A semi-automated system for person re-identification adaptation to cross-outfit and cross-posture scenarios
Journal article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Chanlongrat W., Apichanapong T., Sinngam P., Chaisangmongkon W.
Publisher: Springer
Publication year: 2022
Volume number: 52
Issue number: 8
Start page: 9501
End page: 9520
Number of pages: 20
ISSN: 0924-669X
eISSN: 1573-7497
Languages: English-Great Britain (EN-GB)
View in Web of Science | View on publisher site | View citing articles in Web of Science
Abstract
Person re-identification (ReID) algorithms are often trained on multi-camera snapshots of individuals taken on the same day, wearing the same outfits. Models trained with such protocols often fail in many long-term, indoor applications where person matching must be done across days, necessitating that algorithms be able to adapt to changing clothing and body postures. This study presents a simple, yet effective, system to overcome this challenge in realistic settings. We collected a new dataset capturing the natural variations of office worker appearances across days. To teach a ReID algorithm to adapt, we designed a semi-automated identity labeling system that requires only a small set of identification inputs from human labelers. The system utilized instance segmentation algorithms to detect people and one-shot video segmentation algorithms to track individuals across frames. Identified footages are then fed into the image repository to continually fine-tune the ReID network. These experiments demonstrate the applicability of our proposed method in helping the ReID algorithm overcome the challenges of varied clothing and postures. Our system improves the performance (measured by mAP) compared to pre-trained benchmark by 2.46% for the standard ReID condition, by 18.19% for cross-outfit re-identification, by 22.94% for cross-posture re-identification, and by 19.17% for the cross-posture and cross-outfit setting. As such, we anticipate this method may be beneficial towards the multitude of applications that utilize machine vision to automatically recognize human subjects. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Keywords
Clothing inconsistency, Data labeling tools, Person re-identification, Person re-identification system, Video object segmentation
Contact Information