Next Article in Journal
High-Resolution Spatial Distribution of Bird Movements Estimated from a Weather Radar Network
Previous Article in Journal
Semantic Segmentation Using Deep Learning with Vegetation Indices for Rice Lodging Identification in Multi-date UAV Visible Images
Open AccessArticle

Structure-Aware Convolution for 3D Point Cloud Classification and Segmentation

1
State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
2
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
3
School of Highway, Chang’an University, Xi’an 710064, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(4), 634; https://doi.org/10.3390/rs12040634
Received: 8 January 2020 / Revised: 5 February 2020 / Accepted: 12 February 2020 / Published: 14 February 2020
Semantic feature learning on 3D point clouds is quite challenging because of their irregular and unordered data structure. In this paper, we propose a novel structure-aware convolution (SAC) to generalize deep learning on regular grids to irregular 3D point clouds. Similar to the template-matching process of convolution on 2D images, the key of our SAC is to match the point clouds’ neighborhoods with a series of 3D kernels, where each kernel can be regarded as a “geometric template” formed by a set of learnable 3D points. Thus, the interested geometric structures of the input point clouds can be activated by the corresponding kernels. To verify the effectiveness of the proposed SAC, we embedded it into three recently developed point cloud deep learning networks (PointNet, PointNet++, and KCNet) as a lightweight module, and evaluated its performance on both classification and segmentation tasks. Experimental results show that, benefiting from the geometric structure learning capability of our SAC, all these back-end networks achieved better classification and segmentation performance (e.g., +2.77% mean accuracy for classification and +4.99% mean intersection over union (IoU) for segmentation) with few additional parameters. Furthermore, results also demonstrate that the proposed SAC is helpful in improving the robustness of networks with the constraints of geometric structures. View Full-Text
Keywords: structure-aware convolution; 3D point cloud; classification; segmentation structure-aware convolution; 3D point cloud; classification; segmentation
Show Figures

Figure 1

MDPI and ACS Style

Wang, L.; Liu, Y.; Zhang, S.; Yan, J.; Tao, P. Structure-Aware Convolution for 3D Point Cloud Classification and Segmentation. Remote Sens. 2020, 12, 634.

Show more citation formats Show less citations formats
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