CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation

Guofeng Tong,Guiqiu Xiang,Qi Sun,Yong Li,Wei Cao,Dong Chen

doi:10.1109/access.2020.2992612

Guofeng Tong, Guiqiu Xiang + Show 4 more

Open Access

https://doi.org/10.1109/access.2020.2992612

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 76	License type: CC BY 4.0

Affiliation: Nanjing Forestry University, Northeastern University

Abstract

Large-scale point clouds scanned by light detection and ranging (lidar) sensors provide detailed geometric characteristics of scenes due to the provision of 3D structural data. The semantic segmentation of large-scale point clouds is a crucial step for an in-depth understanding of complex scenes. Of late, although a large number of point cloud semantic segmentation algorithms have been proposed, semantic segmentation methods are still far from being satisfactory in terms of precision and accuracy of large-scale point clouds. For machine learning (ML) and deep learning (DL) methodologies, the semantic segmentation is largely influenced by the quality of training sets and methods themselves. Therefore, we construct a new point cloud dataset, namely CSPC-Dataset (Complex Scene Point Cloud Dataset) for large-scale scene semantic segmentation. CSPC-Dataset point clouds are acquired by a wearable laser mobile mapping robot. It covers five complex urban and rural scenes and mainly includes six types of objects, i.e., ground, car, building, vegetation, bridge, and pole. It provides large-scale outdoor scenes with color information, which has advantages such as the scene more complete, point density relatively uniform, diversity and complexity of objects and the high discrepancy between different scenes. Based on the CSPC-Dataset, we construct a new benchmark, which includes approximately 68 million points with explicit semantic labels. To extend the dataset into a wide range of applications, this paper provides the semantic segmentation results and comparative analysis of 7 baseline methods based on CSPC-Dataset. In the experiment part, three groups of experiments are conducted for benchmarking, which offers an effective way to make comparisons with different point-labeling algorithms. The labeling results have shown that the highest Intersection over Union (IoU) of pole, ground, building, car, vegetation, and bridge for all benchmarks is 36.0%, 97.8%, 93.7%, 65.6%, 92.0%, and 69.6%.

Highlights

In recent years, machine learning (ML) and deep learning (DL) algorithms have achieved excellent performance in many fields
This paper aims to exploit the advantages of wearable laser scanning (WLS) point clouds and establishes a more challenging large-scale point cloud dataset for point cloud-based scene semantic segmentation
We provide a detailed comparison of seven representative methods to establish a benchmark and reference for investigating large-scale point cloud semantic segmentation

Summary

Introduction

Machine learning (ML) and deep learning (DL) algorithms have achieved excellent performance in many fields. To the best of our knowledge, the applications of deep learning methods rely on a large number of data with labeled information for model learning. The associate editor coordinating the review of this manuscript and approving it for publication was Sudipta Roy. the development of deep learning algorithms. ImageNet [1], Pascal VOC [2] and COCO [3] play an important role in the development of deep learning algorithms in the field of 2D vision.

Objectives

Methods

Results

Conclusion