On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments

TL;DR

This paper presents a bottom-up method for inferring support relations and constructing scene hierarchy graphs from point cloud data in clustered environments, enhancing 3D scene understanding for robotics.

Contribution

It introduces a novel approach that infers support relations and builds scene hierarchy graphs using spatial topology, primitive classification, and a bottom-up inference process.

Findings

High accuracy in primitive classification and support relation inference

Scene hierarchy graphs contain detailed geometric and topological info

Method demonstrates scalability and effectiveness in 3D scene understanding

Abstract

Over the years, scene understanding has attracted a growing interest in computer vision, providing the semantic and physical scene information necessary for robots to complete some particular tasks autonomously. In 3D scenes, rich spatial geometric and topological information are often ignored by RGB-based approaches for scene understanding. In this study, we develop a bottom-up approach for scene understanding that infers support relations between objects from a point cloud. Our approach utilizes the spatial topology information of the plane pairs in the scene, consisting of three major steps. 1) Detection of pairwise spatial configuration: dividing primitive pairs into local support connection and local inner connection; 2) primitive classification: a combinatorial optimization method applied to classify primitives; and 3) support relations inference and hierarchy graph construction: bottom-up support relations inference and scene hierarchy graph construction containing primitive level and object level. Through experiments, we demonstrate that the algorithm achieves excellent performance in primitive classification and support relations inference. Additionally, we show that the scene hierarchy graph contains rich geometric and topological information of objects, and it possesses great scalability for scene understanding.