TY - GEN
T1 - InterFusion
T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
AU - Wang, Li
AU - Zhang, Xinyu
AU - Xv, Baowei
AU - Zhang, Jinzhao
AU - Fu, Rong
AU - Wang, Xiaoyu
AU - Zhu, Lei
AU - Ren, Haibing
AU - Lu, Pingping
AU - Li, Jun
AU - Liu, Huaping
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Many recent works detect 3D objects by several sensor modalities for autonomous driving, where high-resolution cameras and high-line LiDARs are mostly used but relatively expensive. To achieve a balance between overall cost and detection accuracy, many multi-modal fusion techniques have been suggested. In recent years, the fusion of LiDAR and Radar has gained ever-increasing attention, especially 4D Radar, which can adapt to bad weather conditions due to its penetrability. Although features have been fused from multiple sensing modalities, most methods cannot learn interactions from different modalities, which does not make for their best use. Inspired by the self-attention mechanism, we present InterFusion, an interaction-based fusion framework, to fuse 16-line LiDAR with 4D Radar. It aggregates features from two modalities and identifies cross-modal relations between Radar and LiDAR features. In experimental evaluations on the Astyx HiRes 2019 dataset, our method outperformed the baseline by 4.20% mAP in 3D and 10.76% BEV mAP for the car class at the moderate level.
AB - Many recent works detect 3D objects by several sensor modalities for autonomous driving, where high-resolution cameras and high-line LiDARs are mostly used but relatively expensive. To achieve a balance between overall cost and detection accuracy, many multi-modal fusion techniques have been suggested. In recent years, the fusion of LiDAR and Radar has gained ever-increasing attention, especially 4D Radar, which can adapt to bad weather conditions due to its penetrability. Although features have been fused from multiple sensing modalities, most methods cannot learn interactions from different modalities, which does not make for their best use. Inspired by the self-attention mechanism, we present InterFusion, an interaction-based fusion framework, to fuse 16-line LiDAR with 4D Radar. It aggregates features from two modalities and identifies cross-modal relations between Radar and LiDAR features. In experimental evaluations on the Astyx HiRes 2019 dataset, our method outperformed the baseline by 4.20% mAP in 3D and 10.76% BEV mAP for the car class at the moderate level.
UR - http://www.scopus.com/inward/record.url?scp=85146341499&partnerID=8YFLogxK
U2 - 10.1109/IROS47612.2022.9982123
DO - 10.1109/IROS47612.2022.9982123
M3 - Conference contribution
AN - SCOPUS:85146341499
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 12247
EP - 12253
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 October 2022 through 27 October 2022
ER -