Next Article in Journal
Positioning in 5G and 6G Networks—A Survey
Previous Article in Journal
Battery-Less Environment Sensor Using Thermoelectric Energy Harvesting from Soil-Ambient Air Temperature Differences
Article

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

by 1,2, 1,2,* and 1,2
1
State Key Laboratory for Strength and Vibration of Mechanical Structures, School of Aerospace Engineering, Xi’an Jiaotong University, Xi’an 710049, China
2
Shaanxi Engineering Laboratory for Vibration Control of Aerospace Structures, Xi’an Jiaotong University, Xi’an 710049, China
*
Author to whom correspondence should be addressed.
Academic Editor: Francesco Longo
Sensors 2022, 22(13), 4742; https://doi.org/10.3390/s22134742
Received: 24 May 2022 / Revised: 15 June 2022 / Accepted: 21 June 2022 / Published: 23 June 2022
(This article belongs to the Section Intelligent Sensors)
Effectively integrating the local features and their spatial distribution information for more effective point cloud analysis is a subject that has been explored for a long time. Inspired by convolutional neural networks (CNNs), this paper studies the relationship between local features and their spatial characteristics and proposes a concise architecture to effectively integrate them instead of designing more sophisticated feature extraction modules. Different positions in the feature map of the 2D image correspond to different weights in the convolution kernel, making the obtained features that are sensitive to local distribution characteristics. Thus, the spatial distribution of the input features of the point cloud within the receptive field is critical for capturing abstract regional aggregated features. We design a lightweight structure to extract local features by explicitly supplementing the distribution information of the input features to obtain distinctive features for point cloud analysis. Compared with the baseline, our model shows improvements in accuracy and convergence speed, and these advantages facilitate the introduction of the snapshot ensemble. Aiming at the shortcomings of the commonly used cosine annealing learning schedule, we design a new annealing schedule that can be flexibly adjusted for the snapshot ensemble technology, which significantly improves the performance by a large margin. Extensive experiments on typical benchmarks verify that, although it adopts the basic shared multi-layer perceptrons (MLPs) as feature extractors, the proposed model with a lightweight structure achieves on-par performance with previous state-of-the-art (SOTA) methods (e.g., MoldeNet40 classification, 0.98 million parameters and 93.5% accuracy; S3DIS segmentation, 1.4 million parameters and 68.7% mIoU). View Full-Text
Keywords: lightweight network; deep learning; point cloud classification; point cloud segmentation lightweight network; deep learning; point cloud classification; point cloud segmentation
Show Figures

Figure 1

MDPI and ACS Style

Zheng, Q.; Sun, J.; Chen, W. A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics. Sensors 2022, 22, 4742. https://doi.org/10.3390/s22134742

AMA Style

Zheng Q, Sun J, Chen W. A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics. Sensors. 2022; 22(13):4742. https://doi.org/10.3390/s22134742

Chicago/Turabian Style

Zheng, Qiang, Jian Sun, and Wei Chen. 2022. "A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics" Sensors 22, no. 13: 4742. https://doi.org/10.3390/s22134742

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop