DenseKPNET: Dense Kernel Point Convolutional Neural Networks for Point Cloud Semantic Segmentation

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 13
• Main Authors: Li, Yong, Li, Xu, Zhang, Zhenxin, Shuang, Feng, Lin, Qi, Jiang, Jincheng
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolution; Datasets; Deep learning; Dense connection; Dense connection-based Kernel Point Network (DenseKPNet); Design; Feature extraction; Image segmentation; Information processing; Inspection; Kernel; kernel point convolution attention module (KPCAM); Kernels; Lasers; Machine learning; Methods; Modules; Neural networks; Point cloud compression; point clouds; Receptive field; Semantic segmentation; semantic segmentation of point clouds; Semantics; Three-dimensional displays
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2022.3162582

In recent years, point clouds have been widely used in powerline inspection, smart cities, autonomous driving, and other fields. The deep learning-based point cloud processing methods have attracted more and more attention due to the developments of laser scanning technology and machine learning. However, the recent methods largely ignore global contextual relationships and do not make full use of the complementation between local feature and high-level geometric information. To the problem, we propose a novel deep neural network, namely, the Dense connection-based Kernel Point Network (DenseKPNet), which can greatly expand the receptive field of kernel point convolution to extract rich semantic context information and valuable geometric features from the local region effectively. Specifically, we first design a multiscale convolution kernel point module to extract initial geometric features from coarse to fine. Then, we design the dense connection module to efficiently learn more expressive local geometric features while capturing rich contextual information. In addition, we propose the kernel point convolution attention module (KPCAM), which can capture global interdependencies between points and strengthen the discriminativeness of effective features. We evaluate our method on public indoor and outdoor datasets. The qualitative and quantitative experimental results show the effectiveness of DenseKPNet. The mIoU of the proposed method on S3DIS and semantic3D datasets can reach 68.9% and 77.9%, respectively.