No abstract

Abstract. Utility poles located along roads play a key role in road safety and planning as well as communications and electricity distribution. In this regard, new sensing technologies such as Mobile Terrestrial Laser Scanner (MTLS) could be an efficient method to detect utility poles and other planimetric objects along roads. However, due to the vast amount of data collected by MTLS in the form of a point cloud, automated techniques are required to extract objects from this data. This study proposes a novel method for automatic extraction of utility poles from the MTLS point clouds. The proposed algorithm is composed of three consecutive steps of pre-processing, cable area detection, and poles extraction. The point cloud is first pre-processed and then candidate areas for utility poles are specified based on Hough Transform (HT). Utility poles are extracted by applying horizontal and vertical density information to these areas. The performance of the method was evaluated on a sample point cloud and 98% accuracy was achieved in extracting utility poles using the proposed method.

The 3D semantic segmentation of a LiDAR point cloud is essential for various complex infrastructure analyses such as roadway monitoring, digital twin, or even smart city development. Different geometric and radiometric descriptors or diverse combinations of point descriptors can extract objects from LiDAR data through classification. However, the irregular structure of the point cloud is a typical descriptor learning problem—how to consider each point and its surroundings in an appropriate structure for descriptor extraction? In recent years, convolutional neural networks (CNNs) have received much attention for automatic segmentation and classification. Previous studies demonstrated deep learning models’ high potential and robust performance for classifying complicated point clouds and permutation invariance. Nevertheless, such algorithms still extract descriptors from independent points without investigating the deep descriptor relationship between the center point and its neighbors. This paper proposes a robust and efficient CNN-based framework named D-Net for automatically classifying a mobile laser scanning (MLS) point cloud in urban areas. Initially, the point cloud is converted into a regular voxelized structure during a preprocessing step. This helps to overcome the challenge of irregularity and inhomogeneity. A density value is assigned to each voxel that describes the point distribution within the voxel’s location. Then, by training the designed CNN classifier, each point will receive the label of its corresponding voxel. The performance of the proposed D-Net method was tested using a point cloud dataset in an urban area. Our results demonstrated a relatively high level of performance with an overall accuracy (OA) of about 98% and precision, recall, and F1 scores of over 92%.

Mobile terrestrial laser scanning (MTLS) systems provide a safe and efficient means to survey roadway corridors at high speed. MTLS point clouds are rich in planimetric data. However, manual extraction of useful information from these point clouds can be time consuming and laborious and automated object extraction from MTLS point clouds has become a hot topic in the remote sensing community. This study proposes an automated method for power line extraction from MTLS point clouds based on a multilayer perceptron (MLP) neural network. The proposed method consists of three main steps: (i) point cloud preprocessing, (ii) descriptor extraction and selection, and (iii) point classification. The preprocessing step involves filtering out more than 90% of the point cloud by eliminating the vast majority of unneeded points. Next, various descriptors are extracted from the remaining points including planarity, linearity, and verticality, and the descriptor standard deviation is used to select the best‐suited descriptors for power line extraction. Finally, an MLP neural network is trained using the selected descriptors from several cable and noncable sample points. The proposed algorithm was evaluated in three MTLS point clouds in urban and nonurban environments totalling 5.5 kilometres in length. An average precision of 94% and a recall of 94% showed the algorithm’s reliability and feasibility.

Abstract. Trees are an essential part of the natural and urban environment due to providing crucial benefits such as increasing air quality and wildlife habitats. Therefore, various remote sensing and photogrammetry technologies, including Mobile Laser Scanner (MLS), have been recently introduced for precise 3D tree mapping and modeling. The MLS provides densely 3D LiDAR point clouds from the surrounding, which results in measuring applicable information of trees like stem diameter or elevation. In this paper, a transfer learning procedure on the PointNet++ has been proposed for tree extraction. Initially, two steps of converting the MLS point clouds into same-length smaller sections and eliminating ground points have been conducted to overcome the massive volume of MLS data. The algorithm was tested on four LiDAR datasets ranging from challengeable urban environments containing multiple objects like tall buildings to railway surroundings. F1-Score accuracy was gained at around 93% and 98%, which showed the feasibility and efficiency of the proposed algorithm. Noticeably, the algorithms also measured geometrical information of extracted trees such as 2D coordinate space, height, stem diameter, and 3D boundary tree locations.