Pedestrian Re-Identification Method Based on Collaborative Scale Learning
A pedestrian re-identification and scale learning technology, applied in the field of pedestrian re-identification based on collaborative scale learning, can solve the problems of high timeliness requirements for video detection applications, difficulty in obtaining sufficient labeling training samples, and low efficiency of manual labeling. The effect of re-identification performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] The technical scheme of the present invention can adopt computer software to realize the automatic operation process. The technical solution of the present invention will be described in detail below in conjunction with the drawings and embodiments.
[0022] The embodiment adopts MATLAB7 as the simulation experiment platform, and tests are carried out on the commonly used pedestrian retrieval data set VIPeR. The VIPeR dataset has 632 pedestrian image pairs under two cameras, and there are obvious differences in viewing angle and illumination between the two cameras. Such as figure 1 , the flow process of embodiment technical solution is as follows:
[0023] A set of labeled pedestrian sample pairs with a given length l That is, the labeled training sample set, the labeled pedestrian training sample x i,a and x i,b are the images of the i-th labeled pedestrian under cameras a and b, forming a pair of pedestrian images, y i is the identity of the pedestrian, and th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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