Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments

TL;DR

Dynablox is a real-time, online mapping-based method for detecting diverse moving objects in complex environments, robustly handling various object types and scene complexities without relying on appearance assumptions.

Contribution

It introduces a novel free-space estimation approach that enables robust moving object detection in complex scenes without appearance-based assumptions.

Findings

Achieves 86% IoU at 17 FPS in real-world robotic settings.

Outperforms recent appearance-based classifiers.

Approaches offline method performance and generalizes to complex environments.

Abstract

Real-time detection of moving objects is an essential capability for robots acting autonomously in dynamic environments. We thus propose Dynablox, a novel online mapping-based approach for robust moving object detection in complex environments. The central idea of our approach is to incrementally estimate high confidence free-space areas by modeling and accounting for sensing, state estimation, and mapping limitations during online robot operation. The spatio-temporally conservative free space estimate enables robust detection of moving objects without making any assumptions on the appearance of objects or environments. This allows deployment in complex scenes such as multi-storied buildings or staircases, and for diverse moving objects such as people carrying various items, doors swinging or even balls rolling around. We thoroughly evaluate our approach on real-world data sets, achieving 86% IoU at 17 FPS in typical robotic settings. The method outperforms a recent appearance-based classifier and approaches the performance of offline methods. We demonstrate its generality on a novel data set with rare moving objects in complex environments. We make our efficient implementation and the novel data set available as open-source.