This study focuses on the task of single tree segmentation in urban environments and improves the PDE-Net model to enhance its ability to process complex features. The original PDE-Net model has limitations when dealing with trees in a large area of land use. In this study, we propose an improved model, PDEC-Net, which combines the original model with the Encoder-Decoder structure, and introduces the Depthwise Separable Convolution layer to better capture the global and local relationships of point clouds. The experimental results show that the PDEC-Net model outperforms the original model in evaluation indicators such as Pre, Recall, and F1 score. Compared with the original PDE-Net, the PDEC-Net has increased Pre, Recall, and F1 score by 4.2%, 0.6%, and 3.2%, respectively. Meanwhile, the improved model also shows better adaptability when dealing with large-scale test sets. Therefore, the PDEC-Net model demonstrates stronger performance in single tree segmentation tasks, providing more powerful support for urban planning, management, and environmental monitoring.

This study addresses the challenge in traditional digital orthophoto map (DOM) generation methods, which typically require a large number of highly overlapping remote sensing images, making them unsuitable for acquiring high-resolution DOM over extensive areas using multirotor unmanned aerial vehicles (UAVs) at low flight altitudes. We propose a more efficient approach that utilizes a small number of low-overlap UAV images, eliminating the need for complex structure-from-motion (SfM) processes. The method employs the Oriented FAST and Rotated BRIEF (ORB) algorithm for feature matching, leveraging its advantages in speed, rotation invariance, and robustness under low-overlap conditions. Additionally, key steps such as camera distortion correction are incorporated. Through qualitative and quantitative assessments, this method demonstrates the capability to generate high-precision orthophoto images rapidly and with minimal human intervention, thus validating its feasibility.

In the context of promoting digital city infrastructure, achieving precise three dimension (3D) modeling of buildings has become increasingly vital. Oblique photogrammetry serves as a primary method for large-scale urban modeling. However, due to limitations in the capture angles and photo quality, the model generated by oblique photogrammetry often has some holes in the side of the building and the ground. To resolve this problem, this study introduces a method for building holes repair and modeling, utilizing point clouds generated from oblique photography reconstruction. The method integrates architectural knowledge and symmetry principles to devise a comprehensive scheme for repairing building surface point clouds. Based on this, the Poisson surface reconstruction algorithm are employed to reconstruct the building model, aiming to enhance both its accuracy and practicality.

With the development of unmanned aerial vehicles (UAV) and embedded development technology, more and more UAV remote sensing applications require real-time transmission of acquired image data or processed result data to ground workstations. In this case, the method, speed, and quality of data transmission will have a significant impact on the real-time performance of such UAV applications. In response to this issue, this study is based on an UAV ground target real-time recognition system, and discusses data transmission methods based on wireless local area network, Internet of Things technology and TCP/IP communication protocol. It explores data transmission methods based on 4G communication network internal network penetration and Cloud server combination, and conducts comparative experimental analysis on these methods. Finally, through experiments, it was found that the combination of 4G communication network and Cloud server is a better method for transmission performance. This method avoids the spatial distance limitations of traditional methods and achieves reliable and superior real-time image data transmission.

In some scenes with complex terrain or features, the accuracy of the constructed three-dimensional (3D) based on oblique photogrammetry model is not ideal, and it often requires manual placement of ground control points (GCPs). What is the impact of GCPs on the accuracy of the constructed 3D model? This study designs a detailed experiment to explore this issue by collecting unmanned aerial vehicle (UAV) images and coordinates of control points in the testing area, adding different numbers of GCPs for 3D modeling, and finally conducting a systematic analysis of the accuracy of the 3D realistic model of the component from both qualitative and quantitative perspectives. The experiment shows that the effect of adding GCPs on the 3D model has been greatly improved, with the error in plane accuracy reduced to 1/14 of that without control points, and the horizontal and vertical deformations also decreased by about 10%. As the number of GCPs increases, the impact of enhancing 3D modeling precision will gradually diminish.

The semantic segmentation of vegetation point clouds has very important application value in the field of geosciences. It can distinguish vegetation regions from other regions, further classify and analyze the vegetation, and help us better understand the distribution and characteristics of vegetation to protect and manage natural resources. The PointNet and PointNet++ models use maximum pooling as the aggregation function, allowing the deep neural networks to classify unordered point clouds directly with high classification accuracy. However, their ability to extract spatial correlations and local features from point clouds is insufficient, which restricts the improvement of point clouds semantic segmentation accuracy and results in the poor processing of vegetation point clouds. To resolve this problem, this research designs the novel hierarchical point cloud transformer (HPCT) model, suitable for the semantic segmentation of multisource vegetation point clouds. Combined with deep learning techniques, different levels of features are processed hierarchically based on a hierarchical structure, and a Transformer module is combined in the feature extraction part, so as to obtain a larger receptive field and stronger semantic feature extraction capability. At the same time, we also propose a unified spatial scale sampling method for heterogeneous point cloud data input, which can be used not only for training and predicting the independent HPCT models with a single source of data, but also for training and predicting a unified HPCT model with multisource data. Semantic segmentation experiments are carried out on self-collected three-source data sets. The results show that the semantic segmentation performance of evaluation indicators (such asRecall,Pre,IoU, andOA) of the proposed HPCT model under the independent training and unified training on the three-source data exceed those of the PointNet, PointNet++, and PCT models, and even exceed some newly emerging models, such as PontCNN and DGCNN. The unified HPCT model has better segmentation performance than the independent HPCT model, with averageRecall,Pre,IoU, andOAindicators increasing by 1.07%, 1.73%, 4.33%, and 1.03%, respectively. We attribute this superior accuracy to the unified training with the three-source data. The averageRecall,Pre,IoU, andOAindicators of the unified HPCT model for the entire three-source data set exceed 96%, 98%, 95%, and 98%, respectively.

Machine unlearning is the process through which a deployed machine learning model is enforced to forget about some of its training data items. It normally generates two machine learning models, the original model and the unlearned model, indicating training results before and after data items are deleted. However, recent studies find that machine unlearning is vulnerable to membership inference attacks—as the directivity of training and nontraining data (i.e., data items in the training set have high posterior probabilities), the attackers can utilize this property to infer whether an item has been used for original model training. Nevertheless, such attacks are incapable in label-only settings, in which the attackers are infeasible to get the posteriors. In this paper, we propose a new label-only membership inference attack scheme targeted at machine unlearning to eliminate the dependence on posteriors. Our heuristic is that injected turbulence on candidate samples will present different behaviors for training and nontraining data. Thus, in our scheme, the attacker iteratively query on the original/unlearned models and inject turbulence to change their predicting labels; it determines whether an item is having-been-delated by observing the disturbance amplitude. Extensive experiments (i.e., on MNIST, CIFAR10, CIFAR100, and STL10 data sets) show that our method achieves high inference accuracy (measured by AUC) in label-only settings, for example, AUC = 0.96 for MNIST data set. Besides, we analyze the existing countermeasures in mitigating inference attacks and find that our scheme can bypass most of them.