Dynamic Semantic Occupancy Mapping Using 3D Scene Flow and Closed-Form Bayesian Inference

doi:10.1109/ACCESS.2022.3205329

Dynamic Semantic Occupancy Mapping Using 3D Scene Flow and Closed-Form Bayesian Inference

2022-01-01

3

OA

AI

A

Aishwarya Unnikrishnan

DOI：10.1109/ACCESS.2022.3205329

Original

Original request for help

Save

Abstract

En 中文

This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment can cause artifacts and traces in current mapping algorithms, leading to an inconsistent map posterior. We leverage state-of-the-art semantic segmentation and 3D flow estimation using deep learning to provide measurements for map inference. We develop a Bayesian model that propagates the scene with flow and infers a 3D continuous (i.e., can be queried at arbitrary resolution) semantic occupancy map outperforming its static counterpart. Extensive experiments using publicly available data sets show that the proposed framework improves over its predecessors and input measurements from deep neural networks consistently.

Keywords:

Semantics

Bayes methods

Three-dimensional displays

Heuristic algorithms

Dynamics

Vehicle dynamics

Simultaneous localization and mapping

Inference

Computer vision

Image analysis

Bayesian inference

computer vision

mapping

semantic scene understanding

Dynamic Semantic Occupancy Mapping Using 3D Scene Flow and Closed-Form Bayesian Inference

Abstract

Journal

Organization