Segmentation of 3D point clouds is essential for applications such as environmental monitoring and autonomous navigation, where making accurate distinctions between different classes from high-resolution 3D datasets is critical. Segmenting 3D point clouds often requires a trade-off between preserving spatial information and achieving computational efficiency. In this paper, we present SAMNet++, a hybrid 3D segmentation model that integrates segment anything model (SAM) and adopted PointNet++ in a sequential two-stage pipeline. Firstly, SAM performs an initial unsupervised segmentation, which is then refined using adopted PointNet++ to improve the accuracy. The key innovations of SAMNet++ include its hybrid architecture, which combines SAM’s generalization with PointNet++’s local feature extraction, and a feature refinement strategy that enhances precision while reducing computational overhead. Additionally, SAMNet++ minimizes the reliance on extensive supervised training, while maintaining high accuracy. The proposed model is tested on three urban datasets, which are collected by an unmanned aerial vehicle (UAV). The proposed SAMNet++ model demonstrates high segmentation performance, achieving accuracy, precision, recall, and F1-score values above 0.97 across all classes on our experimental datasets. Furthermore, its mean intersection over union (mIoU) of 86.93% on a public benchmark dataset signifies a more balanced and precise segmentation across all classes, surpassing previous state-of-the-art methods. In addition to its improved accuracy, SAMNet++ showcases remarkable computational efficiency, requiring almost half the processing time of standard PointNet++ and nearly one-sixteenth of the time needed by the original PointNet algorithm.

Recent advances in event-based cameras have led to significant developments in robotics, particularly in visual simultaneous localization and mapping (VSLAM) applications. This technique enables real-time camera motion estimation and simultaneous environment mapping using visual sensors on mobile platforms. Event cameras offer several distinct advantages over frame-based cameras, including a high dynamic range, high temporal resolution, low power consumption, and low latency. These attributes make event cameras highly suitable for addressing performance issues in challenging scenarios such as high-speed motion and environments with high-range illumination. This review paper delves into event-based VSLAM (EVSLAM) algorithms, leveraging the advantages inherent in event streams for localization and mapping endeavors. The exposition commences by explaining the operational principles of event cameras, providing insights into the diverse event representations applied in event data preprocessing. A crucial facet of this survey is the systematic categorization of EVSLAM research into three key parts: event preprocessing, event tracking, and sensor fusion algorithms in EVSLAM. Each category undergoes meticulous examination, offering practical insights and guidance for comprehending each approach. Moreover, we thoroughly assess state-of-the-art (SOTA) methods, emphasizing conducting the evaluation on a specific dataset for enhanced comparability. This evaluation sheds light on current challenges and outlines promising avenues for future research, emphasizing the persisting obstacles and potential advancements in this dynamically evolving domain.

Indoor localization remains a challenging task due to the unavailability of reliable global navigation satellite system (GNSS) signals in most indoor environments. One way to overcome this challenge is through visual–inertial odometry (VIO), which enables real-time pose estimation by fusing camera and inertial measurements. However, VIO suffers from performance degradation under high-speed motion and in poorly lit environments. In such scenarios, motion blur, sensor noise, and low temporal resolution reduce the accuracy and robustness of the estimated trajectory. To address these limitations, we propose a motion-aware event-based VIO (MA-EVIO) system that adaptively fuses asynchronous event data, frame-based imagery, and inertial measurements for robust and accurate pose estimation. MA-EVIO employs a hybrid tracking strategy combining sparse feature matching and direct photometric alignment. A key innovation is its motion-aware keyframe selection, which dynamically adjusts tracking parameters based on real-time motion classification and feature quality. This motion awareness also enables adaptive sensor fusion: during fast motion, the system prioritizes event data, while under slow or stable motion, it relies more on RGB frames and feature-based tracking. Experimental results on the DAVIS240c and VECtor benchmarks demonstrate that MA-EVIO outperforms state-of-the-art methods, achieving a lower mean position error (MPE) of 0.19 on DAVIS240c compared to 0.21 (EVI-SAM) and 0.24 (PL-EVIO), and superior performance on VECtor with MPE/mean rotation error (MRE) of 1.19%/1.28 deg/m versus 1.27%/1.42 deg/m (EVI-SAM) and 1.93%/1.56 deg/m (PL-EVIO). These results validate the effectiveness of MA-EVIO in challenging dynamic indoor environments.

Fifth-generation (5G) wireless networks have been widely deployed across various applications, including indoor positioning. This paper presents a model for 3D indoor localization of an unmanned aerial vehicle (UAV) using 5G millimeter-wave technology. Wireless InSite software is used to simulate a real-world environment and extract channel state information from multiple 5G next-generation NodeBs (gNBs), which is then used to generate channel frequency response (CFR) images. These images are employed in a fingerprinting method, where a deep convolutional neural network is trained for accurate position prediction. The model is trained across multiple scenarios involving changes in the number of gNBs, receiver positions, and spacing. In all scenarios, the model is tested using a UAV flying along a trajectory at variable speed. It is shown that a mean positioning error (MPE) of 0.36 m in 2D and 0.43 m in 3D is achieved when twelve gNBs with receivers spaced at 0.25 m are used. In addition, the corresponding root mean square error (RMSE) values of 0.32 m (2D) and 0.33 m (3D) further confirm the stability of the localization performance by indicating a low dispersion of positioning errors. This demonstrates that high positioning accuracy is feasible, even when synchronization errors and hardware imperfections exist.

Three-dimensional building extraction is crucial for urban planning, environmental analysis, and autonomous navigation. One method for data collection involves using unmanned aerial vehicles (UAVs), which allow for flexible and rapid data acquisition. However, accurate 3D building extraction from these data remains challenging due to the abundance of information in high-resolution datasets. To tackle this problem, a novel UAV-based multi-sensor data fusion model is developed, which utilizes deep neural networks (DNNs) to enhance point cloud segmentation. Urban datasets, acquired by a UAV equipped with a Zenmuse L1 payload, are collected and used to train, validate, and test the DNNs. It is shown that most building extraction results have precision, accuracy, and F-score values greater than 0.96.