Multi-modal panoramic 3D outdoor datasets for place categorization

TL;DR

This paper introduces two multi-modal panoramic 3D outdoor datasets for semantic place categorization, featuring dense and sparse point clouds, and evaluates several categorization approaches with high accuracy.

Contribution

The creation of two new large-scale multi-modal panoramic 3D datasets for outdoor place categorization, with comprehensive evaluation of different methods.

Findings

Achieved 96.42% accuracy with dense point cloud data.

Achieved 89.67% accuracy with sparse point cloud data.

Datasets are publicly available for research use.

Abstract

We present two multi-modal panoramic 3D outdoor (MPO) datasets for semantic place categorization with six categories: forest, coast, residential area, urban area and indoor/outdoor parking lot. The first dataset consists of 650 static panoramic scans of dense (9,000,000 points) 3D color and reflectance point clouds obtained using a FARO laser scanner with synchronized color images. The second dataset consists of 34,200 real-time panoramic scans of sparse (70,000 points) 3D reflectance point clouds obtained using a Velodyne laser scanner while driving a car. The datasets were obtained in the city of Fukuoka, Japan and are publicly available in [1], [2]. In addition, we compare several approaches for semantic place categorization with best results of 96.42% (dense) and 89.67% (sparse).