Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Off-Road LiDAR Intensity Based Semantic Segmentation

Kasi Viswanath, Peng Jiang, Sujit PB, Srikanth Saripalli

TL;DR

This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks.

Abstract

LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes machine learning techniques to automatically classify objects and regions in LiDAR point clouds. Learning-based models struggle in off-road environments due to the presence of diverse objects with varying colors, textures, and undefined boundaries, which can lead to difficulties in accurately classifying and segmenting objects using traditional geometric-based features. In this paper, we address this problem by harnessing the LiDAR intensity parameter to enhance object segmentation in off-road environments. Our approach was evaluated in the RELLIS-3D data set and yielded promising results as a preliminary analysis with improved mIoU for classes "puddle" and "grass" compared to more complex deep learning-based benchmarks. The methodology was evaluated for compatibility across both Velodyne and Ouster LiDAR systems, assuring its cross-platform applicability. This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks. https://github.com/MOONLABIISERB/lidar-intensity-predictor/tree/main

Off-Road LiDAR Intensity Based Semantic Segmentation

TL;DR

This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks.

Abstract

LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes machine learning techniques to automatically classify objects and regions in LiDAR point clouds. Learning-based models struggle in off-road environments due to the presence of diverse objects with varying colors, textures, and undefined boundaries, which can lead to difficulties in accurately classifying and segmenting objects using traditional geometric-based features. In this paper, we address this problem by harnessing the LiDAR intensity parameter to enhance object segmentation in off-road environments. Our approach was evaluated in the RELLIS-3D data set and yielded promising results as a preliminary analysis with improved mIoU for classes "puddle" and "grass" compared to more complex deep learning-based benchmarks. The methodology was evaluated for compatibility across both Velodyne and Ouster LiDAR systems, assuring its cross-platform applicability. This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks. https://github.com/MOONLABIISERB/lidar-intensity-predictor/tree/main
Paper Structure (9 sections, 6 equations, 10 figures, 1 table)

This paper contains 9 sections, 6 equations, 10 figures, 1 table.

Table of Contents

  1. Introduction
  2. LiDAR Intensity Calibration
  3. Range Dependence
  4. Intensity Correction for Large Range
  5. Angle of Incidence Dependence
  6. Experiments and Results
  7. Pre-Processing Velodyne Intensity data.
  8. Experimental Insights
  9. Conclusions

Figures (10)

  • Figure 1: Segmentation Results on RELLIS-3D dataset.
  • Figure 2: (a) Raw Intensity vs Range of Grass (b) Intensity calibrated for $\alpha$ vs Range.
  • Figure 3: Interaction of laser beam with surface at different angle of incidence
  • Figure 4: (a) Raw Intensity vs $\alpha$ of Grass at different ranges (b) Raw intensity vs $\alpha$ for different classes at 10 meters range. The segregation of intensity values for different classes is observed.
  • Figure 5: Calibrated Intensity ranges of different classes.
  • ...and 5 more figures