Automatic Building Outline Extraction from ALS Point Clouds by Ordered Points Aided Hough Transform

Elyta Widyaningrum,Ben Gorte,Roderik Lindenbergh

doi:10.3390/rs11141727

Abstract

Many urban applications require building polygons as input. However, manual extraction from point cloud data is time- and labor-intensive. Hough transform is a well-known procedure to extract line features. Unfortunately, current Hough-based approaches lack flexibility to effectively extract outlines from arbitrary buildings. We found that available point order information is actually never used. Using ordered building edge points allows us to present a novel ordered points–aided Hough Transform (OHT) for extracting high quality building outlines from an airborne LiDAR point cloud. First, a Hough accumulator matrix is constructed based on a voting scheme in parametric line space (θ, r). The variance of angles in each column is used to determine dominant building directions. We propose a hierarchical filtering and clustering approach to obtain accurate line based on detected hotspots and ordered points. An Ordered Point List matrix consisting of ordered building edge points enables the detection of line segments of arbitrary direction, resulting in high-quality building roof polygons. We tested our method on three different datasets of different characteristics: one new dataset in Makassar, Indonesia, and two benchmark datasets in Vaihingen, Germany. To the best of our knowledge, our algorithm is the first Hough method that is highly adaptable since it works for buildings with edges of different lengths and arbitrary relative orientations. The results prove that our method delivers high completeness (between 90.1% and 96.4%) and correctness percentages (all over 96%). The positional accuracy of the building corners is between 0.2–0.57 m RMSE. The quality rate (89.6%) for the Vaihingen-B benchmark outperforms all existing state of the art methods. Other solutions for the challenging Vaihingen-A dataset are not yet available, while we achieve a quality score of 93.2%. Results with arbitrary directions are demonstrated on the complex buildings around the EYE museum in Amsterdam.

Highlights

The detection of straight and accurate building outlines is essential for urban mapping applications like 3D city modeling, disaster management, cadaster, and taxation
This study proposes a new method to extract accurate building outlines from ALS (Airborne Laser Scanner) point clouds automatically using an extension of Hough transform that exploits lists of ordered points to define line segments and corners
Goal of this study is to provide a robust procedure for automatic building outline extraction from airborne LiDAR point clouds

Summary

Introduction

The detection of straight and accurate building outlines is essential for urban mapping applications like 3D city modeling, disaster management, cadaster, and taxation. To accommodate the high demand of various applications, accurate building outline extraction requires an automated procedure. As LiDAR is able to provide accurate three-dimensional (x, y, z) point clouds free from relief displacement, the use of LiDAR data to extract building polygons automatically has become a key target for researchers and practitioners within the geospatial industry. Efforts on building outline extraction were conducted on the combination of LiDAR point clouds and aerial images to use each of their advantages. To fuse different input data is not easy as building representations may suffer from relief displacement or building distortion in image scenes [3]. The geometric position of images and LiDAR point clouds hardly match

Objectives

Methods

Results

Conclusion