PlaneSDF-based Change Detection for Long-term Dense Mapping

TL;DR

This paper introduces a novel change detection method for long-term dense mapping using PlaneSDF, which models environments as collections of planes and SDF volumes, enabling effective detection of environmental changes over multiple sessions.

Contribution

The paper proposes a new PlaneSDF-based approach for change detection that combines plane registration, height map comparison, and 3D geometric validation, advancing long-term environment understanding.

Findings

Effective change detection demonstrated on synthetic and real datasets.

Improved accuracy in detecting changed objects over multiple sessions.

Robustness of PlaneSDF representation in long-term mapping scenarios.

Abstract

The ability to process environment maps across multiple sessions is critical for robots operating over extended periods of time. Specifically, it is desirable for autonomous agents to detect changes amongst maps of different sessions so as to gain a conflict-free understanding of the current environment. In this paper, we look into the problem of change detection based on a novel map representation, dubbed Plane Signed Distance Fields (PlaneSDF), where dense maps are represented as a collection of planes and their associated geometric components in SDF volumes. Given point clouds of the source and target scenes, we propose a three-step PlaneSDF-based change detection approach: (1) PlaneSDF volumes are instantiated within each scene and registered across scenes using plane poses; 2D height maps and object maps are extracted per volume via height projection and connected component analysis. (2) Height maps are compared and intersected with the object map to produce a 2D change location mask for changed object candidates in the source scene. (3) 3D geometric validation is performed using SDF-derived features per object candidate for change mask refinement. We evaluate our approach on both synthetic and real-world datasets and demonstrate its effectiveness via the task of changed object detection. Supplementary video: https://youtu.be/oh-MQPWTwZI