Occluded Pedestrian-Attribute Recognition for Video Sensors Using Group Sparsityopen access
- Authors
- Lee, Geonu; Yun, Kimin; Cho, Jungchan
- Issue Date
- Sep-2022
- Publisher
- MDPI
- Keywords
- deep learning; group-sparsity loss; temporal attention module; video-based pedestrianattribute recognition
- Citation
- SENSORS, v.22, no.17
- Journal Title
- SENSORS
- Volume
- 22
- Number
- 17
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85652
- DOI
- 10.3390/s22176626
- ISSN
- 1424-8220
- 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, "boots" and "shoe 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 F-1-scores than the advanced baseline method on the occlusion samples in DukeMTMC-VideoRelD and MARS video-based PAR datasets, respectively.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 소프트웨어학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85652)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.