.png){kind=icon}
.png){kind=icon}
Return
EfficientLPS: Efficient LiDAR Panoptic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TRO.2021.3122069.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either combining independent task-specific networks or translating methods from the image domain ignoring the intricacies of LiDAR data and thus often resulting in suboptimal performance. In this article, we present the novel top-down efficient LiDAR panoptic segmentation (EfficientLPS) architecture that addresses multiple challenges in segmenting LiDAR point clouds, including distance-dependent sparsity, severe occlusions, large scale-variations, and reprojection errors. EfficientLPS comprises of a novel shared backbone that encodes with strengthened geometric transformation modeling capacity and aggregates semantically rich range-aware multiscale features. It incorporates new scale-invariant semantic and instance segmentation heads along with the panoptic fusion module which is supervised by our proposed panoptic periphery loss function. Additionally, we formulate a regularized pseudolabeling framework to further improve the performance of EfficientLPS by training on unlabeled data. We benchmark our proposed model on two large-scale LiDAR datasets: nuScenes, for which we also provide ground truth annotations, and SemanticKITTI. Notably, EfficientLPS sets the new state-of-the-art on both these datasets.
Keywords:
Laser radar
Image segmentation
Semantics
Task analysis
Phase change materials
Convolutional codes
Solid modeling
Instance segmentation
panoptic segmentation
scene understanding
semantic segmentation
Journal
IF:
10.5
Papers:
3.3K
Citations:
2.8W