Back to Search
Start Over
IPCONV: Convolution with Multiple Different Kernels for Point Cloud Semantic Segmentation.
- Source :
- Remote Sensing; Nov2023, Vol. 15 Issue 21, p5136, 21p
- Publication Year :
- 2023
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- POINT cloud
AIRBORNE lasers
DEEP learning
REMOTE sensing
MATHEMATICAL convolutions
Subjects
Details
- Language :
- English
- ISSN :
- 20724292
- Volume :
- 15
- Issue :
- 21
- Database :
- Complementary Index
- Journal :
- Remote Sensing
- Publication Type :
- Academic Journal
- Accession number :
- 173568201
- Full Text :
- https://doi.org/10.3390/rs15215136