Unmanned Aerial Vehicle LiDAR Research Articles

Large-scale inventory in natural forests with mobile LiDAR point clouds

Large-scale forest inventory at the individual tree level is critical for natural resource management decision making. Terrestrial Laser Scanning (TLS) has been used for individual tree level inventory at plot scale However, due to the inflexibility of TLS and the complex scene of natural forests, it is still challenging to localize and measure every tree at large scale. In this paper, we present a framework to conduct large-scale natural forest inventory at the individual tree level by taking advantage of deep learning models and Mobile Laser Scanning (MLS) systems. First, a deep learning model, ForestSPG, was developed to perform large-scale semantic segmentation on MLS LiDAR data in natural forests. Then, the forest segmentation results were used for individual stem mapping. Finally, Diameter at Breast Height (DBH) was measured for each individual stem. Two natural forests mapped with backpack and Unmanned Aerial Vehicle (UAV) LiDAR systems were tested. The results showed that the proposed ForestSPG is able to segment large-scale forest LiDAR data into multiple ecologically meaningful classes. The proposed framework was able to localize and measure all 5838 stems at individual tree level in a 20 ha natural forest in less than 20 min using UAV LiDAR. DBH measurement results on trees’ DBH larger than 38.1 cm (15 in) showed that backpack LiDAR was able to achieve 1.82 cm of Root Mean Square Error (RMSE) and UAV LiDAR was able to achieve 3.13 cm of RMSE. The proposed framework can not only segment complex forest components with LiDAR data from different platforms but also demonstrate good performance on stem mapping and DBH measurement. Our research provides and automatic and scalable solution for large-scale natural forest inventory at individual tree level, which can be the basis for large-scale estimation of wood volume and biomass.

Modeling and spatialization of biomass and carbon stock using unmanned Aerial Vehicle Lidar (Lidar-UAV) metrics and forest inventory in cork oak forest of Maamora

Recently, the concerns about climate change have heightened the need for effective methods for estimating and mapping Biomass and Carbon stock at local, national, continental, and global scales. Reliable Biomass and Carbon stock quantification and spatialization is a challenge, especially in degraded Mediterranean Cork oak forest. To estimate and map Biomass (Btree−Total) and Carbon stock (Cst−total), we explored an improved approach using extracted metrics collected by Lidar-UAV (unmanned aerial vehicles Lidar), combined with forest inventory data. We approach three types of models for data analysis: Simple linear regression, multiple linear regressions, and stepwise multiple linear regression. The best Biomass and Carbon stock model fit is the Stepwise multiple linear regressions, involving the following metrics: maximum elevation, canopy cover and point cloud density and intensity. Our finding provides a quantification and spatialization Biomass and Carbon stock model based on Lidar-UAV metrics in Cork Oak Mediterranen forest and the results confirm the degraded state of Maamora Forest with a Biomass and Carbon stock relatively medium to low.

A Semi-Automatic Approach for Tree Crown Competition Indices Assessment From UAV LiDAR

Understanding the spatial heterogeneity of forest structure is crucial for comprehending ecosystem dynamics and promoting sustainable forest management. Unmanned aerial vehicle (UAV) LiDAR technology provides a promising method to capture detailed three-dimensional (3D) information about forest canopies, aiding in management and silvicultural practices. This study investigates the heterogeneity of forest structure in broadleaf forests using UAV LiDAR data, with a particular focus on tree crown features and their different information content compared to diameters. We explored a non-conventionally used method that emphasizes crown competition by employing a nearest neighbor selection technique based on metrics derived from UAV point cloud profiles at the tree level, rather than traditional DBH (diameter at breast height) spatial arrangement. About 300 vegetation elements within 10 plots collected in a managed Beech forest were used as reference data. We demonstrate that crown-based approaches, which are feasible with UAV LiDAR data at a reasonable cost and time, significantly enhances the understanding of forest heterogeneity, adding new information content for managers. Our findings underscore the utility of UAV LiDAR in characterizing the complexity and variability of forest structure at high resolution, offering valuable insights for carbon accounting and sustainable forest management.

Photogrammetry from UAV and Low-Cost Lidar for Sinkhole Hazard Mitigation in Urban Areas: Applications and Evaluations

The Italian national territory is characterised by the widespread presence of cavities dating back to different periods, especially in urban areas. The lack of knowledge of the position of the entrances, planimetric developments and state of preservation contributes to accentuating the unknowns related to sinkhole risk, which are directly related to potential cavity collapses with the opening of surface chasms. To deepen knowledge with a view to risk mitigation, a method has been developed to employ surveys obtained from Unmanned Aerial Vehicles (UAVs) to locate entrances even in hard-to-access urban areas. These surveys, properly supported with GNSS stations, were then integrated with cavity surveys obtained from low-cost lidar mounted on iPhones. Comparisons were made with traditional surveying techniques to better understand the reliability of the surveys made with low-cost lidar. The 3D models obtained, combined with geomechanical surveys of the rock masses hosting the cavities, allowed the application of simplified and empirical methods for an initial stability assessment. This method was tested on a portion of the municipality of Grotte di Castro (Province of Viterbo—Italy).

Identification of Damaged Canopies in Farmland Artificial Shelterbelts Based on Fusion of Unmanned Aerial Vehicle LiDAR and Multispectral Features

With the decline in the protective function for agricultural ecosystems of farmland shelterbelts due to tree withering and dying caused by pest and disease, quickly and accurately identifying the distribution of canopy damage is of great significance for forestry management departments to implement dynamic monitoring. This study focused on Populus bolleana and utilized an unmanned aerial vehicle (UAV) multispectral camera to acquire red–green–blue (RGB) images and multispectral images (MSIs), which were fused with a digital surface model (DSM) generated by UAV LiDAR for feature fusion to obtain DSM + RGB and DSM + MSI images, and random forest (RF), support vector machine (SVM), maximum likelihood classification (MLC), and a deep learning U-Net model were employed to build classification models for forest stand canopy recognition for the four image types. The model results indicate that the recognition performance of RF is superior to that of U-Net, and U-Net performs better overall than SVM and MLC. The classification accuracy of different feature fusion images shows a trend of DSM + MSI images (Kappa = 0.8656, OA = 91.55%) > MSI images > DSM + RGB images > RGB images. DSM + MSI images exhibit the highest producer’s accuracy for identifying healthy and withered canopies, with values of 95.91% and 91.15%, respectively, while RGB images show the lowest accuracy, with producer’s accuracy values of 79.3% and 78.91% for healthy and withered canopies, respectively. This study presents a method for identifying the distribution of Populus bolleana canopies damaged by Anoplophora glabripennis and healthy canopies using the feature fusion of multi-source remote sensing data, providing a valuable data reference for the precise monitoring and management of farmland shelterbelts.

An Integrating Framework for Biomass and Carbon Stock Spatialization and Dynamics Assessment Using Unmanned Aerial Vehicle LiDAR (LiDAR UAV) Data, Landsat Imagery, and Forest Survey Data in the Mediterranean Cork Oak Forest of Maamora

Spatialization of biomass and carbon stocks is essential for a good understanding of the forest stand and its characteristics, especially in degraded Mediterranean cork oak forests. Furthermore, the analysis of biomass and carbon stock changes and dynamics is essential for understanding the carbon cycle, in particular carbon emissions and stocks, in order to make projections, especially in the context of climate change. In this research, we use a multidimensional framework integrating forest survey data, LiDAR UAV data, and extracted vegetation indices from Landsat imagery (NDVI, ARVI, CIG, etc.) to model and spatialize cork oak biomass and carbon stocks on a large scale. For this purpose, we explore the use of univariate and multivariate regression modeling and examine several types of regression, namely, multiple linear regression, stepwise linear regression, random forest regression, simple linear regression, logarithmic regression, and quadratic and cubic regression. The results show that for multivariate regression, stepwise regression gives good results, with R2 equal to 80% and 65% and RMSE equal to 2.59 and 1.52 Mg/ha for biomass and carbon stock, respectively. Random forest regression, chosen as the ML algorithm, gives acceptable results, explaining 80% and 60% of the variation in biomass and carbon stock, respectively, and an RMSE of 2.74 and 1.72 Mg/ha for biomass and carbon stock, respectively. For the univariate regression, the simple linear regression is chosen because it gives satisfactory results, close to those of the quadratic and cubic regressions, but with a simpler equation. The vegetation index chosen is ARVI, which shows good performance indices, close to those of the NDVI and CIG. The assessment of biomass and carbon stock changes in the study area over 35 years (1985–2020) showed a slight increase of less than 10 Mg/ha and a decrease in biomass and carbon stock over a large area.

Effects of Illumination Conditions on Individual Tree Height Extraction Using UAV LiDAR: Pilot Study of a Planted Coniferous Stand

Tree height is one of the key dendrometric parameters for indirectly estimating the timber volume or aboveground biomass of a forest. Field measurement is time-consuming and labor-intensive, while unmanned aerial vehicle (UAV)-borne LiDAR is a more efficient tool for acquiring tree heights of large-area forests. Although individual tree heights extracted from point cloud data are of high accuracy, they are still affected by some weather and environment factors. In this study, taking a planted M. glyptostroboides (Metasequoia glyptostroboides Hu & W.C. Cheng) stand as the study object, we preliminarily assessed the effects of various illumination conditions (solar altitude angle and cloud cover) on tree height extraction using UAV LiDAR. The eight point clouds of the target stand were scanned at four time points (sunrise, noon, sunset, and night) in two consecutive days (sunny and overcast), respectively. The point clouds were first classified into ground points and aboveground vegetation points, which accordingly produced digital elevation model (DEM) and digital surface model (DSM). Then, the canopy height model (CHM) was obtained by subtracting DEM from DSM. Subsequently, individual trees were segmented based on the seed points identified by local maxima filtering. Finally, the individual tree heights of sample trees were separately extracted and assessed against the in situ measured values. As results, the R2 and RMSEs of tree heights obtained in the overcast daytime were commonly better than those in the sunny daytime; the R2 and RMSEs at night were superior among all time points, while those at noon were poorest. These indicated that the accuracy of individual tree height extraction had an inverse correlation with the intensity of illumination. To obtain more accurate tree heights for forestry applications, it is best to acquire point cloud data using UAV LiDAR at night, or at least not at noon when the illumination is generally strongest.

Ground subsidence monitoring in based on UAV-LiDAR technology: a case study of a mine in the Ordos, China

Ground subsidence in Western coal mining areas is characterized by rapid deformation, extensive damage, and a wide range of impacts. The conventional observation methods are inappropriate for surface damage monitoring in high-intensity mining areas of Western China. Therefore, it is a crucial problem to quickly, accurately, and comprehensively monitor the ground subsidence and environmental damage caused by high-intensity and large-scale mining. In this study, we propose a monitoring method for the ground subsidence of high-intensity mining with Unmanned Aerial Vehicle Lidar (UAV-LiDAR) measurement technology. Taking a mine in Ordos of China as an example, the Digital Elevation Model (DEM) is obtained by Kriging Interpolation of the ground point cloud from UAV-LiDAR. Then, the multi-stage DEM differential processing is employed to get ground subsidence. Finally, the median and bilateral filters combine for denoise to obtain the high-precision ground subsidence. The results show that the accuracy of the ground DEM generated by UAV-LiDAR is 15 mm and the mean square error of the ground subsidence basin is 39 mm. UAV-LiDAR technology can quickly obtain abundant surface data and obtain high-precision ground subsidence. Therefore, the application of this technology and method in subsidence monitoring in mining areas is feasible. And it can provide support for ecological environment monitoring, land reclamation, and ecological restoration in mining areas. The research results can provide a useful basis for monitoring the surface damage of coal mining in Western China.

Rotating 3D laser mapping system for multi-rotor drones

Accurate positional estimation is an essential prerequisite for the regular operation of an autonomous rotary-wing Unmanned Aerial Vehicles (UAV). However, the field of view (FOV) limitation problem of lidar makes it more challenging to locate the rotary-wing UAV in an unknown environment. To address rotor drones with an insufficient FOV and the observation blindness of lidar in complex environments, this paper designs a rotorcraft UAV system based on rotating 3D lidar and proposes a simultaneous localization and mapping algorithm for rotating 3D lidar. The algorithm distinguishes between planar and edge features based on the curvature value of the point cloud first. Then, to reduce the impact caused by the UAV motion and lidar rotation, messages about the Inertial Measurement Unit (IMU) and real-time rotation angles are used to compensate for these motions twice, while the IMU measurements are used for state prediction, and the error-sate iterative extended Kalman filter is used to update the residuals after matching line and surface features with sub-map. Finally, Smoother high-rate odometer data was obtained through IMU pre-integration and a first-order low-pass filter. The experimental results show that the proposed rotating lidar unit in indoor and outdoor conditions makes the rotorcraft UAV have a larger FOV, which not only improves the environmental perception capability and positional estimation accuracy of the rotorcraft but enhances the positioning reliability and flight stability of the rotorcraft UAV in complex environments.

Leaf area index and aboveground biomass estimation of an alpine peatland with a UAV multi-sensor approach

ABSTRACT Aboveground biomass (AGB) can serve as an indicator when estimating various biogeochemical processes in peatlands, an ecosystem which provides countless ecosystem services and plays a key role in climate regulation. While remote sensing has been extensively employed to assess AGB across vast areas in forested peatlands its application to small and treeless peatlands, which are typical of the alpine regions, has been limited. Due to the characteristics of peatlands, innovative approaches capable of capturing their fine-scale, highly heterogeneous and short-stature vegetation cover are needed. Likewise, other key requirements include an ability to overcome site accessibility barriers, cost-effective acquisition of datasets and minimizing damage of these protected habitats. Hence, the utilization of Unmanned Aerial Vehicles (UAVs) offers a viable means for mapping AGB in alpine peatlands. In this study, the AGB of the Val di Ciampo alpine peatland (Veneto Region, Italy) was estimated by combining datasets derived from in situ vegetation samples as well as UAV-based LiDAR, hyperspectral and RGB sensors. A limited number of vegetation samples were used to reduce the impact of the study on the ecosystem. The results indicate that a linear regression can model the relationship between AGB and Leaf Area Index (LAI) with a significant explanatory ability (R2 = 0.72; p < 0.001). Several indices derived from digital terrain model (DTM) morphologies, hyperspectral data, and orthophotos were tested using a multiple regression approach to determine their potential to enhance the model’s performance. Among these only the Double Difference (DD) index, derived from hyperspectral data, was found to slightly improve the model’s explanatory ability (R2 = 0.76). Overall, the findings of this study suggest that UAV LiDAR data provides the most reliable solution for estimating AGB in alpine peatlands, while the inclusion of hyperspectral data provides only a minor improvement in accuracy.

Coupling UAV Hyperspectral and LiDAR Data for Mangrove Classification Using XGBoost in China’s Pinglu Canal Estuary

The fine classification of mangroves plays a crucial role in enhancing our understanding of their structural and functional aspects which has significant implications for biodiversity conservation, carbon sequestration, water quality enhancement, and sustainable development. Accurate classification aids in effective mangrove management, protection, and preservation of coastal ecosystems. Previous studies predominantly relied on passive optical remote sensing images as data sources for mangrove classification, often overlooking the intricate vertical structural complexities of mangrove species. In this study, we address this limitation by incorporating unmanned aerial vehicle-LiDAR (UAV-LiDAR) point cloud 3D data with UAV hyperspectral imagery to perform multivariate classification of mangrove species. Five distinct variable scenarios were employed: band characteristics (S1), vegetation index (S2), texture measures (S3), fused hyperspectral characteristics (S4), and a canopy height model (CHM) combined with UAV hyperspectral characteristics and LiDAR point cloud data (S5). To execute this classification task, an extreme gradient boosting (XGBoost) machine learning algorithm was employed. Our investigation focused on the estuary of the Pinglu Canal, situated within the Maowei Sea of the Beibu Gulf in China. By comparing the classification outcomes of the five variable scenarios, we assessed the unique contributions of each variable to the accurate classification of mangrove species. The findings underscore several key points: (1) The fusion of multiple features in the image scenario led to a higher overall accuracy (OA) compared to models that employed individual features. Specifically, scenario S4 achieved an OA of 88.48% and scenario S5 exhibited an even more impressive OA of 96.78%. These figures surpassed those of the individual feature models where the results were S1 (83.35%), S2 (83.55%), and S3 (71.28%). (2) Combining UAV hyperspectral and LiDAR-derived CHM data yielded improved accuracy in mangrove species classification. This fusion ultimately resulted in an OA of 96.78% and kappa coefficient of 95.96%. (3) Notably, the incorporation of data from individual bands and vegetation indices into texture measures can enhance the accuracy of mangrove species classification. The approach employed in this study—a combination of the XGBoost algorithm and the integration of UAV hyperspectral and CHM features from LiDAR point cloud data—proved to be highly effective and exhibited strong performance in classifying mangrove species. These findings lay a robust foundation for future research efforts focused on mangrove ecosystem services and ecological restoration of mangrove forests.

Urban Forest Above-Ground Biomass Estimation Based on UAV 3D Real Scene

(1) Background: A three-dimensional (3D) real scene is a digital representation of the multidimensional dynamic real-world structure that enables the realistic and stereoscopic expression of actual scenarios, and is an important technological tool for urban refinement management. The above-ground biomass (AGB) of urban forests is an important indicator that reflects the urban ecological environment; therefore, the accurate estimation of AGB is of great significance for evaluating urban ecological functions. (2) Methods: In this study, multiangle aerial photographs of urban street trees were obtained via an unmanned aerial vehicle (UAV) single-lens five-way flight, from 0°, 0°, 90°, 180°, 270°, and five other directions. The multiple view stereo (MVS) algorithm was used to construct three-dimensional realistic models of two tree species: ginkgo and camphor. Then, structural parameters such as tree height, crown diameter, and crown volume were estimated from the 3D real-scene models. Lastly, single-tree AGB models were developed based on structural parameters. (3) Results: The results of this study indicated the following: (A) The UAV visible-light realistic 3D model had clear texture and truly reflected the structural characteristics of two tree species, ginkgo and camphor. (B) There was a significant correlation between the reference tree height, crown diameter and crown volume obtained from the realistic 3D model and the measured values; the R2 for ginkgo height was 0.90, the R2 for camphor crown diameter was 0.87, and the R2 for ginkgo crown volume was 0.89. (C) The accuracy of the AGB estimation models constructed with tree height and canopy volume as variables was generally higher than that of models with tree height and canopy diameter; the model with the highest accuracy of AGB estimation for ginkgo was the linear model with a validation accuracy R2 of 0.96 and RMSE of 8.21 kg, while the model with the highest accuracy of AGB estimation for camphor was the quadratic polynomial model with a validation accuracy R2 of 0.92 and RMSE of 27.74 kg. (4) Conclusions: This study demonstrated that the UAV 3D real-scene model can achieve high accuracy in estimating single-wood biomass in urban forests. In addition, for both tree species, there was no significant difference between the AGB estimates based on the UAV 3D real scene and LiDAR and the measured AGB. These results of urban single-wood AGB estimation based on the UAV 3D real-scene model were consistent with those of LiDAR and even with the measured AGB. Therefore, based on the UAV 3D real-scene model, the single-wood biomass can be estimated with high accuracy. This represents a new technical approach to urban forest resource monitoring and ecological environment function evaluation.

UAVStereo: A Multiple Resolution Dataset for Stereo Matching in UAV Scenarios

Stereo matching is a fundamental task in three-dimensional scene reconstruction. Recently, deep learning-based methods have proven effective on some benchmark datasets, such as KITTI and SceneFlow. Unmanned aerial vehicles (UAVs) are commonly used for surface observation, and the images captured are frequently used for detailed 3D reconstruction because of their high resolution and low-altitude acquisition. Currently, mainstream supervised learning networks require a significant amount of training data with ground-truth labels to learn model parameters. However, owing to the scarcity of UAV stereo-matching datasets, learning-based stereo matching methods in UAV scenarios is not fully investigated yet. To facilitate further research, this study proposes a pipeline for generating accurate and dense disparity maps using detailed meshes reconstructed based on UAV images and LiDAR point clouds. Through the proposed pipeline, we constructed a multi-resolution UAV scenario dataset called UAVStereo, with over 34,000 stereo image pairs covering three typical scenes. To the best of our knowledge, UAVStereo is the first stereo matching dataset for UAV low-altitude scenarios. The dataset includes synthetic and real stereo pairs to enable generalization from the synthetic domain to the real domain. Furthermore, our UAVStereo dataset provides multi-resolution and multi-scene image pairs to accommodate various sensors and environments. In this study, we evaluated traditional and state-of-the-art deep learning methods, highlighting their limitations in addressing challenges in UAV scenarios and offering suggestions for future research. Our dataset is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/rebecca0011/UAVStereo.git.</uri>

Above ground biomass estimation from UAV high resolution RGB images and LiDAR data in a pine forest in Southern Italy

Knowledge of forest biomass is an essential parameter for managing the forest in a sustainable way, as forest biomass data availability and reliability are necessary for forestry and forest planning, but also for the carbon market as well as to support the local economy in the mountain and inner areas. However, the accurate quantification of the above-ground biomass (AGB) is still a challenge both at the local and global levels. The use of remote sensing techniques with Unmanned Aerial Vehicle (UAV) platforms can be an excellent trade-off between resolution, scale, and frequency data of AGB estimation. In this study, we evaluated the combined use of RGB images from UAV, LiDAR data and ground truth data to estimate AGB in a forested watershed in Southern Italy. A low-cost AGB estimation method was adopted using a commercial fixed-wing drone equipped with an RGB camera, combined with the canopy information derived by LiDAR and validated by field data. Two modelling methods (stepwise regression, SR and random forest, RF) were used to estimate forest AGB. The output was an accurate maps of AGB for each model. The RF model showed better accuracy than the Steplm model, and the R2 increased from 0.81 to 0.86, and the RMSE and MAE values were decreased from 45.5 to 31.7 Mg ha-1 and from 34.2 to 22.1 Mg ha-1 respectively. We demonstrated that by increasing the computing efficiency through a machine learning algorithm, readily available images can be used to obtain satisfactory results, as proven by the accuracy of the Random forest above biomass estimation model.

Estimation of Urban Forest Characteristic Parameters Using UAV-Lidar Coupled with Canopy Volume

The estimation of characteristic parameters such as diameter at breast height (DBH), aboveground biomass (AGB) and stem volume (V) is an important part of urban forest resource monitoring and the most direct manifestation of the ecosystem functions of forests; therefore, the accurate estimation of urban forest characteristic parameters is valuable for evaluating urban ecological functions. In this study, the height and density characteristic variables of canopy point clouds were extracted as Scheme 1 and combined with the canopy structure variables as Scheme 2 based on unmanned aerial vehicle lidar (UAV-Lidar). We analyzed the spatial distribution characteristics of the canopies of different tree species, and multiple linear regression (MLR), support vector regression (SVR), and random forest (RF) models were used to estimate the DBH, AGB, and V of urban single trees. The estimation accuracy of different models was evaluated based on the field-measured data. The results indicated that the model accuracy of coupling canopy structure variables (R2 = 0.69–0.85, rRMSE = 9.87–24.67%) was higher than that of using only point-cloud-based height and density characteristic variables. The comparison of the results of different models shows that the RF model had the highest estimation accuracy (R2 = 0.76–0.85, rRMSE = 9.87–22.51%), which was better than that of the SVR and MLR models. In the RF model, the estimation accuracy of AGB was the highest (R2 = 0.85, rRMSE = 22.51%), followed by V, with an accuracy of R2 = 0.83, rRMSE = 18.51%, and the accuracy of DBH was the lowest (R2 = 0.76, rRMSE = 9.87%). The results of the study provide an important reference for the estimation of single-tree characteristic parameters in urban forests based on UAV-Lidar.

Design and Experimental Study on Vibration Reduction of an UAV Lidar Using Rubber Material

Rubber shock absorbers are widely used to reduce vibration in aerospace load devices due to their high damping characteristics. However, due to the material nonlinearity of rubber and high temperature, the accurate numerical simulation and practical application of rubber shock absorbers face difficulties and challenges. In this paper, taking a T-type rubber shock absorber as an example, according to the correlation data obtained from the performance test of rubber materials, a constitutive model of rubber materials is established for its hyperelasticity-viscoelasticity simulation analysis. On this basis, the rubber shock absorber was used to carry out the numerical simulation and experimental verification of an Unmanned Aerial Vehicle (UAV) Light Detection And Ranging (LiDAR). The results show that when the rubber constitutive model is used for simulation analysis, the obtained acceleration response curve on the UAV LiDAR is in good agreement with the test results, which effectively confirms the accuracy of the numerical simulation, and successfully verifies that the rubber shock absorber is suitable for vibration reduction of UAV LiDAR. At the same time, this method also provides a practical and effective solution for the vibration reduction design of rubber shock absorbers.

An automated, high-performance approach for detecting and characterizing broccoli based on UAV remote-sensing and transformers: A case study from Haining, China

• A lightweight UAV platform for detecting and characterizing broccoli was developed. • Transformers was chosen because of its success in natural language processing. • Existing TransUet and PCT provide a good balance between the accuracy and speed. • Our integrated framework is robust against variations of environmental conditions. Accurate canopy mapping and head-volume estimation of large areas of broccoli is an important prerequisite for precision farming since it provides important phenotypic traits associated with field management, environmental control, and yield prediction. Currently, the detection and characterization of broccoli mostly rely on ground surveys and human interpretation, which is often time- and labor-intensive. Recent developments based on unmanned aerial vehicle (UAV) remote sensing offer low cost, timely, and flexible data acquisition, thereby providing a potential alternative technique to enhance in situ field surveys. The combination of UAV data and deep learning has led to a series of breakthroughs in rapid and automated collection of simultaneous multisensor and multimodal plant phenotyping data. However, their application for monitoring broccoli remains problematic when faced with the significant spatial scale involved and the variety of vegetation species. To address this problem, we propose herein a fast and reliable semi-automatic workflow based on deep learning to process UAV RGB imagery and LiDAR point clouds and thereby remotely detect and characterize broccoli canopy and heads. First, we explore the use of TransUNet to differentiate canopy and non-canopy regions in RGB images at the individual-plant scale. The results demonstrate that TransUNet consistently achieves the highest accuracy (average returned Precision, Recall, F1 score, and IoU of 0.917, 0.864, 0.901, and 0.895, respectively) compared with three CNN-based and two shallow learning-based approaches. In addition, TransUNet performs best in terms of robustness against variations in training samples. Subsequently, to estimate the volume of broccoli heads, a point cloud transformer (PCT) network is developed for point cloud segmentation. Improving upon the results of three existing methods PointNet, PointNet++, and K-means that were applied to the same datasets, the best-performing PCT produced a precision of 0.914, an overall recall of 0.899, an overall F1 score of 0.901, and an overall IoU of 0.879. A regression analysis indicates that the PCT estimates had R 2 = 0.875, RMSE = 18.62, and rRMSE = 3.64 %, which is also superior to the results from other comparison approaches. Collectively, the wide application of such technology would facilitate applied research in plant phenotyping and precision agro-ecological applications and field management.

Novel Method for Monitoring Mining Subsidence Featuring Co-Registration of UAV LiDAR Data and Photogrammetry

Addressing the problem that traditional methods cannot reliably monitor surface subsidence in coal mining, a novel method has been developed for monitoring subsidence in mining areas using time series unmanned aerial vehicle (UAV) photogrammetry in combination with LiDAR. A dynamic subsidence basin based on the differential digital elevation model (DEM) was constructed and accuracy of the proposed method was verified, with the uncertainty of the DEM of difference (DoD) being quantified via co-registration of a dense matching point cloud of the time series UAV data. The root mean square error calculated for the monitoring points on the subsidence DEM was typically between 0.2 m and 0.3 m with a minimum of 0.17 m. The relative error between the maximum subsidence value of the extracted profile line on the main section after fitting and the measured maximum subsidence value was not more than 20%, and the minimum value was 0.7%. The accuracy of the UAV based method was at the decimeter level, and high accuracy in monitoring the maximum subsidence value was attained, confirming that an innovative strategy for monitoring mining subsidence was realized.

UAVS FOR A COMPLETE TOPOGRAPHIC SURVEY

Abstract. With the advancement of sensor technology, unmanned aerial vehicles (UAVs) or drones revolutionize several fields including topographic surveying, agriculture, recreation, emergency, rescue and so on. The autonomous flight modes available in current UAVs make it broaden to manoeuvring by an unskilled person. This, of course, causes to widely use the drone technology among different user communities. Of the revolutionized fields, topographic surveying is prominent because many low cost UAVs with on-board light weight optical payloads often deliver mapping products such as ortho-photos and DEMs with centimetre level accuracy (in XY and Z) that had been exclusively bounded to the expensive field surveying methods earlier. Though drones enables to obtain centimetre level geometric accuracy, the main drawback of the technology is inability to see underneath vegetation canopy which hinders applicability of drones for a complete topographical survey. In order to view beneath the tree canopies, UAV LiDAR is a solution but due to its high cost, it is still not popular among several communities who involve with land surveying. To measure underside vegetation, field surveying methods such as total stations and theodolites traversing are being mainly practised by the users. But it is also not a viable solution since it consumes much time and money. If remotely sensed data collection is able to capture landscapes that had been hampers by the canopies, definitely it will be a cost effective and a rapid solution. As such, oblique imagery (UAV) acquired in manual flight mode at very low altitudes is a good solution. The objective of the study is to develop a novel approach to generate UAV deliveries without vegetation canopy in vegetated areas.First, autonomous flight mission is completed while maintaining 80% and 70% forward and lateral overlaps. For the terrain patches where they are covered by tree canopies, oblique imageries have been collected while operating the drone manually at low altitudes. Each UAV flight is separately processed and merged in to a single image to extract 2D maps without gaps beneath tree canopies. Re-sampling is fulfilled prior to stitching in order to gain a seamless product. Performed accuracy analysis confirmed that the developed approach is sufficient to produce DTMs and ortho-mosaics having average RMSE-XY 0.087m and RMSE-Z 0.177m at 4.0cm GSD which is really acceptable. Besides, there is not any significant accuracy variation between underneath canopy areas and open areas.

Analysis of UAV lidar information loss and its influence on the estimation accuracy of structural and functional traits in a meadow steppe

• Canopy information loss of UAV lidar in grasslands is investigated. • Factors influencing UAV lidar information loss are analyzed. • UAV lidar information loss at canopy tops is more prevailing than at canopy bottoms. • UAV lidar can be used to extract grassland traits with a comparable accuracy to TLS. • Information loss at canopy tops greatly reduces the accuracy of grassland traits. Accurate quantification of grassland structural and functional traits is the foundation for grassland management and restoration. Light detection and ranging (lidar), especially the unmanned aerial vehicle (UAV) lidar, has been recognized as an accurate and effective technique for local to regional-scale vegetation structural and functional traits estimation. However, in grassland ecosystems, it is more likely to be influenced by UAV lidar information loss caused by dense vegetation canopies. In this study, we investigated how UAV lidar information loss may occur and how it may influence the estimation accuracy of grassland structural and functional traits by comparing it with terrestrial laser scanning (TLS) and field measurements in a meadow steppe of northern China. Five structural traits (i.e., mean vegetation height, maximum vegetation height, standard deviation of vegetation height, canopy cover, and canopy volume) and one functional trait (i.e., aboveground biomass) were estimated from the UAV lidar data and TLS data for evaluation. The results showed that TLS-derived structural and functional traits had a much higher accuracy than UAV lidar-derived traits. By comparing with TLS data, we found that UAV lidar data had a much more prevailing information loss at canopy tops than at canopy bottoms. The average height loss of UAV lidar at canopy tops reached over 0.30 m, and the average relative height loss reached over 49%, comparing to a value of 0.03 m and 6% at canopy bottoms. Maximum vegetation height, standard deviation, and the distance from the UAV lidar system to the ground were the three most influential factors on UAV lidar information loss at canopy tops, indicating the commonly seen sharp canopy tops of grasslands were prone to be missed by the UAV lidar system. UAV lidar information loss at canopy tops had a much stronger influence on the estimation accuracy of grassland structural and functional traits than that at canopy bottoms. With the decrease of information loss at canopy tops, UAV lidar can be used to extract grassland structural and functional traits with a comparable accuracy to TLS. Among the five grassland traits, aboveground biomass was the least influenced by UAV lidar information loss. This study is a very first evaluation on the UAV lidar information loss in grassland ecosystems and its influence on grassland structural and functional trait estimation, which can provide guidance for UAV lidar data collection and processing in future grassland applications.