PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Yeong-Jun, Yoon, Kuk-Jin
Format: Preprint
Published: 2017
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909233223565312
author Cho, Yeong-Jun
Yoon, Kuk-Jin
author_facet Cho, Yeong-Jun
Yoon, Kuk-Jin
contents Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views. Although there has been much progress in person re-identification over the last decade, it remains a challenging task because appearances of people can seem extremely different across diverse camera viewpoints and person poses. In this paper, we propose a novel framework for person re-identification by analyzing camera viewpoints and person poses in a so-called Pose-aware Multi-shot Matching (PaMM), which robustly estimates people's poses and efficiently conducts multi-shot matching based on pose information. Experimental results using public person re-identification datasets show that the proposed methods outperform state-of-the-art methods and are promising for person re-identification from diverse viewpoints and pose variances.
format Preprint
id arxiv_https___arxiv_org_abs_1705_06011
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification
Cho, Yeong-Jun
Yoon, Kuk-Jin
Computer Vision and Pattern Recognition
Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views. Although there has been much progress in person re-identification over the last decade, it remains a challenging task because appearances of people can seem extremely different across diverse camera viewpoints and person poses. In this paper, we propose a novel framework for person re-identification by analyzing camera viewpoints and person poses in a so-called Pose-aware Multi-shot Matching (PaMM), which robustly estimates people's poses and efficiently conducts multi-shot matching based on pose information. Experimental results using public person re-identification datasets show that the proposed methods outperform state-of-the-art methods and are promising for person re-identification from diverse viewpoints and pose variances.
title PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1705.06011