2D–3D geometric fusion network using multi-neighbourhood graph convolution for RGB-D indoor scene classification

Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that...

Descripción completa

Detalles Bibliográficos
Autores: Mosella Montoro, Albert, Ruiz Hidalgo, Javier|||0000-0001-6774-685X
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/346435
Acceso en línea:https://hdl.handle.net/2117/346435
https://dx.doi.org/10.1016/j.inffus.2021.05.002
Access Level:acceso abierto
Palabra clave:Neural networks (Computer science)
Multisensor data fusion
Convolutional Graph Neural Network
Multi-modal fusion
Multi-Neighbourhood Graph Neural Network
Indoor scene classification
RGB-D
Xarxes neuronals (Informàtica)
Fusió d'imatges
Descripción
Sumario:Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that uses two novel layers is proposed. The first layer, Multi-Neighbourhood Graph Convolution, aims to learn a more robust geometric descriptor of the scene combining two different neighbourhoods: one in the Euclidean space and the other in the Feature space. The second proposed layer, Nearest Voxel Pooling, improves the performance of the well-known Voxel Pooling. Experimental results, using NYU-Depth-V2 and SUN RGB-D datasets, show that the proposed method outperforms the current state-of-the-art in RGB-D indoor scene classification task.