TY - GEN
T1 - DVRNet
T2 - 2020 IEEE/IAPR International Joint Conference on Biometrics, IJCB 2020
AU - Shi, Lei
AU - Livermore, Charles
AU - Kakadiaris, Ioannis A.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/28
Y1 - 2020/9/28
N2 - Pedestrian detection remains a challenging task due to the problems caused by occlusion variance. Visible-body bounding boxes are typically used as an extra supervision signal to improve the performance of pedestrian detection to predict the full-body. However, visible-body assisted approaches produce a large number of false positives, which result from a lack of adequate and discriminative full-body contextual information. In this paper, we propose a new network, dubbed DVRNet, based on the representative visible-body assisted pedestrian detector named Bi-box. Specifically, we extend Bi-box by adding three modules named the attention-based feature interleaver module (AFIM), the binary mask learning module (BMLM), and the head-aware feature enhancement module (HFEM), which play important roles in employing features learned by the visible-body and the head supervision signals to enrich high discriminative contextual information of the full-body and enhance the power of feature representation. Experimental results indicate that the DVRNet achieves promising results on the CityPersons and the CrowdHuman datasets.
AB - Pedestrian detection remains a challenging task due to the problems caused by occlusion variance. Visible-body bounding boxes are typically used as an extra supervision signal to improve the performance of pedestrian detection to predict the full-body. However, visible-body assisted approaches produce a large number of false positives, which result from a lack of adequate and discriminative full-body contextual information. In this paper, we propose a new network, dubbed DVRNet, based on the representative visible-body assisted pedestrian detector named Bi-box. Specifically, we extend Bi-box by adding three modules named the attention-based feature interleaver module (AFIM), the binary mask learning module (BMLM), and the head-aware feature enhancement module (HFEM), which play important roles in employing features learned by the visible-body and the head supervision signals to enrich high discriminative contextual information of the full-body and enhance the power of feature representation. Experimental results indicate that the DVRNet achieves promising results on the CityPersons and the CrowdHuman datasets.
UR - http://www.scopus.com/inward/record.url?scp=85099681848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099681848&partnerID=8YFLogxK
U2 - 10.1109/IJCB48548.2020.9304883
DO - 10.1109/IJCB48548.2020.9304883
M3 - Conference contribution
AN - SCOPUS:85099681848
T3 - IJCB 2020 - IEEE/IAPR International Joint Conference on Biometrics
BT - IJCB 2020 - IEEE/IAPR International Joint Conference on Biometrics
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 September 2020 through 1 October 2020
ER -