Digital Elevation Model (DEM)-based mountain vertex extraction is one of the most useful DEM applications, providing important information to properly characterize topographic features. Current vertex-extraction techniques have considerable limitations, such as yielding low-accuracy results and generating false mountain vertices. To overcome these limitations, a new approach is proposed that combines Hotspot Analysis Clustering and the Improved Eight-Connected Extraction algorithms that would quickly and accurately provide the location and elevation of mountain vertices. The use of the elevation-based Hotspot Analysis Clustering Algorithm allows the fast partitioning of the mountain vertex area, which significantly reduces data and considerably improves the efficiency of mountain vertex extraction. The algorithm also minimizes false mountain vertices, which can be problematic in valleys, ridges, and other rugged terrains. The Eight-Connected Extraction Algorithm also hastens the precise determination of vertex location and elevation, providing a better balance between accuracy and efficiency in vertex extraction. The proposed approach was used and tested on seven different datasets and was compared against traditional vertex extraction methods. The results of the quantitative evaluation show that the proposed approach yielded higher efficiency, considerably minimized the occurrence of invalid points, and generated higher vertex extraction accuracy compared to other traditional methods.

In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.

Probabilistic registration algorithms [e.g., coherent point drift, (CPD)] provide effective solutions for point cloud alignment. However, using the original CPD algorithm for automatic registration of terrestrial laser scanner (TLS) point clouds is highly challenging because of density variations caused by scanning acquisition geometry. In this letter, we propose a new global registration method, introducing the use of the CPD framework for TLS point clouds. We first consider the measurement geometry and the intrinsic characteristics of the scene to simplify points. In addition to the Euclidean distance, we incorporate geometric information as well as structural constraints in the probabilistic model to optimize the so-called matching probability matrix. Among the structural constraints, we use a spectral graph to measure the structural similarity between matches at each iteration. The method is tested on three data sets collected by different TLS scanners. Experimental results demonstrate that the proposed method is robust to density variations and can decrease iterations effectively. The average registration errors of the three data sets are 0.05, 0.12, and 0.08 m, respectively. It is also shown that our registration framework is superior to the state-of-the-art methods in terms of both registration errors and efficiency. The experiments demonstrate the effectiveness and efficiency of the proposed probabilistic global registration.