Dissimilarity to Class Medoids as Features for 3D Point Cloud Classification

AbstractClassifying 3D point clouds is an important and challenging task in computer vision. Currently, classification methods using multiple views lose characteristic or detail information during the representation or processing of views. For this reason, we propose a multi-view attention-convolution pooling network framework for 3D point cloud classification tasks. This framework uses Res2Net to extract the features from multiple 2D views. Our attention-convolution pooling method finds more useful information in the input data related to the current output, effectively solving the problem of feature information loss caused by feature representation and the detail information loss during dimensionality reduction. Finally, we obtain the probability distribution of the model to be classified using a full connection layer and the softmax function. The experimental results show that our framework achieves higher classification accuracy and better performance than other contemporary methods using the ModelNet40 dataset.

Download Full-text

A Study of 3D Point Cloud Classification of Urban Structures Based on Spherical Signature Descriptor Using LiDAR Sensor Data

Transactions of the Korean Society of Mechanical Engineers A ◽

10.3795/ksme-a.2019.43.2.085 ◽

2019 ◽

Vol 43 (2) ◽

pp. 85-91 ◽

Cited By ~ 1

Author(s):

Chul Hee Bae ◽

Sejin Lee

Keyword(s):

Point Cloud ◽

Sensor Data ◽

3D Point Cloud ◽

Urban Structures ◽

Cloud Classification ◽

Point Cloud Classification

Download Full-text

An Effective Encoding Method Based on Local Information for 3D Point Cloud Classification

IEEE Access ◽

10.1109/access.2019.2905595 ◽

2019 ◽

Vol 7 ◽

pp. 39369-39377

Author(s):

Yanan Song ◽

Liang Gao ◽

Xinyu Li ◽

Quan-Ke Pan

Keyword(s):

Point Cloud ◽

Local Information ◽

3D Point Cloud ◽

Cloud Classification ◽

Encoding Method ◽

Point Cloud Classification

Download Full-text

Random Walk Network for 3D Point Cloud Classification and Segmentation

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) ◽

10.1109/robio49542.2019.8961535 ◽

2019 ◽

Cited By ~ 1

Author(s):

Lei Zhu ◽

Weinan Chen ◽

Xubin Lin ◽

Li He ◽

Yisheng Guan ◽

...

Keyword(s):

Random Walk ◽

Point Cloud ◽

3D Point Cloud ◽

Cloud Classification ◽

Point Cloud Classification

Download Full-text

GSV-NET: A Multi-Modal Deep Learning Network for 3D Point Cloud Classification

Applied Sciences ◽

10.3390/app12010483 ◽

2022 ◽

Vol 12 (1) ◽

pp. 483

Author(s):

Long Hoang ◽

Suk-Hwan Lee ◽

Eung-Joo Lee ◽

Ki-Ryong Kwon

Keyword(s):

Autonomous Vehicles ◽

Point Cloud ◽

High Performance ◽

3D Point Cloud ◽

Real World Data ◽

Color Representation ◽

Princeton University ◽

Cloud Classification ◽

Sensing Technology ◽

Point Cloud Classification

Light Detection and Ranging (LiDAR), which applies light in the formation of a pulsed laser to estimate the distance between the LiDAR sensor and objects, is an effective remote sensing technology. Many applications use LiDAR including autonomous vehicles, robotics, and virtual and augmented reality (VR/AR). The 3D point cloud classification is now a hot research topic with the evolution of LiDAR technology. This research aims to provide a high performance and compatible real-world data method for 3D point cloud classification. More specifically, we introduce a novel framework for 3D point cloud classification, namely, GSV-NET, which uses Gaussian Supervector and enhancing region representation. GSV-NET extracts and combines both global and regional features of the 3D point cloud to further enhance the information of the point cloud features for the 3D point cloud classification. Firstly, we input the Gaussian Supervector description into a 3D wide-inception convolution neural network (CNN) structure to define the global feature. Secondly, we convert the regions of the 3D point cloud into color representation and capture region features with a 2D wide-inception network. These extracted features are inputs of a 1D CNN architecture. We evaluate the proposed framework on the point cloud dataset: ModelNet and the LiDAR dataset: Sydney. The ModelNet dataset was developed by Princeton University (New Jersey, United States), while the Sydney dataset was created by the University of Sydney (Sydney, Australia). Based on our numerical results, our framework achieves more accuracy than the state-of-the-art approaches.

Download Full-text