3D Light Detection And Ranging Data Research Articles

Dynamic object detection using sparse LiDAR data for autonomous machine driving and road safety applications

Light Detection And Ranging (LiDAR) sensor offers solutions to extract real-time information of vehicle’s surroundings and can provide a new opportunity to improve the road safety related issues in mixed traffic conditions. This paper explores fundamental principles and combination of algorithms, to accurately detect, classify and track surrounding vehicles on expressways using a vehicle mounted cost-effective LiDAR sensor in dynamic conditions. The proposed approach employs algorithms such as Density-Based Spatial Clustering of Applications with Noise, Random sample consensus, and Kalman filter on 3D LiDAR data for ground and non-ground points segmentation, object clustering, road boundary identification, vehicle classification and tracking. Trajectory data of the tracked vehicles is used to estimate their relative positions and speeds. The surrounding vehicles were classified into three categories: two-wheelers, four-wheelers and heavy-vehicles. The proposed method achieves an accuracy, precision, recall, and F1-score above 94 %, demonstrating its robustness. The resilience and versatility of the proposed algorithm were validated through comprehensive evaluations on a significant dataset spanning over 8000 km (around 3.6 million frames) of driving data collected under varied environmental scenarios on expressway. Further, various applications of proposed methodology in road safety studies are discussed. The approach can extract real-time micro-level trajectory data for surrounding vehicles on expressways in any lighting condition, which is useful for researchers and can be used in connected and autonomous vehicles. It also provides valuable information for assessing surrogate safety measures and identifying road safety issues and suggesting countermeasures, including advanced and cost-effective driver assistance system applications.

Fine-Scale Quantification of Absorbed Photosynthetically Active Radiation (APAR) in Plantation Forests with 3D Radiative Transfer Modeling and LiDAR Data.

Quantifying the relationship between light and stands or individual trees is of great significance in understanding tree competition, improving forest productivity, and comprehending ecological processes. However, accurately depicting the spatiotemporal variability of light under complex forest structural conditions poses a challenge, especially for precise forest management decisions that require a quantitative study of the relationship between fine-scale individual tree structure and light. 3D RTMs (3-dimensional radiative transfer models), which accurately characterize the interaction between solar radiation and detailed forest scenes, provide a reliable means for depicting such relationships. This study employs a 3D RTM and LiDAR (light detection and ranging) data to characterize the light environment of larch plantations at a fine spatiotemporal scale, further investigating the relationship between absorbed photosynthetically active radiation (APAR) and forest structures. The impact of specific tree structural parameters, such as crown diameter, crown area, crown length, crown ratio, crown volume, tree height, leaf area index, and a distance parameter assessing tree competition, on the daily-scale cumulative APAR per tree was investigated using a partial least squares regression (PLSR) model. Furthermore, variable importance in projection (VIP) was also calculated from the PLSR. The results indicate that among the individual tree structure parameters, crown volume is the most important one in explaining individual tree APAR (VIP = 4.19), while the competition from surrounding trees still plays a role in explaining individual tree APAR to some extent (VIP = 0.15), and crown ratio contributes the least (VIP = 0.03). Regarding the spatial distribution of trees, the average cumulative APAR per tree of larch plots does not increase with an increase in canopy gap fraction. Tree density and average cumulative APAR per tree were fitted using a natural exponential equation, with a coefficient of determination (R2 = 0.89), and a small mean absolute percentage error (MAPE = 0.03). This study demonstrates the potential of combining 3D RTM with LiDAR data to quantify fine-scale APAR in plantations, providing insights for optimizing forest structure, enhancing forest quality, and implementing precise forest management practices, such as selective breeding for superior tree species.

High‐resolution model reconstruction and bridge damage detection based on data fusion of unmanned aerial vehicles light detection and ranging data imagery

AbstractDamage detection is essential for the maintenance of transportation infrastructure that experiences high daily traffic levels in potentially extreme environments and changes in use patterns. However, traditional physical inspection is always labor‐intensive, subjective, and biased, lacking the objective perspective required for a comprehensive and reliable assessment. Recently, unmanned aerial vehicles (UAVs) combined with emerging high‐performance sensor(s) have been intensively researched. Here, we present an aerial bridge surface survey method that can be used to assess damage. Existing damage detection methods focus on single types of damage and are limited in locating global damage, whereas our method detects two types of damage on the surface and marks them in a panoramic image. The workflow involves three steps: data acquisition using a meticulous UAV flight strategy that covers the entire surface, data processing using image‐based and point‐cloud models after polynomial rectification, and data output (i.e., damage detected by the combined models). To verify the method, a field test detected damage to two real bridges. A UAV equipped with a camera and light detection and ranging (LiDAR) equipment was employed. Experiments demonstrate the effectiveness of the proposed method, which is capable of producing accurate outputs and detecting damage with an average position error of 13.37 mm and a relative size error of 25.25%. Owing to the data fusion model taking advantage of two‐dimensional (2D) images and 3D LiDAR data, it outputs a high‐resolution 3D model and avoids environmental disturbances. After decision‐making‐level damage fusion, all position and size properties of damage information are computed into a panoramic damage image. This panoramic image showing all detecting damage helps technicians perform maintenance; the image can be zoomed to focus on any issue individually.

Reinforcement and Curriculum Learning for Off-Road Navigation of an UGV with a 3D LiDAR

This paper presents the use of deep Reinforcement Learning (RL) for autonomous navigation of an Unmanned Ground Vehicle (UGV) with an onboard three-dimensional (3D) Light Detection and Ranging (LiDAR) sensor in off-road environments. For training, both the robotic simulator Gazebo and the Curriculum Learning paradigm are applied. Furthermore, an Actor-Critic Neural Network (NN) scheme is chosen with a suitable state and a custom reward function. To employ the 3D LiDAR data as part of the input state of the NNs, a virtual two-dimensional (2D) traversability scanner is developed. The resulting Actor NN has been successfully tested in both real and simulated experiments and favorably compared with a previous reactive navigation approach on the same UGV.

Designing and Building an Intelligent Pavement Management System for Urban Road Networks

Pavement maintenance plays a significant role in megacities. Managing complaints and scheduling road reviews are the two maintenance concerns under the intelligent pavement management system (PMS) plan. In contrast, if the damages are not treated immediately, they will increase over time. By leveraging accurate data from sensors, smart PMS will improve management capability, support sustainability, and drive economic growth in the road network. This research aimed to elaborate on the different modules of an intelligent city pavement network to advance to a sustainable city. First, a 3D mobile light detection and ranging (LiDAR) sensor, accompanied by a camera, was applied as the data collection tool. Although 3D mobile LiDAR data have gained popularity, they lack precise detection of pavement distresses, including cracks. As a result, utilizing RGB imaging may help to detect distresses properly. Two approaches were integrated alongside conducting the data analysis in this paper: (1) ArcGIS pro, developed by Esri Inc., which includes noise removal, digital elevation model (DEM) generation, and pavement and building footprint extraction; (2) the Mechanistic-Empirical Pavement Design Guide (AASHTOWare PMED), which was used to assess site specifications such as traffic, weather, subbase, and current pavement conditions in an effort to design the most appropriate pavement for each road section. For the 3D visualization module, CityEngine (a software from Esri) was used to provide the 3D city model. After implementing the research methodology, we drew the following conclusions: (1) using the AASHTOWare PMED method to make decisions about road maintenance and rehabilitation(M&R) actions can significantly speed up the decision-making process, essentially saving time and money and shortening the project’s duration; and (2) if the road conditions are similar, the smart geographical information system (GIS)-based PMS can make consistent decisions about road M&R strategies, i.e., the interference from human factors is less significant.

Adaptive estimation of UAV altitude in complex indoor environments using degraded and time-delayed measurements with time-varying uncertainties

A novel approach for robust Unmanned Aerial Vehicle (UAV) altitude estimation relying on laser measurements that is designed for use in complex indoor environments is proposed in this paper. Specifically, we aim to design a system with general usability inside multi-floor buildings. The multi-floor buildings are characterized by areas lacking distinct vertical geometric features to be used as reference by 3D Light Detection and Ranging (LiDAR) localization algorithms, and by areas with either flat floors or limited areas with inconsistent ground elevation. The proposed approach solves the problem of adaptive fusion of data from multiple sources with apriori-unknown confidence dependent on the current environmental properties. Whenever the environment contains enough geometric structure, altitude data from a 3D LiDAR-based Simultaneous Localization and Mapping (SLAM) algorithm are utilized. In environments that are too symmetrical for reliable SLAM operation, the approach relies mostly on measurements from a downward-facing 1D laser rangefinder, while simultaneously detecting inconsistent ground elevation areas. These measurements are fused with barometer data, Inertial Measurement Unit (IMU) data, and information from the UAV position controllers. Furthermore, our approach correctly handles the measurement delay caused by 3D LiDAR data processing that significantly differs from other sensor delays. The performance of the proposed approach has been validated in complex simulations and real-world experiments with the produced altitude estimate utilized in the control loop of the UAV. The proposed approach is released as open-source as part of the MRS UAV System.

Robust deep learning LiDAR-based pose estimation for autonomous space landers

Accurate relative pose estimation of a spacecraft during space landing operation is critical to ensure a safe and successful landing. This paper presents a 3D Light Detection and Ranging (LiDAR) based AI relative navigation architecture solution for autonomous space landing. The proposed architecture is based on a hybrid Deep Recurrent Convolutional Neural Network (DRCNN) combining a Convolutional Neural Network (CNN) with an Recurrent Neural Network (RNN) based on a Long–Short Term Memory (LSTM) network. The acquired 3D LiDAR data is converted into a multi-projected images and feed the DRCNN with depth and other multi-projected imagery. The CNN module of the architecture allows an efficient representation of features, and the RNN module, as an LSTM, provides robust navigation motion estimates. A variety of landing scenarios are considered, simulated and experimented to evaluate the efficiency of the proposed architecture. A LiDAR based imagery data (Range, Slope, and Elevation) is initially created using PANGU (Planet and Asteroid Natural Scene Generation Utility) software and an evaluation of the proposed solution using this data is conducted. Tests using an instrumented Aerial Robot in Gazebo software to simulate landing scenarios on a synthetic but representative lunar terrain (3D digital elevation model) is proposed. Finally, real experiments using a real flying drone equipped with a Velodyne VLP16 3D LiDAR sensor to generate real 3D scene point clouds while landing on a designed down scaled lunar moon landing surface are conducted. All the test results achieved show that the suggested architecture is capable of delivering good 6 Degree of Freedom (DoF) pose precision with a good and reasonable computation.

Hidden gaps under the canopy: LiDAR-based detection and quantification of porosity in tree belts

Tree belts (TBs) as one of the agroforestry types, provide many ecosystem services (ESs), that reduce the negative environmental impact of agriculture and increase agricultural productivity. Unfortunately, the lack of quantitative and spatial information regarding TB properties, such as the porosity expressed by gap fraction, often leads to insufficient information on the availability of ESs provided by TBs, such as windbreak efficiency, barrier effectiveness for soil erosion and ability to redistribute snow cover. Moreover, image data, which are usually used for the assessment of TB porosity, only provide 2D information. Therefore, we propose the first comprehensive method of TB porosity indicator estimation conducted by gap mapping using 3D LiDAR (Light Detection and Ranging) data. The method allows to diagnose the spatial structure of TBs necessary for reliable evaluation of ES availability. Detailed cross-section diagnostic graphs and TB silhouette maps showed the intra-TB variation of porosity and thus may support the decision making on the crop types and may lead to better predictions of agricultural production. Also, on a testing study area, we revealed that the proposed method is suitable to significantly improve the accuracy of vegetation volume estimation in TB. Such a detailed analysis of the inner TB structure may be used to maximize the positive effect of tree belts on agricultural production and therefore is a way towards the sustainable agriculture as well as better assessment of ES provided by tree belts.

Fusion of UAV Hyperspectral Imaging and LiDAR for the Early Detection of EAB Stress in Ash and a New EAB Detection Index—NDVI(776,678)

Beijing’s One Million Mu Plain Afforestation Project involves planting large areas with the exotic North American tree species Fraxinus pennsylvanica Marsh (ash). As an exotic tree species, ash is very vulnerable to infestations by the emerald ash borer (EAB), a native Chinese wood borer pest. In the early stage of an EAB infestation, attacked trees show no obvious sign. Once the stand has reached the late damage stage, death occurs rapidly. Therefore, there is a need for efficient early detection methods of EAB stress over large areas. The combination of unmanned aerial vehicle (UAV)-based hyperspectral imaging (HI) with light detection and ranging (LiDAR) is a promising practical approach for monitoring insect disturbance. In this study, we identified the most useful narrow-band spectral HI data and 3D LiDAR data for the early detection of EAB stress in ash. UAV-HI data of different infested stages (healthy, light, moderate and severe) of EAB in the 400–1000 nm range were collected from ash canopies and were processed by Partial Least Squares–Variable Importance in Projection (PLS-VIP) to identify the maximally sensitive bands. Band R678 nm had the highest PLS-VIP scores and the most robust classification ability. We combined this band with band R776 nm to develop an innovative normalized difference vegetation index (NDVI(776,678)) to estimate EAB stress. LiDAR data were used to segment individual trees and supplement the HI data. The new NDVI(776,678) identified different stages of EAB stress, with a producer’s accuracy of 90% for healthy trees, 76.25% for light infestation, 58.33% for moderate infestation, and 100% for severe infestation, with an overall accuracy of 82.90% when combined with UAV-HI and LiDAR.

Visual-LiDAR SLAM Based on Unsupervised Multi-channel Deep Neural Networks

Recently, deep learning techniques have been applied to solve visual or light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) problems. Supervised deep learning SLAM methods need ground truth data for training, but collecting such data is costly and labour-intensive. Unsupervised training strategies have been adopted by some visual or LiDAR SLAM methods. However, these methods only exploit the potential of single-sensor modalities, which do not take the complementary advantages of LiDAR and visual data. In this paper, we propose a novel unsupervised multi-channel visual-LiDAR SLAM method (MVL-SLAM) which can fuse visual and LiDAR data together. Our SLAM system consists of an unsupervised multi-channel visual-LiDAR odometry (MVLO) component, a deep learning–based loop closure detection component, and a 3D mapping component. The visual-LiDAR odometry component adopts a multi-channel recurrent convolutional neural network (RCNN). Its input consists of front, left, and right view depth images generated from 360^{circ } 3D LiDAR data and RGB images. We use the features from a deep convolutional neural network (CNN) for the loop closure detection component. Our SLAM method does not require ground truth data for training and can directly construct environmental 3D maps from the 3D mapping component. Experiments conducted on the KITTI odometry dataset have shown the rotation and translation errors are lower than some of the other unsupervised methods, including UnMono, SfmLearner, DeepSLAM, and UnDeepVO. Experimental results show that our methods have good performance. By fusing visual and LiDAR data, MVL-SLAM has higher accuracy and robustness of the pose estimation compared with other single-modal SLAM systems.

The Use of Machine Learning Algorithms in Urban Tree Species Classification

Trees are the key components of urban vegetation in cities. The timely and accurate identification of existing urban tree species with their location is the most important task for improving air, water, and land quality; reducing carbon accumulation; mitigating urban heat island effects; and protecting soil and water balance. Light detection and ranging (LiDAR) is frequently used for extracting high-resolution structural information regarding tree objects. LiDAR systems are a cost-effective alternative to the traditional ways of identifying tree species, such as field surveys and aerial photograph interpretation. The aim of this work was to assess the usage of machine learning algorithms for classifying the deciduous (broadleaf) and coniferous tree species from 3D raw LiDAR data on the Davutpasa Campus of Yildiz Technical University, Istanbul, Turkey. First, ground, building, and low, medium, and high vegetation classes were acquired from raw LiDAR data using a hierarchical-rule-based classification method. Next, individual tree crowns were segmented using a mean shift clustering algorithm from high vegetation points. A total of 25 spatial- and intensity-based features were utilized for support vector machine (SVM), random forest (RF), and multi-layer perceptron (MLP) classifiers to discriminate deciduous and coniferous tree species in the urban area. The machine learning-based classification’s overall accuracies were 80%, 83.75%, and 73.75% for the SVM, RF, and MLP classifiers, respectively, in split 70/30 (training/testing). The SVM and RF algorithms generally gave better classification results than the MLP algorithm for identifying the urban tree species.

Ploughing Furrow Detection Based on 3D LiDAR Sensor Data

Even if today's powerful machines make ploughing easier and faster than before, it is still a demanding task for the operator. To reduce the driver's workload, improve safety, and increase performance, it is reasonable to automate the process. In this paper, we present a novel method for ploughing furrow edge detection based on data from a Velodyne VLP-16 3D Light Detection and Ranging (LiDAR) sensor. From this detection it is possible to derive a guidance line for navigation. Our method is based on maximum gradient edge detection on each individual line of the 16-layer 3D LiDAR data, and RANSAC for fitting a line to the detected edge points. The method is also capable of determining on which side of the furrow is the ploughed and the unploughed land. The evaluation of the method was conducted on a data set that was recorded during in-furrow ploughing, on the part of the data where the furrow edge is always visible on all lines of the LiDAR scan. Based on an initial evaluation the method can detect the ploughing furrow in 3D LiDAR point cloud data.

Ship Berthing Information Extraction System Using Three-Dimensional Light Detection and Ranging Data

Safe and efficient berthing is essential to ensure maritime transportation and the safety of ships and ports. Three-dimensional (3D) light detection and ranging (LiDAR) can monitor and support ship berthing because it provides abundant target information and offers excellent advantages in measuring accuracy. Hence, a berthing information extraction system has been developed based on 3D LiDAR. Principal component analysis is used to calculate a ship’s heading and the normal vector, and the feature points of the bow and stern are determined. The segments passing through the points are obtained via region growing. The bow and stern are recognized by the similarity of the normal vector of the segments and ship’s heading according to the positions of the ship relative to the berth through visibility analysis. Qualitative and quantitative calculated analyses of the distance, velocity, and approach angle of the dynamic ship’s bow and stern relative to the dock are performed based on the feature points of 3D LiDAR data. A laser scanner, used as the detection unit, efficiently monitored the Ro–Ro ship Ocean Island berthing at Lushun Port in field experiments. On-site applications demonstrated the feasibility and effectiveness of the proposed method for the recognition of dynamic ship target and ensuring safe ship berthing.

Comprehensive Airborne Laser Scanning (ALS) Simulation

The 3D topographic data generated by airborne laser scanning (ALS) has numerous applications such as urban planning, transportation planning, flood modeling and mapping. Various types of LiDAR (light detection and ranging) datasets are needed for testing and development of algorithms for these applications. Such datasets are not readily available as the LiDAR data capturing process is complex, time-consuming and expensive. Simulated ALS data can be a low-cost alternative to the expensive LiDAR datasets. This paper presents the development of a simulator (called Limulator 4.0) for ALS data. Limulator includes four components, namely 3D model component, camera component, laser component and LiDAR data generation. The first component provides a user, the facility to input user-defined 3D models of various objects. The laser component mathematically models the scanner movement and flight trajectory to generate simulated ALS parameters. The camera component takes user-defined parameters to generate images captured by a virtual camera. The effects of external and internal forces on flight movement and various errors are also modeled mathematically. Software for this simulation is developed in C + + , and its user-friendly GUI is developed using QT Creator 5.6. Limulator can serve as the ideal testbed for developing, testing and validation of various algorithms.

Longitudinal-Scanline-Based Arterial Traffic Video Analytics with Coordinate Transformation Assisted by 3D Infrastructure Data

High-resolution vehicle trajectory data can be used to generate a wide range of performance measures and facilitate many smart mobility applications for traffic operations and management. In this paper, a Longitudinal Scanline LiDAR-Camera model is explored for trajectory extraction at urban arterial intersections. The proposed model can efficiently detect vehicle trajectories under the complex, noisy conditions (e.g., hanging cables, lane markings, crossing traffic) typical of an arterial intersection environment. Traces within video footage are then converted into trajectories in world coordinates by matching a video image with a 3D LiDAR (Light Detection and Ranging) model through key infrastructure points. Using 3D LiDAR data will significantly improve the camera calibration process for real-world trajectory extraction. The pan-tilt-zoom effects of the traffic camera can be handled automatically by a proposed motion estimation algorithm. The results demonstrate the potential of integrating longitudinal-scanline-based vehicle trajectory detection and the 3D LiDAR point cloud to provide lane-by-lane high-resolution trajectory data. The resulting system has the potential to become a low-cost but reliable measure for future smart mobility systems.

DeepLO: Multi-projection deep LIDAR odometry for space orbital robotics rendezvous relative navigation

This work proposes a new Light Detection and Ranging (LIDAR) based navigation architecture that is appropriate for uncooperative relative robotic space navigation applications. In contrast to current solutions that exploit 3D LIDAR data, our architecture suggests a Deep Recurrent Convolutional Neural Network (DRCNN) that exploits multi-projected imagery of the acquired 3D LIDAR data. Advantages of the proposed DRCNN are; an effective feature representation facilitated by the Convolutional Neural Network module within DRCNN, a robust modeling of the navigation dynamics due to the Recurrent Neural Network incorporated in the DRCNN, and a low processing time. Our trials evaluate several current state-of-the-art space navigation methods on various simulated but credible scenarios that involve a satellite model developed by Thales Alenia Space (France). Additionally, we evaluate real satellite LIDAR data acquired in our lab. Results demonstrate that the proposed architecture, although trained solely on simulated data, is highly adaptable and is more appealing compared to current algorithms on both simulated and real LIDAR data scenarios affording better odometry accuracy at lower computational requirements.

Land-cover classification of multispectral LiDAR data using CNN with optimized hyper-parameters

Multispectral LiDAR (Light Detection And Ranging) is characterized of the completeness and consistency of its spectrum and spatial geometric data, which provides a new data source for land-cover classification. In recent years, the convolutional neural network (CNN), compared with traditional machine learning methods, has made a series of breakthroughs in image classification, object detection, and image semantic segmentation due to its stronger feature learning and feature expression abilities. However, traditional CNN models suffer from some issues, such as a large number of layers, leading to higher computational cost. To address this problem, we propose a CNN-based multi-spectral LiDAR land-cover classification framework and analyze its optimal parameters to improve classification accuracy. This framework starts with the preprocessing of multi-spectral 3D LiDAR data into 2D images. Next, a CNN model is constructed with seven fundamental functional layers, and its hyper-parameters are comprehensively discussed and optimized. The constructed CNN model with the optimized hyper-parameters was tested on the Titan multi-spectral LiDAR data, which include three wavelengths of 532 nm, 1064 nm, and 1550 nm. Extensive experiments demonstrated that the constructed CNN with the optimized hyper-parameters is feasible for multi-spectral LiDAR land-cover classification tasks. Compared with the classical CNN models (i.e., AlexNet, VGG16 and ResNet50) and our previous studies, our constructed CNN model with the optimized hyper-parameters is superior in computational performance and classification accuracies.

LiDAR-Based System and Optical VHR Data for Building Detection and Mapping.

The aim of this paper is to highlight how the employment of Light Detection and Ranging (LiDAR) technique can enhance greatly the performance and reliability of many monitoring systems applied to the Earth Observation (EO) and Environmental Monitoring. A short presentation of LiDAR systems, underlying their peculiarities, is first given. References to some review papers are highlighted, as they can be regarded as useful guidelines for researchers interested in using LiDARs. Two case studies are then presented and discussed, based on the use of 2D and 3D LiDAR data. Some considerations are done on the performance achieved through the use of LiDAR data combined with data from other sources. The case studies show how the LiDAR-based systems, combined with optical Very High Resolution (VHR) data, succeed in improving the analysis and monitoring of specific areas of interest, specifically how LiDAR data help in exploring external environment and extracting building features from urban areas. Moreover the discussed Case Studies demonstrate that the use of the LiDAR data, even with a low density of points, allows the development of an automatic procedure for accurate building features extraction, through object-oriented classification techniques, therefore by underlying the importance that even simple LiDAR-based systems play in EO and Environmental Monitoring.

Object Recognition Based Interpolation With 3D LIDAR and Vision for Autonomous Driving of an Intelligent Vehicle

An algorithm has been developed for fusing 3D LIDAR (Light Detection and Ranging) systems that receive objects detected in deep learning-based image sensors and object data in the form of 3D point clouds. 3D LIDAR represents 3D point data in a planar rectangular coordinate system with a 360° representation of the detected object surface, including the front face. However, only the direction and distance data of the object can be obtained, and point cloud data cannot be used to create a specific definition of the object. Therefore, only the movement of the point cloud data can be tracked using probability and classification algorithms based on image processing. To overcome this limitation, the study matches 3D LIDAR data with 2D image data through the fusion of hybrid level multi-sensors. First, because 3D LIDAR data represents all objects in the sensor’s detection range as dots, all unnecessary data, including ground data, is filtered out. The 3D Random Sample Consensus (RANSAC) algorithm enables the extraction of ground data perpendicular to the reference estimation 3D plane and data at both ends through ground estimation. Classified environmental data facilitates the labeling of all objects within the viewing angle of 3D LIDAR based on the presence or absence of movement. The path of motion of the platform can be established by detecting whether objects within the region of interest are movable or static. Because LIDAR is based on 8- and 16-channel rotation mechanisms, real-time data cannot be used to define objects. Instead, point clouds can be used to detect obstacles in the image through deep learning in the preliminary processing phase of the classification algorithm. By matching the labeling information of defined objects with the classified object cloud data obtained using 3D LIDAR, the exact dynamic trajectory and position of the defined objects can be calculated. Consequently, to process the acquired object data efficiently, we devised an active-region-of-interest technique to ensure a fast processing speed while maintaining a high detection rate.

High-speed multi-dimensional relative navigation for uncooperative space objects

This work proposes a high-speed Light Detection and Ranging (LIDAR) based navigation architecture that is appropriate for uncooperative relative space navigation applications. In contrast to current solutions that exploit 3D LIDAR data, our architecture transforms the odometry problem from the 3D space into multiple 2.5D ones and completes the odometry problem by utilizing a recursive filtering scheme. Trials evaluate several current state-of-the-art 2D keypoint detection and local feature description methods as well as recursive filtering techniques on a number of simulated but credible scenarios that involve a satellite model developed by Thales Alenia Space (France). Most appealing performance is attained by the 2D keypoint detector Good Features to Track (GFFT) combined with the feature descriptor KAZE, that are further combined with either the H∞ or the Kalman recursive filter. Experimental results demonstrate that compared to current algorithms, the GFTT/KAZE combination is highly appealing affording one order of magnitude more accurate odometry and a very low processing burden, which depending on the competitor method, may exceed one order of magnitude faster computation.