Version 1
: Received: 20 September 2024 / Approved: 20 September 2024 / Online: 23 September 2024 (09:06:46 CEST)
How to cite:
Goenawan, C. R.; Paek, D.-H.; Kong, S.-H. See the Unseen: Grid-Wise DA Detection Dataset and Network using LiDAR. Preprints2024, 2024091668. https://doi.org/10.20944/preprints202409.1668.v1
Goenawan, C. R.; Paek, D.-H.; Kong, S.-H. See the Unseen: Grid-Wise DA Detection Dataset and Network using LiDAR. Preprints 2024, 2024091668. https://doi.org/10.20944/preprints202409.1668.v1
Goenawan, C. R.; Paek, D.-H.; Kong, S.-H. See the Unseen: Grid-Wise DA Detection Dataset and Network using LiDAR. Preprints2024, 2024091668. https://doi.org/10.20944/preprints202409.1668.v1
APA Style
Goenawan, C. R., Paek, D. H., & Kong, S. H. (2024). See the Unseen: Grid-Wise DA Detection Dataset and Network using LiDAR. Preprints. https://doi.org/10.20944/preprints202409.1668.v1
Chicago/Turabian Style
Goenawan, C. R., Dong-Hee Paek and Seung-Hyun Kong. 2024 "See the Unseen: Grid-Wise DA Detection Dataset and Network using LiDAR" Preprints. https://doi.org/10.20944/preprints202409.1668.v1
Abstract
Drivable area (DA) detection is crucial for autonomous driving. Camera-based methods heavily rely on lighting conditions and often fail to capture accurate 3D information, while LiDAR-based methods offer accurate 3D data and are less susceptible to lighting conditions. However, existing LiDAR-based methods focus on point-wise detection, prone to occlusion and limited by point cloud sparsity, leading to decreased performance in motion planning and localization. We propose Argoverse-grid, a grid-wise DA detection dataset derived from Argoverse 1, comprising over 13K frames with fine-grained BEV DA labels across various scenarios. We also introduce Grid-DATrNet, a first grid-wise DA detection model utilizing global attention through transformers. Our experiments demonstrate the superiority of Grid-DATrNet over various methods, including both LiDAR and camera-based approaches, in detecting grid-wise DA in the proposed Argoverse-grid dataset. We show that Grid-DATrNet can detect grids even in occluded and unmeasured areas by leveraging contextual and semantic information through global attention, unlike CNN-based DA detection methods. The preprocessing code for Argoverse-grid, experiment code, Grid-DATrNet implementation, and result visualization code will be made available at https://github.com/kaist-avelab/grid-wise-DA.
Keywords
DA Detection; LiDAR; Dataset; Computer Vision; Autonomous Vehicle
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.