Integrating Normal Vector Features into an Atrous Convolution Residual Network for LiDAR Point Cloud Classification

Abstract

LiDAR point clouds are rich in spatial information and can effectively express the size, shape, position, and direction of objects; thus, they have the advantage of high spatial utilization. The point cloud focuses on describing the shape of the external surface of the object itself and will not store useless redundant information to describe the occupation. Therefore, point clouds have become the research focus of 3D data models and are widely used in large-scale scene reconstruction, virtual reality, digital elevation model production, and other fields. Since point clouds have various characteristics, such as disorder, density inconsistency, unstructuredness, and incomplete information, point cloud classification is still complex and challenging. To realize the semantic classification of LiDAR point clouds in complex scenarios, this paper proposes the integration of normal vector features into an atrous convolution residual network. Based on the RandLA-Net network structure, the proposed network integrates the atrous convolution into the residual module to extract global and local features of the point clouds. The atrous convolution can learn more valuable point cloud feature information by expanding the receptive field. Then, the point cloud normal vector is embedded in the local feature aggregation module of the RandLA-Net network to extract local semantic aggregation features. The improved local feature aggregation module can merge the deep features of the point cloud and mine the fine-grained information of the point cloud to improve the model's segmentation ability in complex scenes. Finally, to resolve the imbalance of the distribution of the various categories of point clouds, the original loss function is optimized by adopting a reweighted method to prevent overfitting so that the network can focus on small target categories in the training process to effectively improve the classification performance. Through the experimental analysis of a Vaihingen (Germany) urban 3D semantic dataset from the ISPRS website, it is verified that the proposed algorithm has a strong generalization ability. The overall accuracy (OA) of the proposed algorithm on the Vaihingen urban 3D semantic dataset reached 97.9%, and the average reached 96.1%. Experiments show that the proposed algorithm fully exploits the semantic features of point clouds and effectively improves the accuracy of point cloud classification.

FSS-Net: A Fast Search Structure for 3D Point Clouds in Deep Learning

“…Ref. [2][3][4][5][6]9] learned to extract the local features to enhance the segmentation results. CKConv [7] proposed a spatial attention module to provide comprehensive structure awareness within the local point set, where the representative features were produced.…”

“…The PointNet [1] is the pioneering work that used the per-point multi-layer perception (MLP) to extract point features, and the symmetric function to extract the global feature, where the local context modeling capability was not discussed. Several point-based methods have been proposed, see [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. From the perspective of traditional convolutional neural networks (CNNs), the shape information and semantic information of points are affected by the information of the surrounding points, and it is important to exploit the local structure.…”

Learning a Deep Attention Dilated Residual Convolutional Neural Network for Landslide Susceptibility Mapping in Hanzhong City, Shaanxi Province, China

“…Dilated convolution [21] introduces the concept of expansion on the basis of ordinary convolution. As shown in Figure 4, the dilated convolution has the same convolution kernel and the same number of parameters in the neural network compared with the ordinary convolution.…”