English

Implicit neural representation for change detection

Computer Vision and Pattern Recognition 2023-08-31 v2 Machine Learning Image and Video Processing

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.

Keywords

Cite

@article{arxiv.2307.15428,
  title  = {Implicit neural representation for change detection},
  author = {Peter Naylor and Diego Di Carlo and Arianna Traviglia and Makoto Yamada and Marco Fiorucci},
  journal= {arXiv preprint arXiv:2307.15428},
  year   = {2023}
}

Comments

Main article is 10 pages + 6 pages of supplementary. Conference style paper

R2 v1 2026-06-28T11:42:42.794Z