Support sample based indirect pedestrian re-identification method

A pedestrian re-identification and pedestrian technology, which is applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as enhancing the robustness of pedestrian re-identification algorithms, and achieve the effect of spatial stability and improved accuracy

Active Publication Date: 2017-07-25
安徽科大擎天科技有限公司
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to overcome the deficiencies of the prior art, and provides an indirect pedestrian re-identification method based on supporting samples, in order to effectively overcome the problems of illumination, viewing angle and scale in pedestrian re-identification, and obtain better re-identification performance , so as to effectively improve the pedestrian re-identification rate and enhance the robustness of the pedestrian re-identification algorithm

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
  • Support sample based indirect pedestrian re-identification method
  • Support sample based indirect pedestrian re-identification method
  • Support sample based indirect pedestrian re-identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In this example, if figure 1 As shown, a method of pedestrian re-identification supporting indirect samples includes the following process: firstly, preprocessing the collected videos from different cameras to obtain the required sample images. The support samples of the camera samples are obtained through clustering method learning. On the basis of supporting samples, pedestrians under different cameras can be matched through indirect pedestrian matching. Specifically, proceed as follows:

[0032]Step 1. Use two cameras Camera_P and Camera_Q with no intersection in the shooting area to obtain pedestrian training image sets respectively, and record it as pedestrian training image set P={p 1 ,p 2 ,...,p i ,...,p N} and pedestrian matching image set Q={q 1 ,q 2 ,...,q i ,...,q N}; and the i-th training image p i Pedestrians in the i-th matching image q i The pedestrians in are the same person; 1≤i≤N;

[0033] Step 2. Feature extraction

[0034] The ith traini...

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 support sample based indirect pedestrian re-identification method. The method comprises the following steps that videos collected by two cameras without intersection are preprocessed, needed training sample images are obtained, a dense color histogram is combined with dense SIFT to extract features from the images, support samples of the two different cameras are obtained in a clustering method, and when pedestrians from different cameras are matched, the support samples are used to discriminate the pedestrian types in the corresponding cameras on the basis of distance measurement, and the types are compared to determine whether the pedestrians are the same one. According to the invention, pedestrian images from the different cameras are matched directly, the problems in visual angle, illumination and scale caused by different cameras are solved effectively, the pedestrian re-identifying accuracy is improved, and the robustness of a pedestrian re-identification algorithm is enhanced.

Description

technical field [0001] The invention belongs to the technical field of intelligent video monitoring, and in particular relates to an indirect pedestrian re-identification method based on supporting samples. Background technique [0002] Pedestrian re-identification is to match pedestrians under the surveillance cameras in non-overlapping areas, that is, to check whether the pedestrian target under a certain camera appears under other cameras. Pedestrian re-identification has important applications in the field of social public security. However, the differences between different surveillance cameras lead to changes in viewing angle, illumination and scale, which makes pedestrian re-identification a great challenge. How to establish an efficient and accurate needle re-identification method, researchers have conducted related research. At present, the research on pedestrian re-identification mainly focuses on the learning of feature representation and distance measure. In rec...

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): G06K9/46G06K9/62
CPCG06V10/462G06V10/751
Inventor 孙锐方蔚黄启恒高隽
Owner 安徽科大擎天科技有限公司
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