Knowledge Distillation for Traversable Region Detection of LiDAR Scan in Off-Road Environmentsopen access
- Authors
- Kim, Nahyeong; An, Jhonghyun
- Issue Date
- Jan-2024
- Publisher
- MDPI
- Keywords
- knowledge distillation; off-road; LiDAR point cloud; self-driving; point cloud projection; range image
- Citation
- SENSORS, v.24, no.1
- Journal Title
- SENSORS
- Volume
- 24
- Number
- 1
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/90383
- DOI
- 10.3390/s24010079
- ISSN
- 1424-8220
1424-3210
- Abstract
- In this study, we propose a knowledge distillation (KD) method for segmenting off-road environment range images. Unlike urban environments, off-road terrains are irregular and pose a higher risk to hardware. Therefore, off-road self-driving systems are required to be computationally efficient. We used LiDAR point cloud range images to address this challenge. The three-dimensional (3D) point cloud data, which are rich in detail, require substantial computational resources. To mitigate this problem, we employ a projection method to convert the image into a two-dimensional (2D) image format using depth information. Our soft label-based knowledge distillation (SLKD) effectively transfers knowledge from a large teacher network to a lightweight student network. We evaluated SLKD using the RELLIS-3D off-road environment dataset, measuring the performance with respect to the mean intersection of union (mIoU) and GPU floating point operations per second (GFLOPS). The experimental results demonstrate that SLKD achieves a favorable trade-off between mIoU and GFLOPS when comparing teacher and student networks. This approach shows promise for enabling efficient off-road autonomous systems with reduced computational costs.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/90383)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.