Implicit neural representation for change detection

TL;DR

This paper introduces an unsupervised implicit neural representation method for change detection in 3D LiDAR point clouds, improving accuracy and robustness over existing supervised approaches, and demonstrating practical utility in archaeological site monitoring.

Contribution

It proposes a novel unsupervised framework combining INR and Gaussian Mixture Models for effective change detection in noisy, multi-resolution 3D point clouds.

Findings

Outperforms state-of-the-art by 10% in IoU metric on benchmark datasets.

Effectively detects changes across varying resolutions and noise levels.

Successfully applied to real-world archaeological site monitoring.

Abstract

Identifying changes in a pair of 3D aerial LiDAR point clouds, obtained during two distinct time periods over the same geographic region presents a significant challenge due to the disparities in spatial coverage and the presence of noise in the acquisition system. The most commonly used approaches to detecting changes in point clouds are based on supervised methods which necessitate extensive labelled data often unavailable in real-world applications. To address these issues, we propose an unsupervised approach that comprises two components: Implicit Neural Representation (INR) for continuous shape reconstruction and a Gaussian Mixture Model for categorising changes. INR offers a grid-agnostic representation for encoding bi-temporal point clouds, with unmatched spatial support that can be regularised to enhance high-frequency details and reduce noise. The reconstructions at each timestamp are compared at arbitrary spatial scales, leading to a significant increase in detection capabilities. We apply our method to a benchmark dataset comprising simulated LiDAR point clouds for urban sprawling. This dataset encompasses diverse challenging scenarios, varying in resolutions, input modalities and noise levels. This enables a comprehensive multi-scenario evaluation, comparing our method with the current state-of-the-art approach. We outperform the previous methods by a margin of 10% in the intersection over union metric. In addition, we put our techniques to practical use by applying them in a real-world scenario to identify instances of illicit excavation of archaeological sites and validate our results by comparing them with findings from field experts.