Location-Guided LiDAR-Based Panoptic Segmentation for Autonomous Driving

Abstract

The application of artificial intelligence in autonomous driving is becoming increasingly extensive. LiDAR-based 3D point cloud panoptic segmentation is one of the most promising and arduous tasks. Although recent methods have produced promising results, most of them ignore the prior distribution of objects in the 3D point clouds. In this paper, we first investigate the distribution of objects around the heading of vehicles and observe that several objects are severely biased. On the basis of this observation, we use the bird's eye view (BEV) representation to project the 3D point clouds into a 2D image and divide the BEV projection into eight areas. For each area, we apply input-dependent convolution kernels to extract the local feature. These local features are concatenated to the panoptic backbone for panoptic segmentation. We validate our method on the validation and test sets of the SemanticKITTI dataset. The proposed method outperforms all state-of-the-art methods based on 2D projection in terms of higher panoptic quality scores.