Bottleneck Identification to Semantic Segmentation of Industrial 3D Point Cloud Scene via Deep Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Bottleneck Identification to Semantic Segmentation of Industrial 3D Point Cloud Scene via Deep Learning

Résumé

Point cloud acquisition techniques are an essential tool for the digitization of industrial plants, yet the bulk of a designer's work remains manual. A first step to automatize drawing generation is to extract the semantics of the point cloud. Towards this goal, we investigate the use of deep learning to semantically segment oil and gas industrial scenes. We focus on domain characteristics such as high variation of object size, increased concavity and lack of annotated data, which hampers the use of conventional approaches. To address these issues, we advocate the use of synthetic data, adaptive downsampling and context sharing.

Dates et versions

hal-03322996 , version 1 (20-08-2021)

Identifiants

Citer

Romain Cazorla, Line Poinel, Panagiotis Papadakis, Cédric Buche. Bottleneck Identification to Semantic Segmentation of Industrial 3D Point Cloud Scene via Deep Learning. Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), Aug 2021, Montreal, Canada. pp.4877-4878, ⟨10.24963/ijcai.2021/670⟩. ⟨hal-03322996⟩
56 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More