PyLiGram – Research Application for LiDAR Data Processing Based on Photogrammetric Methods

ABSTRACTLand cover and its change are one of the important factors of global environmental change. The new GaoFen-2 (GF-2) satellite provides abundant spectral features and texture information, and airborne light detection and ranging (lidar) provides accurate three-dimensional coordinates at a finer scale. Fusing these data has the potential to improve land-cover classification. In the article, we selected the Random Forest (RF) as a classifier. The spectral bands of GF-2, normalized difference vegetation index (NDVI), normalized digital surface model derived from lidar data, and their grey-level co-occurrence matrix (GLCM) textures including mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation were generated to create seven scenarios with different combination of RF input variables. We estimated the classification performance on GF-2 satellite data, compared and assessed the individual and combined contributions of GF-2 and lidar data with regard to classification accuracy using fusion data, and identified the optimum combination of input variables that best balances classification performance with the computational challenges for land-cover classification. The results showed that GF-2 multispectral data alone or the fusion of GF-2 data and other sources can provide relatively good classification mapping accuracy in complex urban environments. The classification accuracy of fused data from the GF-2 satellite and lidar data exceeded those of GF-2 or lidar data alone. Moreover, GLCM textures significantly improved the classification performance whether using GF-2 satellite data or lidar height data. A fusion of GF-2 multispectral data, NDVI, lidar data, and their texture features (102 RF variables) achieved the best classification accuracy in seven scenarios. Using the optimum set of variables (55 variables) for RF yielded the most satisfactory classification result, achieving a total accuracy and kappa coefficient of 94.51% and 0.93, respectively. The producer’s accuracy and user’s accuracy exceeded 90% for almost all classes. This study aims to provide a reference for the efficient improvement of land-cover classification and offer support for extending the applications of classification algorithms and data sources.

A bottom-up approach to segment individual deciduous trees using leaf-off lidar point cloud data

High-resolution lidar data, acquired over a deciduous forest, were used to investigate the potential utility and limitations of current virtual reality (VR) software for remote sensing analysis and evaluation. Although a standard remote sensing software package provided a good overview of interpolated, smoothed lidar data, functionality was lower for gridded data that had not been interpolated. However, it was possible to drape orthophotographs and other images over the gridded lidar data, providing a useful method for investigating relationships between the lidar and other data sets. Using a commercial VR package, it was possible to view the original lidar point data; consequently, we were able to visualize the multiple returns from within the canopy of each tree. These point data were preferable for identifying surfaces within the data cloud, especially the ground surface, because the original point data allow an analyst to see, and work with, the full spatial complexity of the data. Being able to visualize the original data clouds also helps in delineating individual trees, the structure of returns within single trees and, potentially, to identify objects hidden within and beneath the trees. For a fully integrated remote-sensing VR package, additional functionality is needed to link point and interpolated coverages, and to enhance the interactive selection of data for further statistical analysis.

Forests are critical natural resources for human life and wildlife, as they sustain and protect biodiversity, and supply multiple ecosystem services. However, these ecosystems are vulnerable to human-driven climate change, necessitating automated systems to monitor structural changes at the individual tree level and assess forest responses to climate anomalies. Forest inventories, that contain accurate and detailed measurements of forest structure, are essential to improving our knowledge of ecosystem services and functions. UAV and LiDAR-based tree canopy detection is valuable for estimating essential ecosystem variables (EEVs). In this research, we have validated tree structural properties primarily diameter at breast height (DBH) and tree height obtained from UAV imagery and airborne LiDAR point cloud data using field measured data. We developed Drone4Tree, a user-friendly platform built on Streamlit and Flask that provides an end-to-end solution for processing UAV imagery. The platform processes UAV-acquired data to generate orthomosaics using OpenDroneMap, delineate tree crowns using U-Net based segmentation, and derive tree attributes such as tree height, canopy area etc.The LiDAR data was processed using forest structural complexity tool (FSCT). This tool applies sensor agnostic semantic segmentation on the point cloud to obtain individual trees, stems and their structural properties. The LiDAR and UAV derived properties were joined with the field obtained parameters. Comparative analysis shows strong agreement between field DBH and LiDAR-derived DBH (R2 = 0.97), indicating reliable DBH estimation from LiDAR data. For tree height, the LiDAR-based measurements correlated well with field measured tree heights (R2 = 0.73), though comparisons with the UAV-based tree height (R2 = 0.97) obtained from canopy height models (CHM) revealed a lower correlation (R2 = 0.66). UAV-based tree height measurements show statistically significant relation with field measured height (R2 = 0.57). These results indicate that LiDAR and UAV data complement each other, with UAVs offering efficient monitoring capabilities while LiDAR providing additional precision.These findings underscore the potential of integrating UAV and LiDAR technologies for accurate and efficient forest monitoring, enabling improved assessment of ecosystem functions and responses to climate change. By combining these complementary methods, platforms like Drone4Tree can support sustainable forest management and contribute to addressing the monitoring of global environmental changes.

Although the GIS community has been quick to exploit the advantages of virtual reality (VR) for display and analysis of spatial data, VR does not appear to have been exploited widely for remote sensing data analysis. A case study of high resolution lidar data acquired over a deciduous forest near Morgantown, WV was used to investigate the potential and limitations of current VR software for remote sensing analysis. The functionality within a standard remote sensing software package was found to provide a good overview of interpolated, smoothed lidar data, but was less useful for gridded data that had not been interpolated. With gridded data, it was possible to drape orthophotographs or other images over the lidar data, providing a useful method for investigating relationships between lidar and other data. Alternatively, using a commercial VR package, it was possible to view the original lidar point data, and thus visualize the multiple returns from within the canopy of each tree. The point data were preferable for identification of surfaces within the data cloud, especially the ground surface. For a fully integrated remote sensing VR package, functionality will be needed to link point and interpolated coverages, and also to enhance the interactive selection of data for further statistical analysis.

Abstract. The accuracy of spatial raw data is contingent on a number of factors, including the accuracy of the sensors, their calibration, and direct and indirect referencing. The efficacy of the captured data can be enhanced through the implementation of effective data processing methodologies. The present research is dedicated to the enhancement of combined photogrammetric and LiDAR data.In the contemporary context, the trajectory of the vehicle can be affected by GPS signal jamming, a phenomenon that is attributable to international circumstances. This necessitates a combined adjustment of RGB/CIR and LiDAR data. The proposed method necessitates the utilisation of both sets of data: The study area was imaged using both RGB and CIR technologies, with intensity LiDAR strips also employed to cover the same area. The present approach is founded upon the notion of lidargrammetry (Jayendra-Lakshman and Devarajan, 2013), which uses photogrammetric algorithms for lidar data processing (Rzonca and Twardowski, 2022).The research tool, PyLiGram, generates synthetic images of the LiDAR data, known as lidargrams or renders, applying the same interior orientation parameters (IOPs) as the real camera used to capture the real RGB/CIR images. The synthetic images are centrally projected according to IOPs and predefined external orientation parameters (EOPs). The projection process is reversible by use of unique lidar point identifiers. Points can be projected onto synthetic images, and after processing the same images, points can be intersected to create a new point cloud.The paper sets out the potential of applying photogrammetric methods to the co-adjustment of RGB/CIR and LiDAR data. The process entails the collaborative processing of RGB/CIR and LiDAR images through the utilisation of deep learning matching techniques and common least squares adjustment. The refined EOPs are then utilised to intersect the refined point cloud and enhance the images' positions.A key benefit of this approach is that it has the potential to eliminate the necessity for LiDAR control patches/points or ground control points for RGB/CIR images, depending on the specific case.The process was subjected to a series of trials on multiple datasets, each comprising a point cloud density of approximately 100 points per square metre and images with a ground sample distance (GSD) ranging from 5 to 10 centimetres.

ABSTRACTThis contribution proposes an evaluation of lidar and radar data processing and its potential in revealing archaeological features within a level plain environment, the southern lowland of Verona (Italy), focusing on evidences dating back to the Bronze Age. Many archaeological sites in the research area, including some of the most outstanding settlements of Terramare Culture, were identified or at least examined through aerial photo observation. Even if in several occasions modern agricultural activities contributed to the discoveries, bringing to the surface artifacts and scrapes of buried layers, this kind of impact has also been progressively deteriorating the archaeological record, hence the proto-historic landscape is now discernible through evanescent marks which cannot be always detected using customary optical sensors. Lidar and radar data analysis has then been considered as an alternative, non-invasive method of investigation on such a vast area.

The fusion of dissimilar data modalities in neural networks presents a significant challenge, particularly in the case of multimodal hyperspectral and lidar data. Hyperspectral data, typically represented as images with potentially hundreds of bands, provide a wealth of spectral information, while lidar data, commonly represented as point clouds with millions of unordered points in 3D space, offer structural information. The complementary nature of these data types presents a unique challenge due to their fundamentally different representations requiring distinct processing methods. In this work, we introduce an alternative hyperspectral data representation in the form of a hyperspectral point cloud (HSPC), which enables ingestion and exploitation with point cloud processing neural network methods. Additionally, we present a composite fusion-style, point convolution-based neural network architecture for the semantic segmentation of HSPC and lidar point cloud data. We investigate the effects of the proposed HSPC representation for both unimodal and multimodal networks ingesting a variety of hyperspectral and lidar data representations. Finally, we compare the performance of these networks against each other and previous approaches. This study paves the way for innovative approaches to multimodal remote sensing data fusion, unlocking new possibilities for enhanced data analysis and interpretation.

The most important part in forest inventory based on remote sensing data is individual tree identification, because only when the tree is identified, we can try to determine its characteristic features. The objective of research is to explore remote sensing methods to determine individual tree position using LIDAR and digital aerial photography in Latvian forest conditions. The study site is a forest in the middle of Latvia at Jelgava district (56o39' N, 23o47' E). Aerial photography camera (ADS 40) and laser scanner (ALS 50 II) were used to capture the data. A LIDAR data is 1.4 to 9 p/m2 depending on the altitude. Image data is RGB (Red, Green, and Blue), NIR (Near Infrared) and PAN (Panchromatic) spectrum with 20 to 50 cm pixel resolution depending on the altitude. Image processing was made using Fourier transform and RGB colour segmentation. LIDAR data are processed with DBSCAN algorithm, global maximum algorithm, and local maximum algorithm. Field measurement's parameters were tree coordinates, species, height, diameter at breast height, crown width, and length. Best results on both ALS and ADS data were achieved using local maximum methods.

High resolution 3d point cloud data obtained by 3d laser scanning system has become a research hotspot and difficulty in recent years due to its large data volume, irregular data and high scene complexity. Target detection is the basis of scene analysis and understanding, which provides the underlying object and analysis basis for high-level scene understanding. Based on high resolution three-dimensional point cloud data of target recognition and tracking problem both in theory and application is facing great challenge, is a new research topic in this paper, according to the laser point cloud data processing as the research object, analyses the characteristics of lidar point cloud data and data processing of train of thought, analysis of lidar point cloud data storage and retrieval strategy, on the basis of the target recognition based on the laser point cloud data. The lidar data are distributed discretely in form. The discretization here refers to the irregular distribution of the positions and intervals of exponential data points in the three-dimensional space, namely the irregular distribution of data. In recent years, with the rise of deep learning and the large-scale application of deep learning in image detection, speech recognition, text processing and other related fields, it has become one of the current important research topics to use the method of deep learning for target recognition of three-dimensional point cloud data. Its main idea is to learn hierarchical feature expression through supervised way and describe the object from the bottom to the top. This method can effectively improve the ability of object feature representation and the performance of object recognition. Deep learning is also widely used in object recognition, object detection, scene segmentation and other image processing. Therefore, this paper adopts the method of deep learning to classify and identify 3d objects.

Species-rich subtropical forests have high carbon sequestration capacity and play important roles in regional and global carbon regulation and climate changes. A timely investigation of the spatial distribution characteristics of subtropical forest aboveground biomass (AGB) is essential to assess forest carbon stocks. Lidar (light detection and ranging) is regarded as the most reliable data source for accurate estimation of forest AGB. However, previous studies that have used lidar data have often beenbased on a single model developed from the relationships between lidar-derived variables and AGB, ignoring the variability of this relationship in different forest types. Although stratification of forest types has been proven to be effective for improving AGB estimation, how to stratify forest types and how many strata to use are still unclear. This research aims to improve forest AGB estimation through exploring suitable stratification approaches based on lidar and field survey data. Different stratification schemes including non-stratification and stratifications based on forest types and forest stand structures were examined. The AGB estimation models were developed using linear regression (LR) and random forest (RF) approaches. The results indicate the following: (1) Proper stratifications improved AGB estimation and reduced the effect of under- and overestimation problems; (2) the finer forest type strata generated higher accuracy of AGB estimation but required many more sample plots, which were often unavailable; (3) AGB estimation based on stratification of forest stand structures was similar to that based on five forest types, implying that proper stratification reduces the number of sample plots needed; (4) the optimal AGB estimation model and stratification scheme varied, depending on forest types; and (5) the RF algorithm provided better AGB estimation for non-stratification than the LR algorithm, but the LR approach provided better estimation with stratification. Results from this research provide new insights on how to properly conduct forest stratification for AGB estimation modeling, which is especially valuable in tropical and subtropical regions with complex forest types.

Forest canopy height estimates, at a regional scale, help understand the forest carbon storage, ecosystem processes, the development of forest management and the restoration policies to mitigate global climate change, etc. The recent availability of the NASA’s Global Ecosystem Dynamics Investigation (GEDI) LiDAR data has opened up new avenues to assess the plant canopy height at a footprint level. Here, we present a novel approach using the random forest (RF) for the wall-to-wall canopy height estimation over India’s forests (i.e., evergreen forest, deciduous forest, mixed forest, plantation, and shrubland) by employing the high-resolution top-of-the-atmosphere (TOA) reflectance and vegetation indices, the synthetic aperture radar (SAR) backscatters, the topography and tree canopy density, as the proxy variables. The variable importance plot indicated that the SAR backscatters, tree canopy density and the topography are the most influential height predictors. 33.15% of India’s forest cover demonstrated the canopy height <10 m, while 44.51% accounted for 10–20 m and 22.34% of forests demonstrated a higher canopy height (>20 m). This study advocates the importance and use of GEDI data for estimating the canopy height, preferably in data-deficit mountainous regions, where most of India’s natural forest vegetation exists.

ABSTRACTLight detection and ranging (LiDAR) data are essential for scientific discoveries such as Earth and ecological sciences, environmental applications, and responding to natural disasters. While collecting LiDAR data over large areas is quite possible the subsequent processing steps typically involve large computational demands. Efficiently storing, managing, and processing LiDAR data are the prerequisite steps for enabling these LiDAR-based applications. However, handling LiDAR data poses grand geoprocessing challenges due to data and computational intensity. To tackle such challenges, we developed a general-purpose scalable framework coupled with a sophisticated data decomposition and parallelization strategy to efficiently handle ‘big’ LiDAR data collections. The contributions of this research were (1) a tile-based spatial index to manage big LiDAR data in the scalable and fault-tolerable Hadoop distributed file system, (2) two spatial decomposition techniques to enable efficient parallelization of different types of LiDAR processing tasks, and (3) by coupling existing LiDAR processing tools with Hadoop, a variety of LiDAR data processing tasks can be conducted in parallel in a highly scalable distributed computing environment using an online geoprocessing application. A proof-of-concept prototype is presented here to demonstrate the feasibility, performance, and scalability of the proposed framework.

Airborne LiDAR is one of the most effective and reliable means of terrain data collection. Using LiDAR data for digital elevation model (DEM) generation is becoming a standard practice in spatial related areas. However, the effective processing of the raw LiDAR data and the generation of an efficient and high-quality DEM remain big challenges. This paper reviews the recent advances of airborne LiDAR systems and the use of LiDAR data for DEM generation, with special focus on LiDAR data filters, interpolation methods, DEM resolution, and LiDAR data reduction. Separating LiDAR points into ground and non-ground is the most critical and difficult step for DEM generation from LiDAR data. Commonly used and most recently developed LiDAR filtering methods are presented. Interpolation methods and choices of suitable interpolator and DEM resolution for LiDAR DEM generation are discussed in detail. In order to reduce the data redundancy and increase the efficiency in terms of storage and manipulation, LiDAR data reduction is required in the process of DEM generation. Feature specific elements such as breaklines contribute significantly to DEM quality. Therefore, data reduction should be conducted in such a way that critical elements are kept while less important elements are removed. Given the high-density characteristic of LiDAR data, breaklines can be directly extracted from LiDAR data. Extraction of breaklines and integration of the breaklines into DEM generation are presented.

Unmanned aerial vehicles (UAVs) provide a new research tool to obtain high spatial and temporal resolution imagery at a reduced cost. Rapid advances in miniature sensor technology are leading to greater potentials for ecological research. We demonstrate one of the first applications of UAV lidar and hyperspectral imagery and a fusion method for individual plant species identification and 3D characterization at submeter scales in south‐eastern Arizona, USA. The UAV lidar scanner characterized the individual vegetation canopy structure and bare ground elevation, whereas the hyperspectral sensor provided species‐specific spectral signatures for the dominant and target species at our study area in leaf‐on condition. We hypothesized that the fusion of the two different data sources would perform better than either data type alone in the arid and semi‐arid ecosystems with sparse vegetation. The fusion approach provides 84–89% overall accuracy (kappa values of 0.80–0.86) in target species classification at the canopy scale, leveraging a wide range of target spectral responses in the hyperspectral data and a high point density (50 points/m2) in the lidar data. In comparison, the hyperspectral image classification alone produced 72–76% overall accuracies (kappa values of 0.70 and 0.71). The UAV lidar‐derived digital elevation model (DEM) is also strongly correlated with manned airborne lidar‐derived DEM (R2 = 0.98 and 0.96), but was obtained at a lower cost. The lidar and hyperspectral data as well as the fusion method demonstrated here can be widely applied across a gradient of vegetation and topography to monitor and detect ecological changes at a local scale.