ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Occluded Pedestrian-Attribute Recognition for Video Sensors Using Group Sparsity
Cited 1 time in scopus Download 69 time Share share facebook twitter linkedin kakaostory
Authors
Geonu Lee, Kimin Yun, Jungchan Cho
Issue Date
2022-09
Citation
Sensors, v.22, no.17, pp.1-16
ISSN
1424-8220
Publisher
MDPI
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.3390/s22176626
Abstract
Pedestrians are often obstructed by other objects or people in real-world vision sensors. These obstacles make pedestrian-attribute recognition (PAR) difficult; hence, occlusion processing for visual sensing is a key issue in PAR. To address this problem, we first formulate the identification of non-occluded frames as temporal attention based on the sparsity of a crowded video. In other words, a model for PAR is guided to prevent paying attention to the occluded frame. However, we deduced that this approach cannot include a correlation between attributes when occlusion occurs. For example, ?쐀oots?? and ?쐓hoe color?? cannot be recognized simultaneously when the foot is invisible. To address the uncorrelated attention issue, we propose a novel temporal-attention module based on group sparsity. Group sparsity is applied across attention weights in correlated attributes. Accordingly, physically-adjacent pedestrian attributes are grouped, and the attention weights of a group are forced to focus on the same frames. Experimental results indicate that the proposed method achieved 1.18% and 6.21% higher (Formula presented.) -scores than the advanced baseline method on the occlusion samples in DukeMTMC-VideoReID and MARS video-based PAR datasets, respectively.
KSP Keywords
Attribute recognition, Formula presented, Group Sparsity, Real-world, Vision sensor, occlusion processing, video based, visual sensing
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
CC BY