Airborne Lidar System Research Articles

Research on visualization of cotton canopy structure and extraction of feature parameters based on dual-perspective point cloud data

ABSTRACT Cotton is one of the crops that requires the most time and labor. Precision agriculture technology is required for efficient management of cotton, and the identification of cotton attribute information in the field is a necessary and crucial step towards implementing precision agriculture. Unmanned aerial vehicles (UAVs) and Light Detection and Ranging (LiDAR) have evolved into essential instruments for plant phenotyping research. In this study, in order to address the demand for cotton attribute identification over wide areas in the field, an airborne LiDAR system was built based on LiDAR detection technology. This work acquired a dual-view point cloud of a cotton field in order to address the high density and low accuracy of the cotton point cloud attributes. Following pre-processing of the data, the point cloud was first coarsely regenerated using a combination of Fast Point Feature Histograms (FPFH) and Intrinsic Shape Signatures (ISS) techniques. The dual-view point cloud registration was then refined and finished using an Iterative Closest Point (ICP) algorithm. The height of the cotton plant was determined using the reconstructed point cloud of the cotton canopy, and a method combining Graham’s algorithm and the Alpha-Shape algorithm was suggested to determine the porosity of the cotton layers. The findings revealed that the root mean square errors (RMSE) between calculated and measured values of cotton plant height and stratified porosity were, respectively, 3.98 cm and 5.21%, and that their mean absolute percentage errors (MAPE) were 4.39% and 9.31%, with correlation coefficients ( R 2 ) of 0.951 and 0.762, respectively. On the whole, our study has demonstrated the effectiveness of the proposed method in terms of providing accurate and reliable cotton parameters in agriculture.

Improving the Accuracy of Digital Terrain Models Using Drone-Based LiDAR for the Morpho-Structural Analysis of Active Calderas: The Case of Ischia Island, Italy

Over the past two decades, the airborne Light Detection and Ranging (LiDAR) system has become a useful tool for acquiring high-resolution topographic data, especially in active tectonics studies. Analyzing Digital Terrain Models (DTMs) from LiDAR exposes morpho-structural elements, aiding in the understanding of fault zones, among other applications. Despite its effectiveness, challenges persist in regions with rapid deformation, dense vegetation, and human impact. We propose an adapted workflow transitioning from the conventional airborne LiDAR system to the usage of drone-based LiDAR technology for higher-resolution data acquisition. Additionally, drones offer a more cost-effective solution, both in an initial investment and ongoing operational expenses. Our goal is to demonstrate how drone-based LiDAR enhances the identification of active deformation features, particularly for earthquake-induced surface faulting. To evaluate the potential of our technique, we conducted a drone-based LiDAR survey in the Casamicciola Terme area, north of Ischia Island, Italy, known for the occurrence of destructive shallow earthquakes, including the 2017 Md = 4 event. We assessed the quality of our acquired DTM by comparing it with existing elevation datasets for the same area. We discuss the advantages and limitations of each DTM product in relation to our results, particularly when applied to fault mapping. By analyzing derivative DTM products, we identified the fault scarps within the Casamicciola Holocene Graben (CHG) and mapped its structural geometry in detail. The analysis of both linear and areal geomorphic features allowed us to identify the primary factors influencing the current morphological arrangement of the CHG area. Our detailed map depicts a nested graben formed by two main structures (the Maio and Sentinella faults) and minor internal faults (the Purgatorio and Nizzola faults). High-resolution DEMs acquired by drone-based LiDAR facilitated detailed studies of the geomorphology and fault activity. A similar approach can be applied in regions where the evidence of high slip-rate faults is difficult to identify due to vegetation cover and inaccessibility.

Ratio of photosynthetically active radiation to global solar radiation above forest canopy in complex terrain: measurements and analyses based on Qingyuan Ker Towers

BackgroundUnderstanding of the ratio of photosynthetic photon flux density (Qp) to global solar radiation (Rs) (Qp/Rs) is crucial for applying Rs to ecology-related studies. Previous studies reported Qp/Rs and its variations based on measurements from a single observatory tower, instead of multi-site-based measurements over complex terrains. This may neglect spatial heterogeneity in the terrain, creating a gap in an understanding of how terrain affects Qp/Rs and how this effect interacts with meteorological factors.MethodsHere the Qingyuan Ker Towers (three towers in a valley with different terrains: T1, T2, and T3) were utilized to measure Qp and Rs over mountainous forests of Northeast China. An airborne LiDAR system was used to generate a digital elevation model, and sky view factor of sectors (SVFs) divided from the field of view of tower’s pyranometer was calculated as a topographic factor to explain the variations of Qp/Rs.ResultsThe results identified significant differences in Qp/Rs of the three towers at both daily and half-hour scales, with larger differences on clear days than on overcast days. Qp/Rs was positively correlated with SVFs of T1 and T3, while this correlation was negative with that of T2. The effect of SVFs on Qp/Rs interacted with clearness index, water vapor pressure and solar zenith angle. Random forest-based importance assessment demonstrated that explanation (R2) on Qp/Rs was improved when SVFs was included in the predictor variable set, indicating that incorporating terrain effects enhances the prediction accuracy of Qp/Rs. The improvement in the R2 values was more pronounced on clear days than on overcast days, suggesting that the effect of terrain on Qp/Rs depended on sky conditions.ConclusionsAll findings suggested that Qp/Rs is affected by terrain, and integrating terrain information into existing Qp/Rs models is a feasible solution to improve Qp/Rs estimates in mountainous areas.

Drone Lidar Deep Learning for Fine-Scale Bare Earth Surface and 3D Marsh Mapping in Intertidal Estuaries

Tidal marshes are dynamic environments providing important ecological and economic services in coastal regions. With accelerating climate change and sea level rise (SLR), marsh mortality and wetland conversion have been observed on global coasts. For sustainable coastal management, accurate projection of SLR-induced tidal inundation and flooding requires fine-scale 3D terrain of the intertidal zones. The airborne Lidar systems, although successful in extracting terrestrial topography, suffer from high vertical uncertainties in coastal wetlands due to tidal effects. This study tests the feasibility of drone Lidar leveraging deep learning of point clouds on 3D marsh mapping. In an ocean-front, pristine estuary dominated by Spartina alterniflora, drone Lidar point clouds, and in-field marsh samples were collected. The RandLA-Net deep learning model was applied to classify the Lidar point cloud to ground, low vegetation, and high vegetation with an overall accuracy of around 0.84. With the extracted digital terrain model and digital surface model, the cm-level bare earth surfaces and marsh heights were mapped. The bare earth terrain reached a vertical accuracy (root-mean-square error, or RMSE) of 5.55 cm. At the 65 marsh samples, the drone Lidar-extracted marsh height was lower than the in-field height measurements. However, their strongly significantly linear relationship (Pearson’s r = 0.93) reflects the validity of the drone Lidar for measuring marsh canopy height. The adjusted Lidar-extracted marsh height had an RMSE of 0.12 m. This experiment demonstrates a multi-step operational procedure to deploy drone Lidar for accurate, fine-scale terrain and 3D marsh mapping, which provides essential base layers for projecting wetland inundation in various climate change and SLR scenarios.

Studying Tropical Dry Forests Secondary Succession (2005–2021) Using Two Different LiDAR Systems

Chronosequence changes among Tropical Dry Forests (TDFs) are essential for understanding this unique ecosystem, which is characterized by its seasonality (wet and dry) and a high diversity of deciduous trees and shrubs. From 2005 to 2021, we used two different airborne LiDAR systems to quantify structural changes in the forest at Santa Rosa National Park. Line- and shape-based waveform metrics were used to record the overall changes in the TDF structure. Based on a 16-year growth analysis, notable variations in height-related profiles were observed, particularly for RH50, RH100, and waveform-produced canopy heights. The results showed that Cy and RG have increased since the forests have been growing, whereas Cx has decreased. The decrease in Cx is because ground returns are lower when the canopy density i and canopy height increase. A positive relationship was observed between Cy and CH, RG, and RH100, particularly for the wet season data collected in 2021. These findings provide important insights into the growth dynamics of TDFs in Santa Rosa National Park and could inform future conservation efforts.

Measuring Surface Deformation of Asphalt Pavement via Airborne LiDAR: A Pilot Study

Measuring the surface deformation of asphalt pavement and acquiring the rutting condition is of great importance to transportation agencies. This paper proposes a rutting measuring method based on an unmanned aerial vehicle (UAV) mounted with Light Detection and Ranging (LiDAR). Firstly, an airborne LiDAR system is assembled and the data acquisition method is presented. Then, the method for point cloud processing and rut depth computation is presented and the results of field testing are discussed. Thirdly, to investigate error factors, the laser footprint positioning model is established and sensitivity analysis is conducted. Factors including flight height, LiDAR instantaneous angel, and ground inclination angle are discussed. The model was then implemented to obtain the virtual rut depth and to verify the accuracy of the field test results. The main conclusions include that the measurement error increases with the flight height, instantaneous angle, and angular resolution of the LiDAR. The inclination angle of the pavement surface has adverse impact on the measuring accuracy. The field test results show that the assembled airborne LiDAR system is more accurate when the rut depth is significant. The findings of this study pave the way for future exploration of rutting measurement with airborne LiDAR.

The Effectiveness of a UAV-Based LiDAR Survey to Develop Digital Terrain Models and Topographic Texture Analyses.

This study presents a comparison of data acquired from three LiDAR sensors from different manufacturers, i.e., Yellow Scan Mapper (YSM), AlphaAir 450 Airborne LiDAR System CHC Navigation (CHC) and DJI Zenmuse L1 (L1). The same area was surveyed with laser sensors mounted on the DIJ Matrice 300 RTK UAV platform. In order to compare the data, a diverse test area located in the north-western part of the Lublin Province in eastern Poland was selected. The test area was a gully system with high vegetation cover. In order to compare the UAV information, LiDAR reference data were used, which were collected within the ISOK project (acquired for the whole area of Poland). In order to examine the differentiation of the acquired data, both classified point clouds and DTM products calculated on the basis of point clouds acquired from individual sensors were compared. The analyses showed that the largest average height differences between terrain models calculated from point clouds were recorded between the CHC sensor and the base data, exceeding 2.5 m. The smallest differences were recorded between the L1 sensor and ISOK data-RMSE was 0.31 m. The use of UAVs to acquire very high resolution data can only be used locally and must be subject to very stringent landing site preparation procedures, as well as data processing in DTM and its derivatives.

Design and demonstration of airborne hyperspectral imaging LiDAR system based on optical fiber array focal plane splitting

The acquisition and application of high-resolution ground object elevation information and spectral information is a frontier scientific problem in the development of earth observation technology. In this paper, we designed and demonstrated an airborne full-waveform hyperspectral imaging lidar system. The hyperspectral lidar adopts the mode of optical fiber array focal plane splitting, which can effectively detect the echo signal in a wide spectrum. The hyperspectral lidar uses a supercontinuum laser as the illumination source. A single pulse emitted from the laser can achieve a simultaneous acquisition of spectral information and elevation information. Through the spectral calibration of the hyperspectral lidar, we have given the center wavelength and bandwidth of 56 channels. Results show that the spectral range of the hyperspectral lidar covers 400–900 nm, and the spectral resolution of each detection channel is close to 9 nm. Because one detection channel is coupled with three optical fibers, the resolution of a single optical fiber of the hyperspectral lidar is close to 3 nm. The successful development of the airborne hyperspectral lidar can accumulate a large number of data sets for research in the field of remote sensing.

Canopy structure from space using GEDI lidar

Canopy structure from space using <scp>GEDI</scp> lidar

Analysis of UAS-LiDAR Ground Points Classification in Agricultural Fields Using Traditional Algorithms and PointCNN

Classifying bare earth (ground) points from Light Detection and Ranging (LiDAR) point clouds is well-established research in the forestry, topography, and urban domains using point clouds acquired by Airborne LiDAR System (ALS) at average point densities (≈2 points per meter-square (pts/m2)). The paradigm of point cloud collection has shifted with the advent of unmanned aerial systems (UAS) onboard affordable laser scanners with commercial utility (e.g., DJI Zenmuse L1 sensor) and unprecedented repeatability of UAS-LiDAR surveys. Therefore, there is an immediate need to investigate the existing methods, and to develop new ground classification methods, using UAS-LiDAR. In this paper, for the first time, traditional ground classification algorithms and modern machine learning methods were investigated to filter ground from point clouds of high-density UAS-LiDAR data (≈900 pts/m2) over five agricultural fields in North Dakota, USA. To this end, we tested frequently used ground classification algorithms: Cloth Simulation Function (CSF), Progressive Morphological Filter (PMF), Multiscale Curvature Classification (MCC), and ArcGIS ground classification algorithms along with the PointCNN deep learning model were trained. We investigated two aspects of ground classification algorithms and PointCNN: (a) Classification accuracy of optimized ground classification algorithms (i.e., fine adjustment is user-defined parameters) and PointCNN over training site, and (b) transferability potential over four yet diverse test agricultural fields. The well-established evaluation metrics of omission error, commission error, and total error, along with kappa coefficients showed that deep learning outperforms the traditional ground classification algorithms in both aspects: (a) overall classification accuracy, and (b) transferability over diverse agricultural fields.

Estimations of Forest Stand Parameters in Open Forest Stand Using Point Cloud Data from Terrestrial Laser Scanning, Unmanned Aerial Vehicle and Aerial LiDAR Data

Two of the very basic forestry parameters, the Breast Height Diameter (DBH) and Tree Height (TH) are very effective when characterizing forest stands and individual trees. The traditional measurement process of these parameters takes a lot of time and consumes human power. On the other hand, 3D Point Cloud (PC) quickly provides a very detailed view of forestry parameters, because of the development of computer processing power and digital storage in recent years. PC data sources for forestry applications include Airborne LiDAR Systems (ALS), Terrestrial Laser Scanning (TLS) and most recently the Unmanned Air Vehicle (UAV). In this study, the PC datasets from these sources were used to study the feasibility of the DBH and TH values of a d development stage (i.e. DBH &amp;gt; 52 cm in mature stage) oak stand. The DBH and TH estimates are compared with the onsite measurements, which are considered to be fundamental truths, to their performance due to overall error statistics, as well as the cost of calculation and the difficulties in data collection. The results show that the computer data obtained by TLS has the best average square error (0.22 cm for DBH and 0,051 m for TH) compared to other computer data. The size of Pearson correlation between TLS-based and on-site-based measurements has reached 0.97 and 0.99 for DBH, respectively.

Technique for comparison of backscatter coefficients derived from in situ cloud probe measurements with concurrent airborne lidar

Abstract. Jet engine power loss due to ice particle accumulation is a recognized aviation hazard occurring in cloud conditions difficult to forecast or visually recognize. High-altitude cirrus clouds can have ice particle concentrations high enough to be dangerous; therefore, pilots must be informed when aircraft enter such environments. One approach to determining ice particle concentration is an onboard lidar system. Concurrent lidar measurements are compared to backscatter coefficients derived from particle size distributions obtained from wing-mounted, in situ probes during four case studies consisting of sixty-second flight segments at different temperatures: +7 and +4 ∘C for water droplet analysis, and −33 and −46 ∘C for ice particle analysis. Backscatter coefficients derived from external cloud probes (ECP) are correlated (0.91) with measurements by an airborne lidar system known as the Optical Ice Detector (OID). Differences between OID and ECP backscatter coefficients range from less than 1 to over 3 standard deviations in terms of uncertainties. The backscatter coefficients are mostly in agreement for liquid clouds and are in disagreement for the −33 and −46 ∘C cases, with ECP-derived backscatter coefficients lower than the OID for three out of the four cases. Measurements over four 60 s research flight segments show that measured total water content is correlated (0.74) with the OID backscatter coefficient, which indicates that the OID is a useful instrument for determining ice particle concentrations over a broad range of environments, including at ice water contents as low as 0.02 g m−3. Additionally, concurrent measurements from cloud imaging probes and the OID provide improved knowledge of cloud conditions, which may help in understanding cloud processes.

Automated extraction of building instances from dual-channel airborne LiDAR point clouds

With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. • Dual-channel ALS data is used to build instances extraction for the first time. • The proposed method is preprocessing-free and fully automated. • The input scene is reorganized based on point distribution and top-down merging. • Both semantic-based and instance-based building segmentation were conducted.

Evaluation of NASA’s GEDI Lidar Observations for Estimating Biomass in Temperate and Tropical Forests

Accurate estimation of forest aboveground biomass (AGB) is vital for informing ecosystem and carbon management. The Global Ecosystem Dynamics Investigation (GEDI) instrument—a new-generation spaceborne lidar system from NASA—provides the first global coverage of high-resolution 3D altimetry data aimed specifically for mapping Earth’s forests, but its performance is yet to be tested for large parts of the world. Here, our goal is to evaluate the accuracies of GEDI in measuring terrain, forest vertical structures, and AGB in reference to independent airborne lidar data over temperate and tropical forests in North America. We compared GEDI-derived elevations and canopy heights (e.g., relative height percentiles such as RH50 and RH100) with those from the Shuttle Radar Topography Mission (SRTM) or from two airborne lidar systems: the Laser Vegetation Imaging Sensor (LVIS) and Goddard’s Lidar, Hyperspectral and Thermal system (G-LiHT). We also estimated GEDI’s geolocation errors by matching GEDI waveforms and G-LiHT pseudo-waveforms. We assessed the predictive power of GEDI metrics in estimating AGB using Random Forests regression. Results showed that GEDI-derived ground elevations correlated strongly those from LVIS, G-LiHT, and LVIS (R2 &gt; 0.91), but with nonnegligible RMSEs of 5.7 m (G-LiHT), 3.1 m (LVIS), and 10.9 m (SRTM). GEDI canopy heights had poorer correlation with LVIS (e.g., R2 = 0.44 for RH100) than with G-LiHT (e.g., R2 = 0.60 for RH100). The estimated horizontal geolocation errors of GEDI footprints averaged 6.5 meters, comparable to the nominal accuracy of 9 m. Correction for the locational errors improved the correlation of GEDI vs G-LiHT canopy heights significantly, on average by 53% (e.g., R2 from 0.57 to 0.82 for RH50). GEDI canopy metrics were useful for predicting AGB (R2 = 0.82 and RMSE = 19.1 Mg/Ha), with the maximum canopy height RH100 being the most useful predictor. Our results highlight the importance of accommodating or correcting for GEDI geolocation errors for estimating forest characteristics and provide empirical evidence on the utility of GEDI for monitoring global biomass dynamics from space.

Unmanned airborne miniaturized pulsed CO2 laser with wavelength automatic tuning

This paper presents a miniaturized mechanically Q-switched pulsed CO2 laser with wavelength automatic tuning, which could be used in unmanned airborne lidar system. A three-mirror cavity structure with real focus in the cavity is designed to provide a stable resonator, which has short beam transit time for mechanically Q-switched laser. The matching relationship between the beam in the resonant cavity and the aperture of the optical chopper is experimentally studied, the CO2 laser pulse output with good waveform is obtained, and the wavelength automatic tuning is realized. The CO2 laser produces a maximum output peak power of 3.7 kW at 10.59 μm for pulse width of 350 ns, corresponding beam quality M2 of 1.75, and the laser weight is about 18 kg.

Comparing tree structures derived among airborne, terrestrial and mobile LiDAR systems in urban parks

ABSTRACT Measuring tree structure using three-dimensional (3D) mapping tools such as light detection and ranging (LiDAR) remote sensing is needed to provide well-managed and designed green spaces. The metrics used to estimate tree structure could be different depending on which LiDAR systems are used. This may lead to confusion and reduce confidence when evaluating tree structures and their derived products, such as plant area index (PAI). Therefore, studies that can determine similarities among measurements derived from different LiDAR systems are needed. In this study, structural canopy metrics in airborne laser scanning (ALS), terrestrial laser scanning (TLS), and mobile laser scanning (MLS) were compared to seek consistencies among the three LiDAR systems. The specific objectives were to test whether the estimates made by the metrics differed depending on single or clustered trees and to test whether LiDAR-derived errors in the metrics are related to tree structures. Tree point clouds were manually classified into single and clustered trees. Heights-related metrics, Rumple Index, area, and PAI were calculated for comparison analysis. Root-mean-square error (RMSE), bias, and Pearson’s correlation coefficient (r) were calculated to evaluate the consistencies in each metric among the LiDAR systems. The results showed that the maximum height of the point clouds (ZMAX) and max and mean heights derived from the canopy height models (minCHM and maxCHM) demonstrated good consistency (RMSE% < 10%, Bias% < 10%, and r > 0.900). Moreover, the biases from the ZMAX- and CHM-derived metrics comparisons among the LiDAR systems did not show strong linear relationships with the tree heights and canopy complexities (i.e. Pearson’s correlation coefficient r < |0.29|). On the contrary, the 95th percentile (Zq95) height and mean z height (ZMEAN) differed depending on the tree classes and showed significant linear relations with canopy heights and complexity. The configurations of LiDAR systems, such as point density and sensing locations, seem to affect the Zq95, ZMEAN metrics, and PAI. Our results suggest that assessing for consistencies among the different LiDAR systems is required before using multiple LiDAR systems interchangeably to estimate the structure of urban park areas.

Application of Airborne LiDAR Measurements to the Topographic Survey of the Tidal Flats of the Northern Jiangsu Radial Sand Ridges in the Southern Yellow Sea

The northern Jiangsu radial sand ridges are typical geomorphic deposit units distributed off the Jiangsu coast. A coastal tidal flat typically develops and provides a good habitat for many migratory birds and benthic organisms. However, topographic surveys of tidal flats have always been difficult in marine surveys because of the dense tidal creek, poor accessibility, and difficulty in setting up control points. In this study, we quickly obtained the point cloud data of the tidal flat near Yangkou Port in the southern part of the radial sand ridges based on an airborne LiDAR system, an integrated 3D laser scanner and a positioning and attitude determination system. We analyzed the adaptabilities of multiple filtering algorithms to tidal flats. In addition, a digital elevation model (DEM) of the tidal flat was constructed and the accuracy was verified with synchronized beach GPS-RTK topographic elevation measurements. The results show that the following: (1) Airborne LiDAR can quickly obtain high precision, high resolution, and a large area of ground point cloud information for tidal flats, overcoming the shortcomings of traditional measurement methods. (2) The triangulated irregular network (TIN) filtering effect is better than that of mathematical morphology and the filtering effect of point cloud normal vector clustering is mediocre. (3) The DEM of the LiDAR point cloud is in good agreement with RTK and the average error of the measurement results is 0.108 m. The error accuracy of the DEM satisfies the surveying specification of a 1:500 topographic map in a flat area, which proves that the airborne LiDAR system can be suitable for tidal flat elevation measurement. Nevertheless, it is possible to provide high precision terrain detection and DEM construction of a tidal flat with the development of airborne infrared and blue-green laser detection radar.

Automatic Calibration Method for Airborne LiDAR Systems Based on Approximate Corresponding Points Model

The calibration of the light detection and ranging (LiDAR) system is critical to ensure the accuracy of point data. In this paper, the lever-arm measurement of airborne LiDAR system (ALS) was realized by photogrammetry. An automatic iterative boresight calibration method based on approximate corresponding points (CPs) matching was proposed to correct the boresight misalignment. It was based on iterative closest point (ICP) registration algorithm with a normal space sampling strategy, and approximate CPs were obtained by establishing filter rules. The experimental results showed that the absolute accuracy of the calibrated ALS reached 7.13 cm when the flight altitude was 100 m, meeting the accuracy requirements.

Hyperspectral and Lidar Data Applied to the Urban Land Cover Machine Learning and Neural-Network-Based Classification: A Review

Rapid technological advances in airborne hyperspectral and lidar systems paved the way for using machine learning algorithms to map urban environments. Both hyperspectral and lidar systems can discriminate among many significant urban structures and materials properties, which are not recognizable by applying conventional RGB cameras. In most recent years, the fusion of hyperspectral and lidar sensors has overcome challenges related to the limits of active and passive remote sensing systems, providing promising results in urban land cover classification. This paper presents principles and key features for airborne hyperspectral imaging, lidar, and the fusion of those, as well as applications of these for urban land cover classification. In addition, machine learning and deep learning classification algorithms suitable for classifying individual urban classes such as buildings, vegetation, and roads have been reviewed, focusing on extracted features critical for classification of urban surfaces, transferability, dimensionality, and computational expense.

Single photon lidar signal attenuation under boreal forest conditions

ABSTRACT Single-photon lidar (SPL100) is a recently commercialized airborne lidar system facilitating efficient wide-area acquisitions of high-density point clouds due to its capacity for higher altitude acquisitions compared to traditional linear-mode lidar (LML) systems. Increased acquisition efficiency and point densities make SPL100 attractive for forest management applications. SPL100 utilizes 532 nm (green wavelength) lasers, wherein there is reduced reflectance from vegetation, increased sensitivity to solar noise, and increased signal attenuation, which may impact the vertical distribution of SPL100 returns in forest canopies. We assessed SPL100 data acquisitions over managed forests in north-eastern Ontario, Canada, using high-density unmanned aerial vehicle-borne laser scanning (ULS) data as reference over a range of forest conditions with variable vertical structure. Signal attenuation depth of individual SPL100 returns was estimated through a surface model normalization approach stratified by a ULS-derived structural index that compared densities of returns in the upper canopy to low vegetation and near ground. Canopy signal attenuation was closely matched in both systems, particularly in the upper canopy and near the ground surface; however, results showed a 31% reduction in the relative characterization of mid-canopy vegetation layers by SPL100 under conditions identified by the structural index as closed canopy, compared to the ULS system.