A voxelized point clouds representation for object classification and segmentation on 3D data

Autor: Abubakar Sulaiman Gezawa, Zikirillahi A. Bello, Qicong Wang, Lei Yunqi
Rok vydání: 2021
Předmět:
Zdroj: The Journal of Supercomputing. 78:1479-1500
ISSN: 1573-0484
0920-8542
DOI: 10.1007/s11227-021-03899-x
Popis: Processing large amount of high-resolution 3D data requires enormous computational resources. As a result, a suitable 3D data representation must be chosen, and the data must be simplified to a size that can be easily processed. The question is how can the data be simplified? Random point sampling is a common sampling strategy. However, it is sensitive to changes in density. We build a sampling module based on a hybrid model that combines point cloud and voxel data. To determine the relationship between points within each voxel, the module uses the magnitude of the point (the Euclidean distance between the point and the object’s center) along with angles between each point embedded within each voxel. By exploiting farthest point sampling (FPS) that begins with a point in the set and selects the farthest point from the points already selected iteratively, our method has the advantage of covering the whole point set within a given number of centroids and still maintains the key benefits of both point cloud and voxel to better characterize geometric details contains in a 3D shape. With further observation that the number of points in each cell differs, we use a point quantization method to ensure that each cell has the same number of points. This allows all voxels to have the same feature size vector, making it easier for 3D convolution kernels to extract object features. We demonstrate these benefits and make comparisons with solid baselines on ModelNet10, ModelNet40 and ShapeNetPart datasets, demonstrating that our method outperforms some deep learning approaches for shape classification and segmentation tasks.
Databáze: OpenAIRE
Externí odkaz: