Unsupervised Machine Learning for Detecting and Locating Human-Made Objects in 3D Point Cloud

TL;DR

Experimental results demonstrate that the proposed ground filtering method outperforms previous techniques, and the LIE method successfully distinguishes between points representing trees and human-made objects.

Abstract

A 3D point cloud is an unstructured, sparse, and irregular dataset, typically collected by airborne LiDAR systems over a geological region. Laser pulses emitted from these systems reflect off objects both on and above the ground, resulting in a dataset containing the longitude, latitude, and elevation of each point, as well as information about the corresponding laser pulse strengths. A widely studied research problem, addressed in many previous works, is ground filtering, which involves partitioning the points into ground and non-ground subsets. This research introduces a novel task: detecting and identifying human-made objects amidst natural tree structures. This task is performed on the subset of non-ground points derived from the ground filtering stage. Marked Point Fields (MPFs) are used as models well-suited to these tasks. The proposed methodology consists of three stages: ground filtering, local information extraction (LIE), and clustering. In the ground filtering stage, a statistical method called One-Sided Regression (OSR) is introduced, addressing the limitations of prior ground filtering methods on uneven terrains. In the LIE stage, unsupervised learning methods are lacking. To mitigate this, a kernel-based method for the Hessian matrix of the MPF is developed. In the clustering stage, the Gaussian Mixture Model (GMM) is applied to the results of the LIE stage to partition the non-ground points into trees and human-made objects. The underlying assumption is that LiDAR points from trees exhibit a three-dimensional distribution, while those from human-made objects follow a two-dimensional distribution. The Hessian matrix of the MPF effectively captures this distinction. Experimental results demonstrate that the proposed ground filtering method outperforms previous techniques, and the LIE method successfully distinguishes between points representing trees and human-made objects.

Figures (11)

• Figure 1: An aircraft equipped with an airborne Lidar system flying over a geological region.
• Figure 2: 3D point cloud for (a) a car beneath a tree; (b) a house beneath a tree
• Figure 3: Scatter plots for the logarithms of the ratios of localized eigenvalues for selected points in Figure 2
• Figure 4: (a) Satellite map of an airborne LiDAR dataset from a region in West Lafayette, Indiana; (b) original labels for ground points (yellow) and nonground points (red).
• Figure 5: (a) Unsupervised ML/AL for human-made objects (yellow) and trees (red) derived by combining our proposed LIE method with the previous GMM method (the clustering stage) for the nonground points in Figure \ref{['fig:satellite map city']}(b); (b) Histogram showing the percentage of the elevations for ground (yellow) and nonground (red) points in Figure \ref{['fig:satellite map city']}(b).