ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building

TL;DR

ERASOR is a fast, robust method for removing dynamic objects from 3D point cloud maps in urban environments, improving localization and navigation for mobile vehicles.

Contribution

The paper introduces ERASOR, a novel pseudo occupancy-based approach that effectively discriminates static from dynamic points using ground contact assumptions.

Findings

Outperforms state-of-the-art methods on SemanticKITTI dataset.

Effectively removes dynamic objects, enhancing static map quality.

Robust to motion ambiguity in urban environments.

Abstract

Scan data of urban environments often include representations of dynamic objects, such as vehicles, pedestrians, and so forth. However, when it comes to constructing a 3D point cloud map with sequential accumulations of the scan data, the dynamic objects often leave unwanted traces in the map. These traces of dynamic objects act as obstacles and thus impede mobile vehicles from achieving good localization and navigation performances. To tackle the problem, this paper presents a novel static map building method called ERASOR, Egocentric RAtio of pSeudo Occupancy-based dynamic object Removal, which is fast and robust to motion ambiguity. Our approach directs its attention to the nature of most dynamic objects in urban environments being inevitably in contact with the ground. Accordingly, we propose the novel concept called pseudo occupancy to express the occupancy of unit space and then discriminate spaces of varying occupancy. Finally, Region-wise Ground Plane Fitting (R-GPF) is adopted to distinguish static points from dynamic points within the candidate bins that potentially contain dynamic points. As experimentally verified on SemanticKITTI, our proposed method yields promising performance against state-of-the-art methods overcoming the limitations of existing ray tracing-based and visibility-based methods.