TY - GEN
T1 - TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting
AU - Tang, Haihan
AU - Wang, Yi
AU - Chau, Lap Pui
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/5
Y1 - 2022/5
N2 - In this paper, we propose a three-stream adaptive fusion network named TAFNet, which uses paired RGB and thermal images for crowd counting. Specifically, TAFNet is divided into one main stream and two auxiliary streams. We combine a pair of RGB and thermal images to constitute the input of main stream. Two auxiliary streams respectively exploit RGB image and thermal image to extract modality-specific features. Besides, we propose an Information Improvement Module (IIM) to fuse the modality-specific features into the main stream adaptively. Experiment results on RGBT-CC dataset show that our method achieves more than 20% improvement on mean average error and root mean squared error compared with state-of-the-art method. The source code will be publicly available at https://github.com/TANGHAIHAN/TAFNet.
AB - In this paper, we propose a three-stream adaptive fusion network named TAFNet, which uses paired RGB and thermal images for crowd counting. Specifically, TAFNet is divided into one main stream and two auxiliary streams. We combine a pair of RGB and thermal images to constitute the input of main stream. Two auxiliary streams respectively exploit RGB image and thermal image to extract modality-specific features. Besides, we propose an Information Improvement Module (IIM) to fuse the modality-specific features into the main stream adaptively. Experiment results on RGBT-CC dataset show that our method achieves more than 20% improvement on mean average error and root mean squared error compared with state-of-the-art method. The source code will be publicly available at https://github.com/TANGHAIHAN/TAFNet.
KW - crowd counting
KW - RGB-T
KW - three-stream network
UR - http://www.scopus.com/inward/record.url?scp=85135891846&partnerID=8YFLogxK
U2 - 10.1109/ISCAS48785.2022.9937583
DO - 10.1109/ISCAS48785.2022.9937583
M3 - Conference article published in proceeding or book
AN - SCOPUS:85135891846
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
SP - 3299
EP - 3303
BT - IEEE International Symposium on Circuits and Systems, ISCAS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
Y2 - 27 May 2022 through 1 June 2022
ER -