Object-Aware Guidance for Autonomous Scene Reconstruction

TL;DR

This paper introduces an object-aware guidance system for autonomous indoor scene reconstruction that balances global exploration and local object scanning, enabling efficient and comprehensive 3D scene understanding.

Contribution

It presents a novel integrated approach combining object segmentation, next best object selection, and view planning for autonomous scene reconstruction.

Findings

Effective object segmentation via multi-class graph cuts

Successful identification and scanning of objects in unknown scenes

Demonstrated feasibility through experiments and comparisons

Abstract

To carry out autonomous 3D scanning and online reconstruction of unknown indoor scenes, one has to find a balance between global exploration of the entire scene and local scanning of the objects within it. In this work, we propose a novel approach, which provides object-aware guidance for autoscanning, for exploring, reconstructing, and understanding an unknown scene within one navigation pass. Our approach interleaves between object analysis to identify the next best object (NBO) for global exploration, and object-aware information gain analysis to plan the next best view (NBV) for local scanning. First, an objectness-based segmentation method is introduced to extract semantic objects from the current scene surface via a multi-class graph cuts minimization. Then, an object of interest (OOI) is identified as the NBO which the robot aims to visit and scan. The robot then conducts fine scanning on the OOI with views determined by the NBV strategy. When the OOI is recognized as a full object, it can be replaced by its most similar 3D model in a shape database. The algorithm iterates until all of the objects are recognized and reconstructed in the scene. Various experiments and comparisons have shown the feasibility of our proposed approach.