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

Pedestrian attribute identification method based on deep learning

A technology of attribute recognition and deep learning, applied in the field of pedestrian attribute recognition based on deep learning, can solve problems such as lack of methods, achieve reasonable design and improve accuracy

Active Publication Date: 2019-07-30
CIVIL AVIATION UNIV OF CHINA
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no corresponding method

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
  • Pedestrian attribute identification method based on deep learning
  • Pedestrian attribute identification method based on deep learning
  • Pedestrian attribute identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The pedestrian attribute recognition method based on deep learning provided by the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] Such as figure 1 , figure 2 As shown, the pedestrian attribute recognition method based on deep learning provided by the present invention includes the following steps carried out in order:

[0033] (1) Using the classic Deeplab-v2 network in the image semantic segmentation method, the pedestrian image in the pedestrian attribute dataset is used as the input of the Deeplab-v2 network, and the output is the mask image of the pedestrian image;

[0034] The pedestrian image can be expressed as a multi-dimensional matrix mathematically, and the mask image is a matrix with the same dimension as the pedestrian image; the pedestrian body area element in the pedestrian image is set to 1, and the matrix obtained by setting the background area element to 0 is is the ...

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 pedestrian attribute identification method based on deep learning. The method comprises the following steps: taking a pedestrian image as the input of a Deeplab-v2 network to obtain a mask map; multiplying the mask image and the pedestrian image element by element to obtain a foreground image, negating the mask image, and multiplying the mask image and the pedestrian image element by element to obtain a background image; constructing a pedestrian attribute identification network, and combining the regional-level ternary loss function and the weighted cross entropy loss function as a loss function of the network; taking the pedestrian image, the foreground image and the background image as input of a pedestrian attribute recognition network, calculating a networkloss value by utilizing a loss function, optimizing the network through a random gradient descent method, and storing network parameters; and initializing a pedestrian attribute recognition network byutilizing the pedestrian attribute recognition network parameters, and inputting pedestrian images to obtain an attribute recognition result. The method is reasonable in design, so that the accuracyof pedestrian attribute recognition can be greatly improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a pedestrian attribute recognition method based on deep learning. Background technique [0002] In recent years, people have paid more and more attention to public security issues. A large number of surveillance cameras are used in shopping malls, subway stations, intersections and other places where there are dense crowds and public security incidents are prone to occur. Surveillance videos can provide people with a lot of useful information. Pedestrian attribute recognition can identify some observable external feature information of pedestrians in the monitoring scene, such as gender, age, clothing, and belongings, etc. This information can provide clues for the public security department to detect criminal cases such as shopping mall theft and crowd fighting. Play an important role in maintaining national security. [0003] At present, pedestrian attribute recogniti...

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
CPCG06V40/103G06F18/241Y02T10/40
Inventor 张良袁配配
Owner CIVIL AVIATION UNIV OF CHINA
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