Person Reidentification Using Multiple Egocentric Views

Development of a robust and scalable multicamera surveillance system is the need of the hour to ensure public safety and security. Being able to reidentify and track one or more targets over multiple nonoverlapping camera field of views in a crowded environment remains an important and challenging p...

Full description

Saved in:
Bibliographic Details
Main Authors: Chakraborty, Anirban, Mandal, Bappaditya, Yuan, Junsong
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2017
Subjects:
Online Access:https://hdl.handle.net/10356/82229
http://hdl.handle.net/10220/43503
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-82229
record_format dspace
spelling sg-ntu-dr.10356-822292020-03-07T14:02:35Z Person Reidentification Using Multiple Egocentric Views Chakraborty, Anirban Mandal, Bappaditya Yuan, Junsong School of Electrical and Electronic Engineering Rapid-Rich Object Search Lab Person reidentification Egocentric videos Development of a robust and scalable multicamera surveillance system is the need of the hour to ensure public safety and security. Being able to reidentify and track one or more targets over multiple nonoverlapping camera field of views in a crowded environment remains an important and challenging problem because of occlusions, large change in the viewpoints, and illumination across cameras. However, the rise of wearable imaging devices has led to new avenues in solving the reidentification (re-id) problem. Unlike static cameras, where the views are often restricted or low resolution and occlusions are common scenarios, egocentric/first person views (FPVs) mostly get zoomed in, unoccluded face images. In this paper, we present a person re-id framework designed for a network of multiple wearable devices. The proposed framework builds on commonly used facial feature extraction and similarity computation methods between camera pairs and utilizes a data association method to yield globally optimal and consistent re-id results with much improved accuracy. Moreover, to ensure its utility in practical applications where a large amount of observations are available every instant, an online scheme is proposed as a direct extension of the batch method. This can dynamically associate new observations to already observed and labeled targets in an iterative fashion. We tested both the offline and online methods on realistic FPV video databases, collected using multiple wearable cameras in a complex office environment and observed large improvements in performance when compared with the state of the arts. MOE (Min. of Education, S’pore) Accepted version 2017-07-31T06:41:00Z 2019-12-06T14:51:18Z 2017-07-31T06:41:00Z 2019-12-06T14:51:18Z 2016 Journal Article Chakraborty, A., Mandal, B., & Yuan, J. (2017). Person Reidentification Using Multiple Egocentric Views. IEEE Transactions on Circuits and Systems for Video Technology, 27(3), 484-498. 1051-8215 https://hdl.handle.net/10356/82229 http://hdl.handle.net/10220/43503 10.1109/TCSVT.2016.2615445 en IEEE Transactions on Circuits and Systems for Video Technology © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TCSVT.2016.2615445]. 14 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Person reidentification
Egocentric videos
spellingShingle Person reidentification
Egocentric videos
Chakraborty, Anirban
Mandal, Bappaditya
Yuan, Junsong
Person Reidentification Using Multiple Egocentric Views
description Development of a robust and scalable multicamera surveillance system is the need of the hour to ensure public safety and security. Being able to reidentify and track one or more targets over multiple nonoverlapping camera field of views in a crowded environment remains an important and challenging problem because of occlusions, large change in the viewpoints, and illumination across cameras. However, the rise of wearable imaging devices has led to new avenues in solving the reidentification (re-id) problem. Unlike static cameras, where the views are often restricted or low resolution and occlusions are common scenarios, egocentric/first person views (FPVs) mostly get zoomed in, unoccluded face images. In this paper, we present a person re-id framework designed for a network of multiple wearable devices. The proposed framework builds on commonly used facial feature extraction and similarity computation methods between camera pairs and utilizes a data association method to yield globally optimal and consistent re-id results with much improved accuracy. Moreover, to ensure its utility in practical applications where a large amount of observations are available every instant, an online scheme is proposed as a direct extension of the batch method. This can dynamically associate new observations to already observed and labeled targets in an iterative fashion. We tested both the offline and online methods on realistic FPV video databases, collected using multiple wearable cameras in a complex office environment and observed large improvements in performance when compared with the state of the arts.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Chakraborty, Anirban
Mandal, Bappaditya
Yuan, Junsong
format Article
author Chakraborty, Anirban
Mandal, Bappaditya
Yuan, Junsong
author_sort Chakraborty, Anirban
title Person Reidentification Using Multiple Egocentric Views
title_short Person Reidentification Using Multiple Egocentric Views
title_full Person Reidentification Using Multiple Egocentric Views
title_fullStr Person Reidentification Using Multiple Egocentric Views
title_full_unstemmed Person Reidentification Using Multiple Egocentric Views
title_sort person reidentification using multiple egocentric views
publishDate 2017
url https://hdl.handle.net/10356/82229
http://hdl.handle.net/10220/43503
_version_ 1681035450728316928