Optimal Transport for Change Detection on LiDAR Point Clouds
This addresses the problem of detecting changes in LiDAR data for applications like urban monitoring, without requiring labeled data or DEMs, though it is incremental as it builds on existing optimal transport techniques.
The authors tackled the problem of unsupervised change detection in LiDAR point clouds, which is challenging due to mismatched spatial support and noise, by proposing a method based on unbalanced optimal transport. Their approach outperformed previous state-of-the-art unsupervised methods by a significant margin, as demonstrated on public datasets for urban monitoring.
Unsupervised change detection between airborne LiDAR data points, taken at separate times over the same location, can be difficult due to unmatching spatial support and noise from the acquisition system. Most current approaches to detect changes in point clouds rely heavily on the computation of Digital Elevation Models (DEM) images and supervised methods. Obtaining a DEM leads to LiDAR informational loss due to pixelisation, and supervision requires large amounts of labelled data often unavailable in real-world scenarios. We propose an unsupervised approach based on the computation of the transport of 3D LiDAR points over two temporal supports. The method is based on unbalanced optimal transport and can be generalised to any change detection problem with LiDAR data. We apply our approach to publicly available datasets for monitoring urban sprawling in various noise and resolution configurations that mimic several sensors used in practice. Our method allows for unsupervised multi-class classification and outperforms the previous state-of-the-art unsupervised approaches by a significant margin.