponding density map, and may also cause ...

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): G06K9/00G06K9/62
CPCG06V20/53G06F18/241G06F18/253
Inventor 王莉赵怀林汪涛
Owner SHANGHAI INSTITUTE OF TECHNOLOGY
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