Real-time Semantic 3D Dense Occupancy Mapping with Efficient Free Space Representations

TL;DR

This paper introduces a real-time semantic 3D occupancy mapping framework that uses novel free space representations to enhance speed and handle dynamic environments, suitable for deployment on standard CPUs.

Contribution

It presents two new free space representations that improve mapping efficiency and enables real-time semantic mapping on consumer-grade hardware.

Findings

Achieves real-time mapping on a CPU

Handles dynamic scenarios effectively

Improves mapping speed with novel free space representations

Abstract

A real-time semantic 3D occupancy mapping framework is proposed in this paper. The mapping framework is based on the Bayesian kernel inference strategy from the literature. Two novel free space representations are proposed to efficiently construct training data and improve the mapping speed, which is a major bottleneck for real-world deployments. Our method achieves real-time mapping even on a consumer-grade CPU. Another important benefit is that our method can handle dynamic scenarios, thanks to the coverage completeness of the proposed algorithm. Experiments on real-world point cloud scan datasets are presented.