Moving Object Segmentation in Point Cloud Data using Hidden Markov Models

TL;DR

This paper introduces a robust, learning-free method for segmenting moving objects in point cloud data using Hidden Markov Models, demonstrating superior performance across diverse datasets and environments.

Contribution

The paper presents a novel HMM-based approach for moving object segmentation in point clouds that does not rely on learning, offering strong generalization and robustness.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Demonstrates robustness across different sensors and environments

Provides an open-source implementation for reproducibility

Abstract

Autonomous agents require the capability to identify dynamic objects in their environment for safe planning and navigation. Incomplete and erroneous dynamic detections jeopardize the agent's ability to accomplish its task. Dynamic detection is a challenging problem due to the numerous sources of uncertainty inherent in the problem's inputs and the wide variety of applications, which often lead to use-case-tailored solutions. We propose a robust learning-free approach to segment moving objects in point cloud data. The foundation of the approach lies in modelling each voxel using a hidden Markov model (HMM), and probabilistically integrating beliefs into a map using an HMM filter. The proposed approach is tested on benchmark datasets and consistently performs better than or as well as state-of-the-art methods with strong generalized performance across sensor characteristics and environments. The approach is open-sourced at https://github.com/vb44/HMM-MOS.