It is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification. However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds. For large-scene laser point clouds, the current data preprocessing methods are mostly based on random sampling, which is not suitable for DEM extraction tasks. In this study, we propose a novel data sampling algorithm for the data preparation of patch-based training and classification named T-Sampling. T-Sampling uses the set of the lowest points in a certain area as basic points with other points added to supplement it, which can guarantee the integrity of the terrain in the sampling area. In the learning part, we propose a new convolution model based on terrain named Tin-EdgeConv that fully considers the spatial relationship between ground and non-ground points when constructing a directed graph. We design a new network based on Tin-EdgeConv to extract local features and use PointNet architecture to extract global context information. Finally, we combine this information effectively with a designed attention fusion module. These aspects are important in achieving high classification accuracy. We evaluate the proposed method by using large-scale data from forest areas. Results show that our method is more accurate than existing algorithms.
A deep convolution neural network is frequently used in airborne laser scanning (ALS) point cloud segmentation. In this study, we propose a joint graph-voxel convolution network to recognize on-ground objects accurately. In our network, the spatial context features of an input point cloud are first extracted by a designed U-Net via sparse convolution neural networks (SU-Net). Next, the extracted features are used as input features of a designed graph convolution network. We design a graph convolution module called the G-Net to extract the local spatial structure of each point. To enhance the representation of spatial context information, we initialize a graph based on a horizontal direction to enhance the difference between objects and the ground. The output probabilities of SU-Net and the graph convolution model are weighted as the input of the conditional random field optimizing model. The framework proposed in this study exhibits high processing efficiency. Experiments on the semantic 3D labeling dataset of the International Society for Photogrammetry and Remote Sensing (ISPRS) and 2019 IEEE Data Fusion Contest Dataset demonstrate that the proposed model significantly improve the highest F1 score and outperforms various previous networks.
Ground filtering (GF) is a fundamental step for airborne laser scanning (ALS) data processing. The advent of deep learning techniques provides new solutions to this problem. Existing deep-learning-based methods utilize a segmentation or classification framework to extract ground/non-ground points, which suffers from a dilemma in keeping high spatial resolution while acquiring rich contextual information when dealing with large-scale ALS data due to the computing resource limits. To this end, we propose SeqGP, a novel deep-learning-based GF pipeline that explicitly converts the GF task into an iterative sequential ground prediction (SeqGP) problem using points-profiles. The proposed SeqGP utilizes deep reinforcement learning (DRL) to optimize the prediction sequence and retrieve the bare terrain gradually. The 3D sparse convolution is integrated with the SeqGP strategy to generate high-precision classification results with memory efficiency. Extensive experiments on two challenging test sets demonstrate the state-of-the-art filtering performance and universality of the proposed method in dealing with large-scale ALS data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.