Semantic Segmentation and Building Extraction from Airborne LiDAR Data with Multiple Return Using PointNet++

Young-Ha Shin,Dong-Cheon Lee,Kyung-Wahn Son

doi:10.3390/app12041975

Abstract

Light detection and ranging (LiDAR) data of 3D point clouds acquired from laser sensors is a crucial form of geospatial data for recognition of complex objects since LiDAR data provides geometric information in terms of 3D coordinates with additional attributes such as intensity and multiple returns. In this paper, we focused on utilizing multiple returns in the training data for semantic segmentation, in particular building extraction using PointNet++. PointNet++ is known as one of the efficient and robust deep learning (DL) models for processing 3D point clouds. On most building boundaries, two returns of the laser pulse occur. The experimental results demonstrated that the proposed approach could improve building extraction by adding two returns to the training datasets. Specifically, the recall value of the predicted building boundaries for the test data was improved from 0.7417 to 0.7948 for the best case. However, no significant improvement was achieved for the new data because the new data had relatively lower point density compared to the training and test data.

Highlights

Airborne laser scanner (ALS) systems have become the most important geospatial data acquisition technology since the mid-1990s
Two Light detection and ranging (LiDAR) data were selected from the Dayton Annotated Laser Earth Scan (DALES) datasets as test data, and two LiDAR
Even though the aerial images were not involved in training PointNet++, they are presented for the purpose of identifying regional characteristics and visually analyzing semantic segmentation results

Summary

Introduction

Airborne laser scanner (ALS) systems have become the most important geospatial data acquisition technology since the mid-1990s. Light detection and ranging (LiDAR) data obtained from the ALS provides geometric information in terms of 3D coordinates (i.e., X, Y, and Z coordinates) and additional data including intensity, return number, scan direction and angle, classification, and global positioning system (GPS) time. Unlike optical imagery, LiDAR data can be collected regardless of the Sun’s illumination and weather conditions. 3D geospatial data contains richer information, such as geometric characteristics of the objects, to represent the real world in comparison with 2D imagery. Point clouds including LiDAR are widely used simple form of 3D data that basically consists of

Objectives

Results

Conclusion