Název:	MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds
Autoři:	Luo, Chuanyu Li, Xiaohan Cheng, Nuo Li, Pu
Datum vydání:	2022
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	článek article
URI:	http://hdl.handle.net/11025/49388
ISSN:	1213-6972 (print) 1213-6964 (on-line)
Klíčová slova:	mračno bodů;sémantická segmentace;křivky vyplňující prostor;konvoluční neuronové sítě
Klíčová slova v dalším jazyce:	point cloud;semantic segmentation;space filling curves;convolutional neural networks
Abstrakt v dalším jazyce:	Semantic segmentation of 3D point cloud is an essential task for autonomous driving environment perception. The pipeline of most pointwise point cloud semantic segmentation methods includes points sampling, neighbor searching, feature aggregation, and classification. Neighbor searching method like K-nearest neighbors algorithm, KNN, has been widely applied. However, the complexity of KNN is always a bottleneck of efficiency. In this paper, we propose an end-to-end neural architecture, Multiple View Pointwise Net, MVP-Net, to efficiently and directly infer large-scale outdoor point cloud without KNN or any complex pre/postprocessing. Instead, assumption-based space filling curves and multi-rotation of point cloud methods are introduced to point feature aggregation and receptive field expanding. Numerical experiments show that the proposed MVP-Net is 11 times faster than the most efficient pointwise semantic segmentation method RandLA-Net [Qin20a] and achieves the same accuracy on the large-scale benchmark SemanticKITTI dataset.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	Volume 30, Number 1-2 (2021)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.