TY - JOUR
T1 - KAM-Net
T2 - Keypoint-Aware and Keypoint-Matching Network for Vehicle Detection from 2-D Point Cloud
AU - Zou, Tianpei
AU - Chen, Guang
AU - Li, Zhijun
AU - He, Wei
AU - Qu, Sanqing
AU - Gu, Shangding
AU - Knoll, Alois
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2022/4/1
Y1 - 2022/4/1
N2 - Two-dimesional (2-D) LiDAR is an efficient alternative sensor for vehicle detection, which is one of the most critical tasks in autonomous driving. Compared to the fully developed 3-D LiDAR vehicle detection, 2-D LiDAR vehicle detection has much room to improve. Most existing state-of-the-art works represent 2-D point clouds as pseudo-images and then perform detection with traditional object detectors on 2-D images. However, they ignore the sparse representation and geometric information of vehicles in the 2-D cloud points. To address these issues, in this article, we present a novel keypoint-aware and keypoint-matching network termed as KAM-Net, which focuses on better detecting the vehicles by explicitly capturing and extracting the sparse information of L-shape in 2-D LiDAR point clouds. The whole framework consists of two stages - namely, keypoint-aware stage and keypoint-matching stage. The keypoint-aware stage utilizes the heatmap and edge extraction module to simultaneously predict the position of L-shaped keypoints and inflection offset of L-shaped endpoints. The keypoint-matching stage is followed to group the keypoints and produce the oriented bounding boxes with axis by utilizing the endpoint-matching and L-shaped-matching methods. Further, we conduct extensive experiments on a recently released public dataset to evaluate the effectiveness of our approach. The results show that our KAM-Net achieves a new state-of-the-art performance. The source code is available at https://github.com/ispc-lab/KAM-Net.
AB - Two-dimesional (2-D) LiDAR is an efficient alternative sensor for vehicle detection, which is one of the most critical tasks in autonomous driving. Compared to the fully developed 3-D LiDAR vehicle detection, 2-D LiDAR vehicle detection has much room to improve. Most existing state-of-the-art works represent 2-D point clouds as pseudo-images and then perform detection with traditional object detectors on 2-D images. However, they ignore the sparse representation and geometric information of vehicles in the 2-D cloud points. To address these issues, in this article, we present a novel keypoint-aware and keypoint-matching network termed as KAM-Net, which focuses on better detecting the vehicles by explicitly capturing and extracting the sparse information of L-shape in 2-D LiDAR point clouds. The whole framework consists of two stages - namely, keypoint-aware stage and keypoint-matching stage. The keypoint-aware stage utilizes the heatmap and edge extraction module to simultaneously predict the position of L-shaped keypoints and inflection offset of L-shaped endpoints. The keypoint-matching stage is followed to group the keypoints and produce the oriented bounding boxes with axis by utilizing the endpoint-matching and L-shaped-matching methods. Further, we conduct extensive experiments on a recently released public dataset to evaluate the effectiveness of our approach. The results show that our KAM-Net achieves a new state-of-the-art performance. The source code is available at https://github.com/ispc-lab/KAM-Net.
KW - Artificial intelligence algorithmic design and analysis
KW - artificial intelligence in transportation
KW - deep learning
KW - supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85132955393&partnerID=8YFLogxK
U2 - 10.1109/TAI.2021.3112945
DO - 10.1109/TAI.2021.3112945
M3 - Article
AN - SCOPUS:85132955393
SN - 2691-4581
VL - 3
SP - 207
EP - 217
JO - IEEE Transactions on Artificial Intelligence
JF - IEEE Transactions on Artificial Intelligence
IS - 2
ER -