SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving
This addresses the need for efficient and accurate perception in autonomous driving systems, representing an incremental improvement with a novel auto-labeling method to overcome data scarcity.
The paper tackles the problem of semantic segmentation of 3D LiDAR point clouds for autonomous driving by introducing SalsaNet, a deep encoder-decoder network that segments road and vehicles, achieving state-of-the-art accuracy and faster computation time on the KITTI dataset.
In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic segmentation of 3D LiDAR point clouds. SalsaNet segments the road, i.e. drivable free-space, and vehicles in the scene by employing the Bird-Eye-View (BEV) image projection of the point cloud. To overcome the lack of annotated point cloud data, in particular for the road segments, we introduce an auto-labeling process which transfers automatically generated labels from the camera to LiDAR. We also explore the role of imagelike projection of LiDAR data in semantic segmentation by comparing BEV with spherical-front-view projection and show that SalsaNet is projection-agnostic. We perform quantitative and qualitative evaluations on the KITTI dataset, which demonstrate that the proposed SalsaNet outperforms other state-of-the-art semantic segmentation networks in terms of accuracy and computation time. Our code and data are publicly available at https://gitlab.com/aksoyeren/salsanet.git.