LiDAR Point Cloud Data Research Articles

Estimating Cooling Energy Demand from Building Attributes and Environmental Parameters using 3D City Models

Abstract. Most of the global population have shifted to urbanization with advancements in technology. With this transition comes the responsibility of applying these technologies to promote sustainable development practice. Since energy demand is highest in the urbanized areas, it is important that proper assessment and management of energy resource is considered in policy-making and urban planning. This study investigated the estimation of cooling energy demand in Iloilo City Proper, Philippines using a 3D city model integrated with building attributes including building functions and year of construction, while also taking into consideration meteorological factors in the area. The proposed method used the application SimStadt2.0, following the German computation standard DINV18599. Building functions and year of construction were extracted from available building attributes data and satellite images respectively, using the free and open-source software QGIS. A CityGML Level of Detail 1 was generated from 3Dfier using building footprints and LiDAR point cloud data, along with the extracted building attributes of the 5,426 buildings. Meteorological data from INSEL 8 were also considered in the estimation of cooling energy demand in SimStadt2.0. Results showed a monthly energy demand of 12.33 kWh to 313,530.08 kWh in the study area. The estimated energy demand values were higher than the standard mean for different building functions in the country, but within the expected range of values for each season. Urban Heat Islands (UHIs), analyzed using Land Surface Temperature (LST) values, also have significant correlation to areas with higher cooling energy demands. However, inconsistencies can imply the need for further investigation.

Unveiling Anomalies in Terrain Elevation Products from Spaceborne Full-Waveform LiDAR over Forested Areas

Anomalies displaying significant deviations between terrain elevation products acquired from spaceborne full-waveform LiDAR and reference elevations are frequently observed in assessment studies. While the predominant focus is on “normal” data, recognizing anomalies within datasets obtained from the Geoscience Laser Altimeter System (GLAS) and the Global Ecosystem Dynamics Investigation (GEDI) is essential for a comprehensive understanding of widely used spaceborne full-waveform data, which not only facilitates optimal data utilization but also enhances the exploration of potential applications. Nevertheless, our comprehension of anomalies remains limited as they have received scant specific attention. Diverging from prevalent practices of directly eliminating outliers, we conducted a targeted exploration of anomalies in forested areas using both transmitted and return waveforms from the GLAS and the GEDI in conjunction with airborne LiDAR point cloud data. We unveiled that elevation anomalies stem not from the transmitted pulses or product algorithms, but rather from scattering sources. We further observed similarities between the GLAS and the GEDI despite their considerable disparities in sensor parameters, with the waveforms characterized by a low signal-to-noise ratio and a near exponential decay in return energy; specifically, return signals of anomalies originated from clouds rather than the land surface. This discovery underscores the potential of deriving cloud-top height from spaceborne full-waveform LiDAR missions, particularly the GEDI, suggesting promising prospects for applying GEDI data in atmospheric science—an area that has received scant attention thus far. To mitigate the impact of abnormal return waveforms on diverse land surface studies, we strongly recommend incorporating spaceborne LiDAR-offered terrain elevation in data filtering by establishing an elevation-difference threshold against a reference elevation. This is especially vital for studies concerning forest parameters due to potential cloud interference, yet a consensus has not been reached within the community.

Seal Pipeline: Enhancing Dynamic Object Detection and Tracking for Autonomous Unmanned Surface Vehicles in Maritime Environments

This study addresses the dynamic object detection problem for Unmanned Surface Vehicles (USVs) in marine environments, which is complicated by boat tilting and camera illumination sensitivity. A novel pipeline named “Seal” is proposed to enhance detection accuracy and reliability. The approach begins with an innovative preprocessing stage that integrates data from the Inertial Measurement Unit (IMU) with LiDAR sensors to correct tilt-induced distortions in LiDAR point cloud data and reduce ripple effects around objects. The adjusted data are grouped using clustering algorithms and bounding boxes for precise object localization. Additionally, a specialized Kalman filter tailored for maritime environments mitigates object discontinuities between successive frames and addresses data sparsity caused by boat tilting. The methodology was evaluated using the VRX simulator, with experiments conducted on the Volga River using real USVs. The preprocessing effectiveness was assessed using the Root Mean Square Error (RMSE) and tracking accuracy was evaluated through detection rate metrics. The results demonstrate a 25% to 30% improvement in detection accuracy and show that the pipeline can aid industry even with sparse object representation across different frames. This study highlights the potential of integrating sensor fusion with specialized tracking for accurate dynamic object detection in maritime settings, establishing a new benchmark for USV navigation systems’ accuracy and reliability.

Intelligent processing of UAV remote sensing data for building high-precision DEMs in complex terrain: A case study of Loess Plateau in China

The Loess Plateau in China is renowned for its dense gullies and complex terrain, with drastic changes primarily due to soil erosion and human activities, significantly affecting the evolution of the ecological environment. The complex terrains and dense vegetation make precise terrain measurement and modeling challenging. Although the development of Unmanned Aerial Vehicle (UAV) light detection and ranging (LiDAR) scanning and photogrammetry technologies has improved data acquisition precision, relying solely on one remote sensing technology struggles with accurately extracting bare earth information. This study adopted a method that fuses UAV lidar scanning with aerial photogrammetric imagery, generating detailed lidar point cloud data that includes coordinate, reflectance, true color, and texture information to enhance data classifiability and interpretability. Subsequently, a point cloud classification model based on the Transformer architecture (Stratified Transformer) is introduced to intelligently complete the initial ground point cloud extraction in complex gully terrains. Further, to address residual non-ground noise in the initial ground point clouds, a new point cloud classification optimization algorithm (MDD, Multi-scale C2M Distance Difference) is proposed. This algorithm, based on the characteristics of discrete and non-continuous with the ground surface of the noisy point clouds, effectively eliminates the discrete noisy point clouds by analyzing the distances between the point clouds and TINs (Triangular Irregular Networks) of different scales and their differences. This study effectively addresses the technical challenges of ground point cloud extraction in the mixed environment of complex terrain and vegetation, solving the problem of precise terrain measurement and intelligent data processing in complex gully terrains, and offering new technical pathways for detecting geomorphological changes.

Modelling the Contributions of Riparian Vegetation and Topography to Stream Shade Using LiDAR and Conventional Digital Elevation Data

ABSTRACTStream temperature is widely considered the master variable in stream ecosystems. One of the key drivers of diel and seasonal stream temperature variability is the solar radiation received at the stream surface, which can be influenced by shading associated with both larger scale topographic features and riparian vegetation. In this study, a stream shade model was developed that uses LiDAR point cloud data to model shading by riparian vegetation, including canopy overhang, and conventional elevation data to model stream shading by topography. The model was applied to a dominantly north–south oriented river flowing in a floodplain within a mountain valley. When compared with shade interpreted from PlanetScope visual imagery, the model predicted stream shade at the point scale with 92% agreement. Sources of error were attributed to pixel and azimuth band size, which can be refined within the model arguments, although at the cost of increased processing time. The shade model was re‐run after virtually rotating the reach by 90° and 270° clockwise to evaluate the effect of valley orientation. Peak reach‐wide sunlight exposure occurred approximately 2 h later in the day when the stream reach was rotated 90°, and produced greater shading from mid‐morning to mid‐afternoon. Further work should test the model on smaller streams using ground‐based oblique or drone‐based photography to provide ground‐truthing, particularly to assess the accuracy of predicted shade below over‐hanging vegetation.

LiDAR point cloud simplification strategy utilizing probabilistic membership

With the continuous progress of information acquisition technology, the volume of LiDAR point cloud data is also expanding rapidly, which greatly hinders the subsequent point cloud processing and engineering applications. In this study, we propose a point cloud simplification strategy utilizing probabilistic membership to address this challenge. The methodology initially develops a feature extraction scheme based on curvature to identify the set of feature points. Subsequently, a combination of k-means clustering and Possibilistic C-Means is employed to partition the point cloud into subsets, and to simultaneously acquire the probabilistic membership information of the point cloud. This information is then utilized to establish a rational and efficient simplification scheme. Finally, the simplification results of the feature point set and the remaining point set are merged to obtain the ultimate simplification outcome. This simplification method not only effectively preserves the features of the point cloud while maintaining uniformity in the simplified results but also offers flexibility in balancing feature retention and the degree of simplification. Through comprehensive comparative analysis across multiple point cloud models and benchmarking against various simplification methods, the proposed approach demonstrates superior performance. Finally, the proposed algorithm was critically discussed in light of the experimental results.

TrajectoryNAS: A Neural Architecture Search for Trajectory Prediction.

Autonomous driving systems are a rapidly evolving technology. Trajectory prediction is a critical component of autonomous driving systems that enables safe navigation by anticipating the movement of surrounding objects. Lidar point-cloud data provide a 3D view of solid objects surrounding the ego-vehicle. Hence, trajectory prediction using Lidar point-cloud data performs better than 2D RGB cameras due to providing the distance between the target object and the ego-vehicle. However, processing point-cloud data is a costly and complicated process, and state-of-the-art 3D trajectory predictions using point-cloud data suffer from slow and erroneous predictions. State-of-the-art trajectory prediction approaches suffer from handcrafted and inefficient architectures, which can lead to low accuracy and suboptimal inference times. Neural architecture search (NAS) is a method proposed to optimize neural network models by using search algorithms to redesign architectures based on their performance and runtime. This paper introduces TrajectoryNAS, a novel neural architecture search (NAS) method designed to develop an efficient and more accurate LiDAR-based trajectory prediction model for predicting the trajectories of objects surrounding the ego vehicle. TrajectoryNAS systematically optimizes the architecture of an end-to-end trajectory prediction algorithm, incorporating all stacked components that are prerequisites for trajectory prediction, including object detection and object tracking, using metaheuristic algorithms. This approach addresses the neural architecture designs in each component of trajectory prediction, considering accuracy loss and the associated overhead latency. Our method introduces a novel multi-objective energy function that integrates accuracy and efficiency metrics, enabling the creation of a model that significantly outperforms existing approaches. Through empirical studies, TrajectoryNAS demonstrates its effectiveness in enhancing the performance of autonomous driving systems, marking a significant advancement in the field. Experimental results reveal that TrajcetoryNAS yields a minimum of 4.8 higger accuracy and 1.1* lower latency over competing methods on the NuScenes dataset.

Estimating Maize Crop Height and Aboveground Biomass Using Multi-Source Unmanned Aerial Vehicle Remote Sensing and Optuna-Optimized Ensemble Learning Algorithms

Accurately assessing maize crop height (CH) and aboveground biomass (AGB) is crucial for understanding crop growth and light-use efficiency. Unmanned aerial vehicle (UAV) remote sensing, with its flexibility and high spatiotemporal resolution, has been widely applied in crop phenotyping studies. Traditional canopy height models (CHMs) are significantly influenced by image resolution and meteorological factors. In contrast, the accumulated incremental height (AIH) extracted from point cloud data offers a more accurate estimation of CH. In this study, vegetation indices and structural features were extracted from optical imagery, nadir and oblique photography, and LiDAR point cloud data. Optuna-optimized models, including random forest regression (RFR), light gradient boosting machine (LightGBM), gradient boosting decision tree (GBDT), and support vector regression (SVR), were employed to estimate maize AGB. Results show that AIH99 has higher accuracy in estimating CH. LiDAR demonstrated the highest accuracy, while oblique photography and nadir photography point clouds were slightly less accurate. Fusion of multi-source data achieved higher estimation accuracy than single-sensor data. Embedding structural features can mitigate spectral saturation, with R2 ranging from 0.704 to 0.939 and RMSE ranging from 0.338 to 1.899 t/hm2. During the entire growth cycle, the R2 for LightGBM and RFR were 0.887 and 0.878, with an RMSE of 1.75 and 1.76 t/hm2. LightGBM and RFR also performed well across different growth stages, while SVR showed the poorest performance. As the amount of nitrogen application gradually decreases, the accumulation and accumulation rate of AGB also gradually decrease. This high-throughput crop-phenotyping analysis method offers advantages, such as speed and high accuracy, providing valuable references for precision agriculture management in maize fields.

Efficient Path Planning Algorithm Based on Laser SLAM and an Optimized Visibility Graph for Robots

Mobile robots’ efficient path planning has long been a challenging task due to the complexity and dynamism of environments. If an occupancy grid map is used in path planning, the number of grids is determined by grid resolution and the size of the actual environment. Excessively high resolution increases the number of traversed grid nodes and thus prolongs path planning time. To address this challenge, this paper proposes an efficient path planning algorithm based on laser SLAM and an optimized visibility graph for mobile robots, which achieves faster computation of the shortest path using the optimized visibility graph. Firstly, the laser SLAM algorithm is used to acquire the undistorted LiDAR point cloud data, which are converted into a visibility graph. Secondly, a bidirectional A* path search algorithm is combined with the Minimal Construct algorithm, enabling the robot to only compute heuristic paths to the target node during path planning in order to reduce search time. Thirdly, a filtering method based on edge length and the number of vertices of obstacles is proposed to reduce redundant vertices and edges in the visibility graph. Additionally, the bidirectional A* search method is implemented for pathfinding in the efficient path planning algorithm proposed in this paper to reduce unnecessary space searches. Finally, simulation and field tests are conducted to validate the algorithm and compare its performance with classic algorithms. The test results indicate that the method proposed in this paper exhibits superior performance in terms of path search time, navigation time, and distance compared to D* Lite, FAR, and FPS algorithms.

MosViT: towards vision transformers for moving object segmentation based on Lidar point cloud

Abstract Moving object segmentation is fundamental for various downstream tasks in robotics and autonomous driving, providing crucial information for them. Effectively extracting spatial-temporal information from consecutive frames and addressing the scarcity of dataset is paramount for learning-based 3D LiDAR Moving Object Segmentation (LIDAR-MOS). In this work, we propose a novel deep neural network based on Vision Transformers (ViTs) to tackle this problem. We first validate the feasibility of Transformer networks for this task, offering an alternative to CNNs. Specifically, we utilize a dual-branch structure based on range-image data to extract spatial-temporal information from consecutive frames and fuse it using a motion-guided attention mechanism. Furthermore, we employ the ViT as the backbone, keeping its architecture unchanged from what is used for RGB images. This enables us to leverage pre-trained models from RGB images to improve results, addressing the issue of limited LIDAR point cloud data, which is cheaper compared to acquiring and annotating point cloud data. We validate the effectiveness of our approach on the LIDAR-MOS benchmark of SemanticKitti and achieve comparable results to methods that use CNNs on range image data. The source code and trained models are available at https://github.com/mafangniu/MOSViT.git.

Intra-Frame Graph Structure and Inter-Frame Bipartite Graph Matching with ReID-Based Occlusion Resilience for Point Cloud Multi-Object Tracking

Three-dimensional multi-object tracking (MOT) using lidar point cloud data is crucial for applications in autonomous driving, smart cities, and robotic navigation. It involves identifying objects in point cloud sequence data and consistently assigning unique identities to them throughout the sequence. Occlusions can lead to missed detections, resulting in incorrect data associations and ID switches. To address these challenges, we propose a novel point cloud multi-object tracker called GBRTracker. Our method integrates an intra-frame graph structure into the backbone to extract and aggregate spatial neighborhood node features, significantly reducing detection misses. We construct an inter-frame bipartite graph for data association and design a sophisticated cost matrix based on the center, box size, velocity, and heading angle. Using a minimum-cost flow algorithm to achieve globally optimal matching, thereby reducing ID switches. For unmatched detections, we design a motion-based re-identification (ReID) feature embedding module, which uses velocity and the heading angle to calculate similarity and association probability, reconnecting them with their corresponding trajectory IDs or initializing new tracks. Our method maintains high accuracy and reliability, significantly reducing ID switches and trajectory fragmentation, even in challenging scenarios. We validate the effectiveness of GBRTracker through comparative and ablation experiments on the NuScenes and Waymo Open Datasets, demonstrating its superiority over state-of-the-art methods.

SaBi3d—A LiDAR Point Cloud Data Set of Car-to-Bicycle Overtaking Maneuvers

While cycling presents environmental benefits and promotes a healthy lifestyle, the risks associated with overtaking maneuvers by motorized vehicles represent a significant barrier for many potential cyclists. A large-scale analysis of overtaking maneuvers could inform traffic researchers and city planners how to reduce these risks by better understanding these maneuvers. Drawing from the fields of sensor-based cycling research and from LiDAR-based traffic data sets, this paper provides a step towards addressing these safety concerns by introducing the Salzburg Bicycle 3d (SaBi3d) data set, which consists of LiDAR point clouds capturing car-to-bicycle overtaking maneuvers. The data set, collected using a LiDAR-equipped bicycle, facilitates the detailed analysis of a large quantity of overtaking maneuvers without the need for manual annotation through enabling automatic labeling by a neural network. Additionally, a benchmark result for 3D object detection using a competitive neural network is provided as a baseline for future research. The SaBi3d data set is structured identically to the nuScenes data set, and therefore offers compatibility with numerous existing object detection systems. This work provides valuable resources for future researchers to better understand cycling infrastructure and mitigate risks, thus promoting cycling as a viable mode of transportation.

FLApy: A Python package for evaluating the 3D light availability heterogeneity within forest communities

Abstract Light availability (LAv) dictates a variety of biological and ecological processes across a range of spatiotemporal scales. Quantifying the spatial pattern of LAv in three‐dimensional (3D) space can promote the understanding of microclimates that are critical to fine‐scale species distribution. However, there is still a lack of tools that are robust to evaluate spatiotemporal heterogeneity of LAv in forests. Here, we propose the Forest Light Analyzer python package (FLApy), an open‐source computational tool designed for the analysis of intra‐forest LAv variation across multiple spatial scales. FLApy is freely invoked by Python, facilitating the processing of LiDAR point cloud data into a 3D data container constructed by voxels, as well as traversal calculations related to the LAv regime by high performance synthetic hemispherical algorithm. Furthermore, FLApy incorporates 37 indicators, enabling users to expediently export and visualize LAv patterns and the evaluation of heterogeneity of LAv at two scales (voxel scale and 3D‐cluster scale) for a range of fine‐scale ecological study purposes. To validate the efficacy of the FLApy, we employed a simulated point cloud dataset that simulates forests (varying in canopy closure). Furthermore, to evaluate real world forest, we executed the standard workflow of FLApy utilizing drone‐derived data from three subtropical evergreen broad‐leaved forest dynamics plots within the Ailao Mountain Reserve. Our findings underscore that a series of indices derived from FLApy provide a robust characterization of light availability heterogeneity within diverse forest settings. Additionally, when juxtaposed with conventional monitoring techniques, the metrics offered by FLApy demonstrated better generality in our field assessments. FLApy offers ecologists a solution for rapid quantification of understory light 3D‐regimes across multiple scales, addressing the disparity between traditional manual approaches and the precision required for contemporary ecological studies. Moreover, FLApy provides robust support for the establishment and expansion of heterogeneity indices based on 3D micro‐environments, enhancing our understanding of the largely uncharted 3D structural patterns. Anticipated outcomes suggest that FLApy will enhance our knowledge concerning the intra‐forest climatic conditions into a 3D context, proving pivotal in the delineation of microhabitats and the development of detailed 3D‐scale species distribution models.

Assessment of traffic sign retroreflectivity for autonomous vehicles: a comparison between handheld retroreflectometer and LiDAR data

This study investigates the critical role of retroreflectivity in traffic signs, particularly in the context of autonomous vehicles (AVs), where accurate detection is paramount for road safety. Retroreflectivity, influencing visibility and legibility, is essential for ensuring safe road conditions. The study aims to assess traffic sign retroreflectivity using handheld retroreflectometers and LiDAR data, offering a comprehensive comparison of results with a specific focus on the RA1 and RA2 traffic sign classes. In a real-world setting, an AV equipped with LiDAR sensors, GPS units, and a stereo camera collects data on traffic signs, including point cloud attributes such as intensity and density. Simultaneously, a handheld retroreflectometer measures retroreflectivity coefficients from identified traffic signs. While retroreflectometers provide precision, they face limitations regarding time-consuming measurements and handling large or elevated signs. In contrast, LiDAR systems efficiently evaluate retroreflective features for numerous signs without such constraints. Despite both methods consistently yielding accurate retroreflectivity, the study reveals a limited correlation between LiDAR point cloud data and handheld retroreflectivity coefficients. The implications of these findings are significant, particularly in the selection and maintenance of retroreflective materials in traffic signs, with direct repercussions on overall road safety. The results offer valuable insights into leveraging LiDAR technology to enhance AVs' detection capabilities. Recommendations for further research include exploring factors influencing LiDAR intensity, establishing a more accurate relationship between intensity and retroreflectivity, correcting the point cloud during intensity calibration, and testing empirical prediction models with a larger sample size. These endeavors aim to generate a robust regression graph and determine correlation coefficients, providing a more nuanced understanding of the intricate relationship between LiDAR data and handheld retroreflectivity coefficients in the context of traffic sign assessment.

Use of lidar for monitoring vegetation growth dynamics in reclaimed mine lands in Kentucky

Surface coal mining in the Appalachian region has led to a significant forest disturbance over time. Evaluating the effectiveness of current reclamation practices in promoting vegetation growth on reclaimed mine sites is a key to understanding how much vegetation has changed in those sites since reclamation. This study employed statewide airborne lidar data to assess changes in lidar vegetation structural metrics on reclaimed mine lands in the Lower Levisa Watershed of Eastern Kentucky between 2011 and 2019 and compare vegetation growth at various reclaimed sites reclaimed in different decades. Eighteen inactive surface mines were selected for the study and categorized into four groups based on the release of their reclamation bonds in different decades. Lidar point cloud data were processed in ArcGIS Pro using filtering and segmentation algorithms to calculate various vegetation attributes from the point clouds, including maximum vegetation height (Hmax), mean height (Hmean), standard deviation of height (HSD), canopy cover (CC), and height percentiles (10, 50 and 75), which were represented as lidar metrics. The process of generating the lidar metrics involved creating Digital Elevation Models (DEMs) and Digital Surface Models (DSMs), calculating Canopy Height Models (CHMs), creating LAS height metrics and generating point statistics rasters to derive these metrics. Change maps for each metric were visually assessed over time, and circular plots with a radius of 12 m were established within each site for further statistical analysis. Significant changes in lidar vegetation metrics were observed between 2011 and 2019 with significant differences among sites reclaimed at different time periods. There was an overall increase in Hmean from 2011 to 2019, with values ranging from 2.4 to 3.8 m. Sites reclaimed in the 1980s experienced an average decrease in canopy cover of −0.5%, while those from the 1990s, 2000s, and 2010s demonstrated increases of 4.9%, 10.1%, and 18.1%, respectively, suggesting that canopy growth rates are higher in younger sites compared to older ones. Vertical variability of the vegetation also increased over time, as indicated by increasing HSD values. Utilizing statewide airborne lidar data allowed for a comprehensive and detailed assessment of vegetation dynamics on reclaimed mine lands. The findings of this study serve as a foundation for future research endeavors focused on vegetation recovery assessment and success in reclaimed mine lands using lidar data.

A panoramic driving perception fusion algorithm based on multi-task learning.

With the rapid development of intelligent connected vehicles, there is an increasing demand for hardware facilities and onboard systems of driver assistance systems. Currently, most vehicles are constrained by the hardware resources of onboard systems, which mainly process single-task and single-sensor data. This poses a significant challenge in achieving complex panoramic driving perception technology. While the panoramic driving perception algorithm YOLOP has achieved outstanding performance in multi-task processing, it suffers from poor adaptability of feature map pooling operations and loss of details during downsampling. To address these issues, this paper proposes a panoramic driving perception fusion algorithm based on multi-task learning. The model training involves the introduction of different loss functions and a series of processing steps for lidar point cloud data. Subsequently, the perception information from lidar and vision sensors is fused to achieve synchronized processing of multi-task and multi-sensor data, thereby effectively improving the performance and reliability of the panoramic driving perception system. To evaluate the performance of the proposed algorithm in multi-task processing, the BDD100K dataset is used. The results demonstrate that, compared to the YOLOP model, the multi-task learning network performs better in lane detection, drivable area detection, and vehicle detection tasks. Specifically, the lane detection accuracy improves by 11.6%, the mean Intersection over Union (mIoU) for drivable area detection increases by 2.1%, and the mean Average Precision at 50% IoU (mAP50) for vehicle detection improves by 3.7%.

Research on LiDAR point cloud data transformation method based on weighted altitude difference map

Road surface detection plays a pivotal role in the realm of autonomous vehicle navigation. Contemporary methodologies primarily leverage LiDAR for acquiring three-dimensional data and utilize imagery for chromatic information. However, these approaches encounter significant integration challenges, particularly due to the inherently unstructured nature of 3D point clouds. Addressing this, our novel algorithm, specifically tailored for predicting drivable areas, synergistically combines LiDAR point clouds with bidimensional imagery. Initially, it constructs an altitude discrepancy map via LiDAR, capitalizing on the height uniformity characteristic of planar road surfaces. Subsequently, we introduce an innovative and more efficacious attention mechanism, streamlined for image feature extraction. This mechanism employs adaptive weighting coefficients for the amalgamation of the altitude disparity imagery and two-dimensional image features, thereby facilitating road area delineation within a semantic segmentation framework. Empirical evaluations conducted using the KITTI dataset underscore our methodology’s superior road surface discernment and extraction precision, substantiating the efficacy of our proposed network architecture and data processing paradigms. This research endeavor seeks to propel the advancement of three-dimensional perception technology in the autonomous driving domain.

Analysis of Multiple Scattering Characteristics of Cable-Stayed Bridges with Multi-band SAR

Abstract. Accurate localization of multi-scattering features of cable-stayed bridges in multi-band Synthetic Aperture Radar (SAR) imagery is crucial for intelligent recognition of bridge targets within images, as well as for precise water level extraction. This study focuses on the Badong Yangtze River Bridge, utilizing Unmanned Aerial Vehicle (UAV) LiDAR data of the bridge, and analyzes the multi-scattering characteristics of different bridge structural targets based on Geometric Optics (GO) methods and the Range-Doppler principle. Furthermore, the study integrates LiDAR data of the bridge's cable-stays to examine their multi-scattering phenomena, finding that the undulations of the Yangtze River's surface waves significantly contribute to the pronounced double scattering features of the bridge's cable-stays. Additionally, statistical analysis of multi-source SAR data indicates that this phenomenon is not directly correlated with radar wavelength, implying no direct connection to surface roughness. Utilizing LiDAR point cloud data from the bridge's street lamps, this paper proposes a novel method for estimating water level elevation by identifying the center position of spots formed by double scattering from lamp posts. The results show that using TerraSAR ascending and descending orbit images, this method achieves a water level elevation accuracy of approximately 0.2 meters.

Research on the drone endoscopic system for fusion reactors

This paper proposes an air-ground separation drone endoscopic system (DES) design scheme for the fusion reactor internal inspection task. A foldable rotor drone with vertical takeoff and landing capability is used as the main body of DES. The nest platform is designed separately from the drone to reduce the weight. Meanwhile, the nest platform can be installed with a safety cable and 2D code to realize emergency rescue and precise take-off and landing. DES adds 3D lidar sensors for 360° stereo sensing, realizing real-time positioning in dark or even lightless environments in vacuum chambers. The first-generation DES prototype is developed, and the flight test is performed inside the PF6 superconducting coil shell by fusing 3D lidar point cloud data with visual camera image data. The results show that the position error of DES is stabilized within ±0.05 m during the hovering phase. The error is mainly due to the narrow space inside the PF6 coil shell, which produces a perturbed flow field on the DES. In general, the DES accomplished circumferential autonomous flight control and 3D point cloud data acquisition in a confined space, proving the feasibility of drone inspection in vacuum chambers.

A Brief Discussion on the Overall Classification Algorithm of Airborne LiDAR Point Cloud

Abstract. Point cloud classification is the most important problem in airborne LiDAR point cloud data processing. In recent years, classification strategies with new theoretical background keep emerging, so it is urgent to make a more systematic and detailed summary of existing point cloud filtering algorithms, so that relevant researchers can have a more macroscopic and clear understanding of various algorithms and their advantages and disadvantages. Based on the characteristics of airborne LiDAR point cloud data, this paper combs the general process of point cloud classification. This paper summarizes the current mainstream classification methods and analyses their application effects in different scenarios, aiming at exploring and customizing suitable point cloud classification methods according to specific purpose objectives or industry standards. The point cloud classification is classified into three-level classification strategy. The first-level classification is gross error elimination, the second-level classification is point cloud filtering, which is to distinguish ground points from non-ground points. The third-level classification is to extract thematic point clouds from non-ground points according to application requirements. At present, the primary and secondary classification methods are relatively diverse and mature, reaching a certain level of application, while the tertiary classification is still in the initial stage of exploration, and large-scale application is not widespread.