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

Pedestrian re-recognition method based on body decomposition and significance detection

A pedestrian re-identification and salience technology, applied in the field of image processing, can solve the problem of large differences in the color and outline of pedestrian images, and achieve the effect of improving the re-identification rate

Active Publication Date: 2018-09-11
NORTHEASTERN UNIV
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Affected by different viewing angles, lighting and scales, the pose, color and outline of pedestrian images are quite different. How to improve the re-recognition rate of pedestrian images is still a huge challenge

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 re-recognition method based on body decomposition and significance detection
  • Pedestrian re-recognition method based on body decomposition and significance detection
  • Pedestrian re-recognition method based on body decomposition and significance detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to better explain the present invention and facilitate understanding, the present invention will be described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0064] State-of-the-art feature representation methods mainly focus on two different aspects: handcrafted features and deep features. An increasing number of discriminative handcrafted features have been developed to achieve exact matching. In recent years, deep learning has been widely used and has made great breakthroughs in almost all visual fields. Especially in recognition tasks, many convolutional neural network (CNN) based methods have been proposed to extract deep features. Related studies have shown that deep models trained on large-scale datasets (eg: ImageNet) are very effective.

[0065] Background subtraction is an important preprocessing of image recognition tasks, which eliminates a lot of interference in matching different people in the same c...

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 re-recognition method based on body decomposition and significance detection. The method comprises the following steps: firstly, pedestrian images are analyzed into a deep decomposition network (DDN) with the semantics, and the pedestrians are separated from the messy environment by using a sliding window and a color matching method; next, the pedestrian imageis divided into a small block, and an effective picture region is automatically selected according to the result of background deduction and the salient region; finally, a local description method isproposed to assist in extracting global visual features after background subtraction so as to re-identify people. Specifically, the PHOG, HSV histogram and SIFT features are extracted from the selected image region and the LOMO features are extracted from the whole image. According to the invention, the local description operator and the global feature are tightly combined, so that the re-recognition rate of pedestrian images in different cameras can be effectively improved.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a pedestrian re-identification method based on body decomposition and saliency detection. Background technique [0002] The purpose of pedestrian re-identification technology is to identify all the images of a person captured by different cameras. It is an important aspect in the field of intelligent video research. In the current field of computer vision, it is a subject that is developing rapidly but still needs to be improved. Affected by different viewing angles, illumination, and scales of shooting, the pose, color, and outline of pedestrian images are quite different. How to improve the re-identification rate of pedestrian images is still a huge challenge. [0003] For this reason, how to improve the re-identification rate of pedestrian images has become a technical problem that needs to be solved at present. Contents of the invention [0004] Aiming at the problems in th...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/103G06V10/462G06F18/22G06F18/24147G06F18/253
Inventor 张云洲刘一秀王松史维东孙立波刘双伟李瑞龙
Owner NORTHEASTERN 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