TY - GEN
T1 - Highly Reliable Vehicle Detection through CNN with Attention Mechanism
AU - Wang, Li Wen
AU - Siu, Wan Chi
AU - Yang, Xue Fei
AU - Liu, Zhi Song
AU - Lun, Daniel Pak Kong
N1 - Funding Information:
Acknowledge.: The work was partly funded by Hong Kong PolyU, Caritas Institute of Higher Education and UGC Grants: UGC/IDS(C)11/E01/20 for manpower and IDS(R)11/19 for computing facility.
Publisher Copyright:
© 2022 IEEE.
PY - 2022/1
Y1 - 2022/1
N2 - This paper presents a novel approach to provide reliable vehicle detection by using CNN-based approach and lane information. We firstly propose an adaptive RoI strategy that utilizes road lane information to give focus on frontal area for vehicle detection. Then we introduce a novel attention mechanism that automatically learns an attention map to refine the features for detection. Experimental results show a large improvement (+73 % on recall rate) for long-range (30 to 60m) vehicle detection which is extremely useful for users of driving assistant systems.
AB - This paper presents a novel approach to provide reliable vehicle detection by using CNN-based approach and lane information. We firstly propose an adaptive RoI strategy that utilizes road lane information to give focus on frontal area for vehicle detection. Then we introduce a novel attention mechanism that automatically learns an attention map to refine the features for detection. Experimental results show a large improvement (+73 % on recall rate) for long-range (30 to 60m) vehicle detection which is extremely useful for users of driving assistant systems.
UR - http://www.scopus.com/inward/record.url?scp=85127084377&partnerID=8YFLogxK
U2 - 10.1109/ICCE53296.2022.9730525
DO - 10.1109/ICCE53296.2022.9730525
M3 - Conference article published in proceeding or book
AN - SCOPUS:85127084377
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
SP - 1
EP - 2
BT - 2022 IEEE International Conference on Consumer Electronics, ICCE 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Consumer Electronics, ICCE 2022
Y2 - 7 January 2022 through 9 January 2022
ER -