Search

Within this study, we present a pioneering cross-platform point cloud registration (PCR) framework aimed at the automated alignment of UAV and terrestrial forest LiDAR point clouds. This framework leverages canopy profile skyline (CPS) descriptors and feature orientation information to support registration. Given the inherent irregular and natural distribution of point clouds derived from crown environments, conventional registration techniques that operate on geometric primitives such as points, lines, and planes are susceptible to inadequacies. In this article, we first analyze the high resolution and robustness of a skyline formed from successive tree canopy profiles as feature elements in forest data. Subsequently, we highlight the intriguing property that, whether they are UAV-based or terrestrial-based scanning data, the tree CPS obtained from the same location exhibits remarkably similar shapes and trends. Therefore, we propose a novel feature descriptor that encompasses M dimensions across 8 directions, with the aim of establishing reliable feature correspondences, subsequently leveraging directional constraints and employing one-shot estimation RANSAC to achieve automated UAV and terrestrial-based forest point cloud registration. Finally, the standard ICP algorithm combined with the constraint strategy based on tree trunk geometric morphological features will be utilized to refine the registration results. We conducted tests using five datasets with heterogeneous tree species and structures, and the results demonstrate that the proposed approach achieves SOTA performance.

To generate a complete 3D point cloud model for complex urban environments, data must be captured from both top-view and street-view sides due to the limited field of view of the sensors. Unmanned aerial vehicle-laser scanning (UAV-LS) point clouds are captured from a top view, and they often contain information about building roofs and tree crowns. In contrast, terrestrial point clouds, collected by terrestrial laser scanners (TLS) and mobile laser scanners (MLS), are captured from a street view and contain information about building facades and tree stems. These two types of point clouds are challenging to register without manual efforts or target-based assistance because of (1) very limited overlapping regions caused by the cross-view and (2) the wide search of regions for the automatic localization of terrestrial scans in a large-scale scene from a UAV scan. Consequently, we highlight that a semantic map can be developed by utilizing the invariant semantic and geometric relationships to automatically locate from a local scan to a global scan. In our tasks, the buildings and tree regions are detected and assigned as semantic objects and input to generate a 2.5D semantic map related to their actual location information. We propose a novel template matching strategy combined with a penalty system to realize the localization. Specifically, the templates can be produced by the obtained semantic maps, and then the best localization can be achieved by a graded punishment method based on the developed rules. We emphasize that the proposed method can handle the integration of multiple-aligned scans and even a single scan by using a terrestrial scanner to a UAV scan owing to the stability and continuity of semantic information. In the experiments, we used a UAV to capture the lidar point clouds over the campus of the Southwest Jiaotong university and generated a global semantic map offline. Keeping the global map in hand, we collected the data from the street views by TLS and MLS also the campus and then implemented the localization from TLS/MLS point clouds to the UAV point clouds. The evaluations are grouped into two grades related to the degree of difficulty: (1) the regular group, which contains the multiple-registered TLS scans and MLS scans, and (2) the challenging group, which has independent TLS scans. In general, from the experimental results, for the proposed method, the success rate of localization is up to 100% in the regular group and 90% in the challenging group, indicating that only one in ten tests fails for the challenging group.

Recent studies have introduced transformer modules into convolutional neural networks (CNNs) to solve the inherent limitations of CNNs in global modeling and have achieved impressive performance. However, some challenges have yet to be addressed: first, networks with simple connections between the CNN and transformer perform poorly in small change areas; second, networks that only use transformer structures are prone to attaining coarse detection results and excessively generalizing feature boundaries. In addition, the methods of fusing the CNN and transformer have the issue of a unilateral flow of feature information and inter-scale communication, leading to a loss of change information across different scales. To mitigate these problems, this study proposes a full-scale connected CNN–Transformer network, which incorporates the Siamese structure, Unet3+, and transformer structure, used for change detection in remote sensing images, namely SUT. A progressive attention module (PAM) is adopted in SUT to deeply integrate the features extracted from both the CNN and the transformer, resulting in improved global modeling, small target detection capacities, and clearer feature boundaries. Furthermore, SUT adopts a full-scale skip connection to realize multi-directional information flow from the encoder to decoder, enhancing the ability to extract multi-scale features. Experimental results demonstrate that the method we designed performs best on the CDD, LEVIR-CD, and WHU-CD datasets with its concise structure. In particular, based on the WHU-CD dataset, SUT upgrades the F1-score by more than 4% and the intersection over union (IOU) by more than 7% compared with the second-best method. [ABSTRACT FROM AUTHOR]

Vehicle‐borne laser scanning (VLS) point cloud semantic segmentation is one of the fundamental issues in motorway target extraction. In this study, a uniform sampling‐based neural network (NN) is constructed based on the popular RandLA‐Net. The uniform sampling can ensure high efficiency and stable spatial coverage. In the proposed NN, a local extra feature encoding structure is designed, and it is combined with local geometric spatial encoding and attention mechanisms to enhance the distinctiveness of depth features and improve the geometric detail preservation ability of the network. The VLS point cloud dataset of motorway scenes collected in this study is labelled for network training and evaluation. Experimental results demonstrate the superiority of the proposed network over the state‐of‐the‐art networks, attaining the highest intersection‐over‐union (IoU) on the majority of categories and a 4.39% improvement in mean IoU on all categories. For the pole‐shaped targets, the improvement in IoU is 9.08% relative to those of the compared methods. The labelled VLS point cloud dataset generated in this work will be made publicly available. [ABSTRACT FROM AUTHOR]