Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization

TL;DR

This paper introduces a CNN-based method for outdoor place categorization using panoramic LiDAR data, demonstrating superior performance with a new large-scale dataset and analyzing learned features.

Contribution

It presents a novel CNN approach for outdoor place categorization using panoramic LiDAR data and introduces the MPO dataset for this task.

Findings

Outperforms traditional methods on MPO dataset

Utilizes both depth and reflectance modalities effectively

Visualizes learned features for analysis

Abstract

Semantic place categorization, which is one of the essential tasks for autonomous robots and vehicles, allows them to have capabilities of self-decision and navigation in unfamiliar environments. In particular, outdoor places are more difficult targets than indoor ones due to perceptual variations, such as dynamic illuminance over twenty-four hours and occlusions by cars and pedestrians. This paper presents a novel method of categorizing outdoor places using convolutional neural networks (CNNs), which take omnidirectional depth/reflectance images obtained by 3D LiDARs as the inputs. First, we construct a large-scale outdoor place dataset named Multi-modal Panoramic 3D Outdoor (MPO) comprising two types of point clouds captured by two different LiDARs. They are labeled with six outdoor place categories: coast, forest, indoor/outdoor parking, residential area, and urban area. Second, we provide CNNs for LiDAR-based outdoor place categorization and evaluate our approach with the MPO dataset. Our results on the MPO dataset outperform traditional approaches and show the effectiveness in which we use both depth and reflectance modalities. To analyze our trained deep networks we visualize the learned features.