The complexity of terrain features poses a substantial challenge in the effective processing and application of airborne LiDAR data, particularly in regions characterized by steep slopes and diverse objects. In this paper, we propose a novel multiscale filtering method utilizing a modified 3D alpha shape algorithm to increase the ground point extraction accuracy in complex terrain. Our methodology comprises three pivotal stages: preprocessing for outlier removal and potential ground point extraction; the deployment of a modified 3D alpha shape to construct multiscale point cloud layers; and the use of a multiscale triangulated irregular network (TIN) densification process for precise ground point extraction. In each layer, the threshold is adaptively determined based on the corresponding $\alpha$. Points closer to the TIN surface than the threshold are identified as ground points. The performance of the proposed method was validated using a classical benchmark dataset provided by the ISPRS and an ultra-large-scale ground filtering dataset called OpenGF. The experimental results demonstrate that this method is effective, with an average total error and a kappa coefficient on the ISPRS dataset of 3.27% and 88.97%, respectively. When tested in the large scenarios of the OpenGF dataset, the proposed method outperformed four classical filtering methods and achieved accuracy comparable to that of the best of learning-based methods.

Powerlines are critical components of powerline corridors, essential for ensuring a stable and reliable power supply. With the increasing adoption of airborne laser scanning (ALS) in corridor inspections, the demand for efficient and automated methods to extract powerline points from point clouds has grown significantly. This paper presents a method for automated powerline extraction from ALS-acquired point clouds, addressing key challenges such as large-scale data processing, complex terrains, and precise segmentation of powerlines and associated components. The proposed approach begins with gridbased pylon location detection and span-based organization of massive powerline corridor data, enabling efficient data processing. A robust segmentation technique is then introduced, transforming the task into a connected component identification problem within a mesh generated using the 3D Alpha Wrapping algorithm to effectively separate powerlines from other objects. To address irregular gaps in powerline point clouds, a graphcut-based energy minimization method is developed to identify and merge powerline fragments. Furthermore, a novel slice-based segmentation technique is introduced to accurately differentiate powerlines from components such as pylons, insulator strings, and jumper wires. The method was evaluated on nine datasets spanning 80.32 km, covering voltage levels of 220 kV, 500 kV, and 800 kV. It achieved an average recall of 0.9981, precision of 0.9977, and F1 score of 0.9979, demonstrating its robustness, adaptability, and high performance across diverse scenarios.

As an essential parameter in forestry, crown base height (CBH) faces many tasks. The methods are still developing for estimating it. Unmanned aerial vehicles (UAV)light detection and ranging (LiDAR) supplies new, massive and high-density data for estimating CBH. Many methods hadbeen generated to compute CBH indirectly using regression-based ways or directly using geometric/statistical LiDAR-based ways. However, there werefew methods to deal with the problem of understory, trunkand noise points caused by high-density UAV data. A robust method was firstlyproposed in this studyto directly estimate CBH from LiDAR data, which containedtwo significant skills: 1)understory vegetation removal for each tree using a polynomial curve,and 2) computing CBH by kernel densification ofthe elevation frequency histogram of LiDAR data. It could tolerate the understoryand trunk points better through kernel convolution. The method proposed in this study and a previous simple model were applied in a crabapple plot in Huailai Remote Sensing Comprehensive Experimental Station, Hebei Province, China and verified byfield-measured data. Itwasinspiringthat our method is slightly better, the mean CBH of LiDAR-derived trees was only 1.60 cm higher than that of field-measured trees.The mean absolute error (MAE) of CBH was 4.91 cm, R2 was 0.73, RMSE was 8.29 cm and bias was 2.68%for these trees. Generally, this method showedstrong usability for high-density UAV LiDAR data and high precision for measuringCBH of low trees.

The monitoring of telegraph poles as essential features supporting overhead distribution network lines is the primary subject of this work. This paper proposes a method for locating and extracting telegraph poles from an image matching-based point cloud. Firstly, the point cloud of the poles is extracted using the planar grid segmentation clustering algorithm and the connected component analysis algorithm of the region grows according to the isolated features of the poles perpendicular to the ground. Secondly, the candidate telegraph poles are located based on the suspension point of the buffer, considering that the top of the pole is connected to the power suspension line. Thirdly, the horizontal projection method of the backbone area is utilized to eliminate the interference of vegetation in the buffer area. Finally, the point cloud of the telegraph pole is extracted through the density-based spatial clustering of applications with noise (DBSCAN) algorithm. The experimental results demonstrate that the average values of Recall, Precision, and F1-score in telegraph pole detection can reach 91.09%, 90.82%, and 90.90%, respectively. The average RMSE value of location deviation is 0.51m. The average value of the F1-score in the telegraph pole extraction is 91.83%, and the average extraction time of a single pole is 0.27s. Accordingly, this method has strong adaptability to areas with lush vegetation and can automatically locate and extract the telegraph pole point cloud with high accuracy, and it can still achieve very high accuracy even under the holes in the data.

The integration of multi-source remote sensing data, bolstered by advancements in deep learning, has emerged as a pivotal strategy for enhancing land use and land cover (LULC) classification accuracy. However, current methods often fail to consider the numerous prior knowledge of remote sensing images and the characteristics of heterogeneous remote sensing data, resulting in data loss between different modalities and the loss of a significant amount of useful information, thus affecting classification accuracy. To tackle these challenges, this paper proposes a LULC classification method based on remote sensing data that combines a Transformer and cross-pseudo-siamese learning deep neural network (TCPSNet). It first conducts shallow feature extraction in a dynamic multi-scale manner, fully leveraging the prior information of remote sensing data. Then, it further models deep features through the multimodal cross-attention module (MCAM) and cross-pseudo-siamese learning module (CPSLM). Finally, it achieves comprehensive fusion of local and global features through feature-level fusion and decision-level fusion combinations. Extensive experiments on datasets such as Trento, Houston 2013, Augsburg, MUUFL and Berlin demonstrate the superior performance of the proposed TCPSNet. The overall accuracy (OA) of the network on the Trento, Houston 2013 and Augsburg datasets is of 99.76%, 99.92%, 97.41%, 87.97% and 97.96%, respectively.

Cylinder point extraction is a crucial prerequisite for applications of industrial scenarios, such as reverse engineering and clearance analysis, using laser point clouds. This task currently suffers from data missing, noise, and interference from the planar objects. The generalization capability for cylindrical objects with different radii is also required. Considering the cylindrical object as the continuously extended cylinder, a region growth algorithm using a multi-scale prospecting strategy is proposed in this paper. Firstly, the preprocess is conducted to subsample the point cloud and estimate each point normal. Secondly, the kernel computation is used to detect the potential cylinder patches as kernels with the multi-scale cylinder prospecting. Then, the rough extraction is performed to compute the cylinder parameters with the iterative growth starting from kernels. Finally, the fine extraction labels the raw point cloud by assigning points to different cylinders under the length constraint. The real-world point clouds, which are collected from four industrial scenarios, the simulated point cloud, and an open dataset are employed to evaluate the proposed method performance. Experimental results demonstrate the effectiveness and robustness of the proposed method. The average precision, recall, and F1-Score on the real-world dataset and open dataset are 0.879, 0.894, 0.885 and 0.931, 0.893, 0.909, respectively.