Chamelion: Reliable Change Detection for Long-Term LiDAR Mapping in Transient Environments

TL;DR

Chamelion introduces a dual-head neural network for reliable online change detection in long-term LiDAR mapping, effectively handling transient environments with a novel data augmentation strategy that synthesizes structural changes.

Contribution

The paper presents a new dual-head network architecture and a data augmentation method for improved change detection and map maintenance in dynamic environments.

Findings

Effective in real-world construction sites and indoor environments

Generalizes well across diverse scenarios

Enables efficient and accurate map updates

Abstract

Online change detection is crucial for mobile robots to efficiently navigate through dynamic environments. Detecting changes in transient settings, such as active construction sites or frequently reconfigured indoor spaces, is particularly challenging due to frequent occlusions and spatiotemporal variations. Existing approaches often struggle to detect changes and fail to update the map across different observations. To address these limitations, we propose a dual-head network designed for online change detection and long-term map maintenance. A key difficulty in this task is the collection and alignment of real-world data, as manually registering structural differences over time is both labor-intensive and often impractical. To overcome this, we develop a data augmentation strategy that synthesizes structural changes by importing elements from different scenes, enabling effective model training without the need for extensive ground-truth annotations. Experiments conducted at real-world construction sites and in indoor office environments demonstrate that our approach generalizes well across diverse scenarios, achieving efficient and accurate map updates.\resubmit{Our source code and additional material are available at: https://chamelion-pages.github.io/.