Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes

Real-time acquisition and intelligent classification of pole-like street-object point clouds are of great significance in the construction of smart cities. Efficient point cloud processing technology in road scenes can accelerate the development of intelligent transportation and promote the developm...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ziyang Wang, Lin Yang, Yehua Sheng, Mi Shen
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/a01c54f8799d4d0095cfb7e4e43b2012
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a01c54f8799d4d0095cfb7e4e43b2012
record_format dspace
spelling oai:doaj.org-article:a01c54f8799d4d0095cfb7e4e43b20122021-11-11T18:55:05ZPole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes10.3390/rs132143822072-4292https://doaj.org/article/a01c54f8799d4d0095cfb7e4e43b20122021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4382https://doaj.org/toc/2072-4292Real-time acquisition and intelligent classification of pole-like street-object point clouds are of great significance in the construction of smart cities. Efficient point cloud processing technology in road scenes can accelerate the development of intelligent transportation and promote the development of high-precision maps. However, available algorithms have the problems of incomplete extraction and the low recognition accuracy of pole-like objects. In this paper, we propose a segmentation method of pole-like objects under geometric structural constraints. As for classification, we fused the classification results at different scales with each other. First, the point cloud data excluding ground point clouds were divided into voxels, and the rod-shaped parts of the pole-like objects were extracted according to the vertical continuity. Second, the regional growth based on the voxel was carried out based on the rod part to retain the non-rod part of the pole-like objects. A one-way double coding strategy was adopted to preserve the details. For spatial overlapping entities, we used multi-rule supervoxels to divide them. Finally, the random forest model was used to classify the pole-like objects based on local- and global-scale features and to fuse the double classification results under the different scales in order to obtain the final result. Experiments showed that the proposed method can effectively extract the pole-like objects of the point clouds in the road scenes, indicating that the method can achieve high-precision classification and identification in the lightweight data. Our method can also bring processing inspiration for large data.Ziyang WangLin YangYehua ShengMi ShenMDPI AGarticleroad scene point cloudspole-like objectspoint cloud classificationrandom forest modelmultiscale fusionScienceQENRemote Sensing, Vol 13, Iss 4382, p 4382 (2021)
institution DOAJ
collection DOAJ
language EN
topic road scene point clouds
pole-like objects
point cloud classification
random forest model
multiscale fusion
Science
Q
spellingShingle road scene point clouds
pole-like objects
point cloud classification
random forest model
multiscale fusion
Science
Q
Ziyang Wang
Lin Yang
Yehua Sheng
Mi Shen
Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
description Real-time acquisition and intelligent classification of pole-like street-object point clouds are of great significance in the construction of smart cities. Efficient point cloud processing technology in road scenes can accelerate the development of intelligent transportation and promote the development of high-precision maps. However, available algorithms have the problems of incomplete extraction and the low recognition accuracy of pole-like objects. In this paper, we propose a segmentation method of pole-like objects under geometric structural constraints. As for classification, we fused the classification results at different scales with each other. First, the point cloud data excluding ground point clouds were divided into voxels, and the rod-shaped parts of the pole-like objects were extracted according to the vertical continuity. Second, the regional growth based on the voxel was carried out based on the rod part to retain the non-rod part of the pole-like objects. A one-way double coding strategy was adopted to preserve the details. For spatial overlapping entities, we used multi-rule supervoxels to divide them. Finally, the random forest model was used to classify the pole-like objects based on local- and global-scale features and to fuse the double classification results under the different scales in order to obtain the final result. Experiments showed that the proposed method can effectively extract the pole-like objects of the point clouds in the road scenes, indicating that the method can achieve high-precision classification and identification in the lightweight data. Our method can also bring processing inspiration for large data.
format article
author Ziyang Wang
Lin Yang
Yehua Sheng
Mi Shen
author_facet Ziyang Wang
Lin Yang
Yehua Sheng
Mi Shen
author_sort Ziyang Wang
title Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
title_short Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
title_full Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
title_fullStr Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
title_full_unstemmed Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes
title_sort pole-like objects segmentation and multiscale classification-based fusion from mobile point clouds in road scenes
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/a01c54f8799d4d0095cfb7e4e43b2012
work_keys_str_mv AT ziyangwang polelikeobjectssegmentationandmultiscaleclassificationbasedfusionfrommobilepointcloudsinroadscenes
AT linyang polelikeobjectssegmentationandmultiscaleclassificationbasedfusionfrommobilepointcloudsinroadscenes
AT yehuasheng polelikeobjectssegmentationandmultiscaleclassificationbasedfusionfrommobilepointcloudsinroadscenes
AT mishen polelikeobjectssegmentationandmultiscaleclassificationbasedfusionfrommobilepointcloudsinroadscenes
_version_ 1718431662655668224