IPCONV: Convolution with Multiple Different Kernels for Point Cloud Semantic Segmentation
Remote Sensing · 27.10.2023 · 15 (21) · 5136
DOI: 10.3390/rs15215136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 27.10.2023. Verfasst von Ruixiang Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Major S&T Program of Hunan Province, Science and Technology Research and Development Program Project of China Railway Group Limited (Major Special Project).
Abstract (Originalsprache)
The segmentation of airborne laser scanning (ALS) point clouds remains a challenge in remote sensing and photogrammetry. Deep learning methods, such as KPCONV, have proven effective on various datasets. However, the rigid convolutional kernel strategy of KPCONV limits its potential use for 3D object segmentation due to its uniform approach. To address this issue, we propose an Integrated Point Convolution (IPCONV) based on KPCONV, which utilizes two different convolution kernel point generation strategies, one cylindrical and one a spherical cone, for more efficient learning of point cloud data features. We propose a customizable Multi-Shape Neighborhood System (MSNS) to balance the relationship between these convolution kernel point generations. Experiments on the ISPRS benchmark dataset, LASDU dataset, and DFC2019 dataset demonstrate the validity of our method.
Förderung
- National Natural Science Foundation of China
- Major S&T Program of Hunan Province
- Science and Technology Research and Development Program Project of China Railway Group Limited (Major Special Project)
Zitieren
APA
Zhang, R., Chen, S., Wang, X., & Zhang, Y. (2023). IPCONV: Convolution with Multiple Different Kernels for Point Cloud Semantic Segmentation. Remote Sensing, 15(21), 5136. https://doi.org/10.3390/rs15215136
Vancouver
Zhang R, Chen S, Wang X, Zhang Y. IPCONV: Convolution with Multiple Different Kernels for Point Cloud Semantic Segmentation. Remote Sensing. 2023;15(21):5136. doi:10.3390/rs15215136
BibTeX
@article{Zhang2023,
author = {Zhang, Ruixiang and Chen, Siyang and Wang, Xuying and Zhang, Yunsheng},
title = {IPCONV: Convolution with Multiple Different Kernels for Point Cloud Semantic Segmentation},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {21},
pages = {5136},
doi = {10.3390/rs15215136}
}
EUVIMED