Explore the vast range of titles available.

A high-definition (HD) map development framework providing real-time visualization of multimodal perception data for state estimation, motion planning, and decision-making in autonomous navigation is presented and experimentally validated. The proposed framework integrates synchronized visual and LiDAR data and generates consistent frame transformations to construct accurate and interpretable HD maps suitable for navigation in dynamic environments. In addition, the framework enables flexible customization of essential map elements, including road features and static landmarks, facilitating efficient map generation and visualization. Building upon the developed HD map visualizer, a semantic-aware visual odometry (VO)-based pose estimation module is designed and verified through extensive evaluations and under perceptually degraded conditions. To ensure the reliability of synchronized multimodal data used by downstream perception and pose estimation modules, a sensor health monitoring system is also developed and validated in urban canyon scenarios with intermittent or unavailable global navigation satellite system (GNSS) measurements. Experimental results demonstrate that the proposed HD map visualizer and associated perception modules are transferable for autonomous navigation and can be effectively employed as benchmarking tools for state estimation and motion planning algorithms in autonomous driving.

The operational effectiveness of Unmanned Surface Vehicles (USVs) in modern naval scenarios depends on robust situational awareness. While LiDAR sensors are integral to 3D perception, their performance is frequently affected by incomplete data resulting from long-range sparsity and target occlusion. This study investigates a framework to restore incomplete point clouds to support improved surface vessel classification. The framework first estimates the target’s heading angle using a 2D area projection technique, combined with a descriptor to address orientation ambiguity. Subsequently, the 3D point cloud is converted into a 2D multi-channel image representation to leverage a deep learning-based image inpainting algorithm for data restoration. Finally, a high-density keypoint extraction method is applied to the completed point cloud to generate features for classification. This image-based approach is designed to prioritize computational efficiency and inference speed, facilitating deployment on resource-constrained maritime platforms. Experiments conducted on a simulator dataset reveal that the classification of restored point clouds yields higher accuracy compared to using the original, incomplete LiDAR data, particularly at extended distances (>70 m) and challenging aspect angles (0° and 180°). The results suggest the framework’s potential to address perception failures in sparse data scenarios, thereby supporting the operational envelope of USVs in contested environments.

Aiming at the problems of low efficiency and high cost in determining the phenotypic parameters of Cymbidium seedlings by artificial approaches, this study proposed a fully automated measurement scheme for some phenotypic parameters based on point cloud. The key point or difficulty is to design a segmentation method for individual tillers according to the morphology-specific structure. After determining the branch points, two rounds of segmentation schemes were designed. The non-overlapping part of each tiller and the overlapping parts of each ramet are separated in the first round based on the edge point cloud-based segmentation, while in the second round, the overlapping part was sliced along the horizontal direction according to the weight ratio of the tillers above, to obtain the complete point cloud of all tillers. The core superiority of the algorithm is that the segmentation fits the tiller growth direction well, and the extracted skeleton points of tillers are close to the actual growth direction, significantly improving the prediction accuracy of the subsequent phenotypic parameters. Five phenotypic parameters, plant height, leaf number, leaf length, leaf width and leaf area, were automatically calculated. Through experiments, the accuracy of the five parameters reached 98.6%, 100%, 92.2%, 89.1%, and 82.3%, respectively, which reach the needs of various phenotypic applications.

High-precision 3D point cloud data have various analyses and application use cases. This study aimed to achieve a more precise noise reduction of the raw 3D point cloud data of asphalt pavements obtained using 3D laser scanning. Hence, a noise-reduction algorithm integrating improved Gaussian filtering and coefficient of variation was developed. A portable laser scanner was used to collect raw, high-precision 3D point cloud data of surface textures from pavement slab samples prepared with three different types of asphalt mixtures: AC-13, SMA-13, and OGFC-13, as well as asphalt from the test sections of the Yakang Expressway. An improved Gaussian filtering and Gaussian filtering that extracts noise using the coefficient of variation were used to filter out the obvious outlier noise and small-scale burr noise, respectively. Finally, the filtering effect of the proposed algorithm, Gaussian filtering, median filtering, and mean filtering on raw 3D point cloud data of pavement textures was evaluated through subjective visual quality and objective index evaluations. The results showed that the proposed algorithm filters out noise while preserving the micro-texture structure information, outperforming Gaussian filtering, median filtering, and mean filtering.

Morphological neuron classification helps to reveal the functional characteristics and information transmission mechanisms of the nervous system. However, existing methods that use geometric feature extraction or image-based transformation do not consider the 3D properties of neurons, often resulting in a significant loss of valuable morphological information. To address this, we propose a spiking point cloud neural network (SPCNNet) model to improve classification performance, which is capable of directly processing 3D point clouds and applying spike signals to represent morphological features and classify neurons. A neuronal representation strategy is designed to convert original SWC data into 3D point clouds, and encode real-valued point cloud data into spike trains for further processing by the spiking neural networks. Furthermore, the SPCNNet model with spike-based deep learning algorithm learns the spatial features of neurons for classification tasks. In experiment, we analyzed the impact of different SPCNNet parameters on neuron classification performance, including the number of sampled points, simulation duration and batch size. We also conducted ablation experiments to verify the effectiveness of the proposed method. Experimental results demonstrate that our SPCNNet method precisely represents neuronal morphologies and achieves superior performance on the two NeuroMorpho datasets, with classification accuracies of 84.76% and 85.42% respectively. Compared with other mainstream machine learning methods, our spike-driven method is more plausible for solving complex morphological neuron classification problems on NeuMorph dataset.

Small-modulus gears, which are essential for motion transmission in precision instruments, present a measurement challenge due to their minuscule gear gaps. A high-precision measurement method under the influence of positioning errors is proposed, enabling precise evaluation of the machining quality of small-modulus gears. Firstly, a compound measurement platform for small-modulus gears is developed. Using a 3D model of the measurement system, the mathematical relationships governing motion transmission between various components are analyzed. Secondly, the formation mechanism of gear positioning error is revealed and its important influence on measurement accuracy is discussed. An optimization method for spatial coordinate transformation matrices under positioning errors of gears is proposed. Thirdly, the study focuses on small-sized gears with a modulus of 0.1 mm and a six-level accuracy. Based on the aforementioned measurement system, the tooth profile measurement points are collected in the actual workpiece coordinate system. Then, gear error parameters are extracted based on the established models for tooth profile deviation and pitch deviation. Finally, the accuracy and effectiveness of the proposed measurement method are verified by comparing the measurement results of the P26 gear measuring center.

With the rapid development of computer technology and measurement technology, three-dimensional point cloud data, as an important form of data in computer graphics, is used by light reactions in reverse engineering, surveying, robotics, virtual reality, stereo 3D imaging, Indoor scene reconstruction and many other fields. This paper aims to study the key technology of 3D point cloud data multi-view image texture mapping seam fusion, and propose a joint coding and compression scheme of multi-view image texture to replace the previous independent coding scheme of applying MVC standard compression to multi-view image texture. Experimental studies have shown that multi-view texture depth joint coding has different degrees of performance improvement compared with the other two current 3D MVD data coding schemes. Especially for Ballet and Dancer sequences with better depth video quality, the performance of JMVDC is very obvious. Compared with the KS_ IBP structure, the gain can reach as high as 1.34dB at the same bit rate.

Giant trees are pivotal in forest ecosystems, yet our current understanding of their significance is constrained primarily by the limited knowledge of their precise locations and structural characteristics. Amidst escalating human‐induced disturbances globally, there is an urgent need to devise a practical approach to discover and measure giant trees accurately and efficiently. Here, we propose a novel light detection and ranging (lidar)‐based framework designed for the discovery and measurement of giant trees. Our framework integrates cutting‐edge lidar platforms, including spaceborne, Unmanned Aerial Vehicle (UAV), and backpack lidar, to create an end‐to‐end workflow. The algorithm involved in the proposed framework was compiled into a code package and made available as open source. The method successfully identified the tallest trees in China, including the tallest tree in Asia, a Cupressus austrotibetica with a height of 102.3 m, discovered in Yarlung Zangbo Grand Canyon in May 2023. This finding has not only established a new record but also demonstrated the efficacy of our proposed framework. Utilising lidar data, we performed meticulous measurements at both individual and stand levels, revealing the unique characteristics of this giant tree. The new framework for the discovery and measurement of giant trees, encompassing detailed procedures and codes, is expected to facilitate the discovery and measurement of giant trees with high efficiency, thus fostering advancements in giant tree ecology.

Leaves are used extensively as an indicator in research on tree growth. Leaf area, as one of the most important index in leaf morphology, is also a comprehensive growth index for evaluating the effects of environmental factors. When scanning tree surfaces using a 3D laser scanner, the scanned point cloud data usually contain many outliers and noise. These outliers can be clusters or sparse points, whereas the noise is usually non-isolated but exhibits different attributes from valid points. In this study, a 3D point cloud filtering method for leaves based on manifold distance and normal estimation is proposed. First, leaf was extracted from the tree point cloud and initial clustering was performed as the preprocessing step. Second, outlier clusters filtering and outlier points filtering were successively performed using a manifold distance and truncation method. Third, noise points in each cluster were filtered based on the local surface normal estimation. The 3D reconstruction results of leaves after applying the proposed filtering method prove that this method outperforms other classic filtering methods. Comparisons of leaf areas with real values and area assessments of the mean absolute error (MAE) and mean absolute error percent (MAE%) for leaves in different levels were also conducted. The root mean square error (RMSE) for leaf area was 2.49 cm2. The MAE values for small leaves, medium leaves and large leaves were 0.92 cm2, 1.05 cm2 and 3.39 cm2, respectively, with corresponding MAE% values of 10.63, 4.83 and 3.8. These results demonstrate that the method proposed can be used to filter outliers and noise for 3D point clouds of leaves and improve 3D leaf visualization authenticity and leaf area measurement accuracy.

Forests play a crucial role in carbon sequestration and climate change mitigation, offering ecosystem services, biodiversity conservation, and water resource management. As global efforts to reduce greenhouse gas emissions intensify, the demand for accurate spatial information to monitor forest conditions and assess carbon absorption capacity has grown. LiDAR (Light Detection and Ranging) has emerged as a transformative tool, providing high-resolution 3D spatial data for detailed analysis of forest attributes, including tree height, canopy structure, and biomass distribution. Unlike traditional manpower-intensive forest surveys, which are time-consuming and often limited in accuracy, LiDAR offers a more efficient and reliable solution. This study evaluates the accuracy and applicability of advanced LiDAR technologies—drone-mounted, terrestrial, and mobile scanners—for generating 3D forest spatial data. The results show that the terrestrial LiDAR achieved the highest precision for diameter at breast height (DBH) and tree height measurements, with RMSE values of 0.66 cm and 0.91 m, respectively. Drone-mounted LiDAR demonstrated excellent efficiency for large-scale surveys, while mobile LiDAR offered portability and speed but required further improvement in accuracy (e.g., RMSE: DBH 0.76 cm, tree height 1.83 m). By comparing these technologies, this study identifies their strengths, limitations, and optimal application scenarios, contributing to more accurate forest management practices and carbon absorption assessments.