Unsupervised discovery of 3D structural elements for scanned indoor scenes

Antić, Miloš (avtor), Zdešar, Andrej (avtor), Iglesias Martínez, José Antonio (avtor), Sanchis, Araceli (avtor), Škrjanc, Igor (avtor)

This paper addresses the growing demand for effective 3D sensing applications by presenting a comprehensive point cloud segmentation method developed for large indoor spaces. Our approach recognises the challenges associated with (un)ordered data and presents a robust algorithm capable of dealing with irregularities caused by measurement inaccuracies, e.g. occlusion, noise, outliers and discontinuous data transitions. The method uses a multi-step filtering approach that sequentially navigates through Gaussian map, distance space and regular grid representations. Connected component analysis, structural rules and assumptions guide the unsupervised clustering of structural elements (SEs), e.g. walls, ceilings and floors. The method is adaptable to various datasets, including joint 2D-3D datasets such as true RGB-D data. A colour metric is introduced to account for illumination effects during scanning and to ensure the generalisability of the method. The importance of detecting SEs lies in their role as input to deep neural networks, which improve the accuracy of SLAM algorithms and influence the quality of subsequent indoor residual object detection. This paper introduces density-based clustering of objects using colour similarity measures and low-level features to further refine the segmentation by eliminating outliers and improving the detection of sharp shapes. The proposed method represents a sophisticated and versatile solution that overcomes scene complexity and makes an important contribution to applications in scene understanding, SLAM and indoor object recognition.

• Jezik: Angleški jezik
• Ključne besede: point cloud, unsupervised search, statistical clustering, harmonic interpolation, structural elements, objects
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2025
• Št. strani: 19 str.
• Številčenje: Vol. 170, art. 112680
• PID: 20.500.12556/RUL-166687
• UDK: 681.5:004
• ISSN pri članku: 1568-4946
• DOI: 10.1016/j.asoc.2024.112680
• COBISS.SI-ID: 223324163
• Datum objave v RUL: 21.01.2025

Gradivo je del revije

• Naslov: Applied soft computing
• Založnik: Elsevier
• ISSN: 1568-4946
• COBISS.SI-ID: 16080679

Licence

• Licenca: CC BY-NC-ND 4.0, Creative Commons Priznanje avtorstva-Nekomercialno-Brez predelav 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by-nc-nd/4.0/deed.sl
• Opis: Najbolj omejujoča licenca Creative Commons. Uporabniki lahko prenesejo in delijo delo v nekomercialne namene in ga ne smejo uporabiti za nobene druge namene.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: oblak točk, nenadzorovano iskanje, statistično rojenje, harmonična interpolacija, strukturni elementi, objekti

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P2-0219
• Naslov: Modeliranje, simulacija in vodenje procesov