TY - GEN
T1 - Local learning in point clouds based on spectral pooling
AU - Li, Yushi
AU - Baciu, George
N1 - Publisher Copyright:
©2020 IEEE
PY - 2020/9/26
Y1 - 2020/9/26
N2 - As one of the most fundamental geometric data types for the representation of space and object shapes, a point cloud usually maintains much structural information about the spatial relationship between objects and their features. However, the relative sparseness of point clouds sampled in most practical applications make extracting information-rich features a major challenge. Traditionally, feature extraction algorithms resorted to structured feature engineering and used handcrafted representations for some specific problems. Motivated by the development of deep neural networks, many researchers started to handle the unstructured point clouds from the raw data samples of 3D scanning devices. Some important advantages that deep learning frameworks have over traditional feature engineering is generalizing complex features and associated semantic concepts in a hierarchical manner. Deep learning models have achieved significant landmarks in cognitive processing of speech, image, and video signals. However, unlike in 2D image processing, a 3D point cloud is irregular and sparse. Hence, traditional network frameworks are difficult to apply on 3D geometric data directly. In this paper, we propose to integrate a local point convolution network with spectral pooling to aggregate and learn features in 3D point clouds. The benefits of our framework are fast convergence and competitive performance on point cloud classification.
AB - As one of the most fundamental geometric data types for the representation of space and object shapes, a point cloud usually maintains much structural information about the spatial relationship between objects and their features. However, the relative sparseness of point clouds sampled in most practical applications make extracting information-rich features a major challenge. Traditionally, feature extraction algorithms resorted to structured feature engineering and used handcrafted representations for some specific problems. Motivated by the development of deep neural networks, many researchers started to handle the unstructured point clouds from the raw data samples of 3D scanning devices. Some important advantages that deep learning frameworks have over traditional feature engineering is generalizing complex features and associated semantic concepts in a hierarchical manner. Deep learning models have achieved significant landmarks in cognitive processing of speech, image, and video signals. However, unlike in 2D image processing, a 3D point cloud is irregular and sparse. Hence, traditional network frameworks are difficult to apply on 3D geometric data directly. In this paper, we propose to integrate a local point convolution network with spectral pooling to aggregate and learn features in 3D point clouds. The benefits of our framework are fast convergence and competitive performance on point cloud classification.
UR - http://www.scopus.com/inward/record.url?scp=85112865124&partnerID=8YFLogxK
U2 - 10.1109/ICCICC50026.2020.9450222
DO - 10.1109/ICCICC50026.2020.9450222
M3 - Conference Proceeding
AN - SCOPUS:85112865124
T3 - Proceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
SP - 84
EP - 91
BT - Proceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
A2 - Wang, Yingxu
A2 - Ge, Ning
A2 - Lu, Jianhua
A2 - Tao, Xiaoming
A2 - Soda, Paolo
A2 - Howard, Newton
A2 - Widrow, Bernard
A2 - Feldman, Jerome
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
Y2 - 26 September 2020 through 28 September 2020
ER -