USING IMAGE MATCHING AND AIRBORNE LASER SCANNING POINT CLOUDS FOR GENERATING CANOPY HEIGHT MODEL

Airborne laser scanning (ALS) point clouds are employed for the generation of country-wide digital terrain and surface models (DTMs and DSMs) and to derive further information about forested areas. This acquisition method has been established as a state-of-the-art of topographic data acquisition, especially in forested areas. However, as ALS data acquisitions are done on relatively low temporal resolution (e.g. for Austria every 6-10 years), forest parameter extraction with high temporal resolution based on ALS data is limited. In particular, the derivation of dynamic forest information such as biomass or canopy cover changes requires relatively high temporal resolution.Aerial images, along with their image-matching-based point clouds (IM), provide a further option for the creation of DSMs. Especially in areas with high vegetation such as forests, the ALS and IM data yield different elevation values.The aim of this study is to systematically quantify these differences and to investigate strategies to approximate IM-based DSMs to the ALS-based DSMs. For this research, a study site within the Vienna Woods Biosphere Reserve in the Eastern part of Austria was selected for the development and evaluation of an approach to minimise the height differences. For this area ALS and IM datasets from the same month are available.Initially, topographic models, such as the normalised DSM (nDSM), were derived from the available point clouds. Statistical parameters for different kernel sizes of the image matching nDSM were further calculated within a derived canopy mask. These parameters as predictors, along with the known differences of the nDSMS based on ALS and IM as target values, were used to train a random forest regression to further fit the IM to the ALS data.The validation, conducted on three different areas, showed an approximation of the elevation values to the ALS nDSM utilised as a reference within the canopy mask. This improvement demonstrates a promising approximation of the two models of about 77% in relation to the median of the deviations between the adjusted and the given model compared to the initial situation. The IM data shows its limitations in elongated gaps in the canopy, as the closing effects of small canopy gaps in forested areas pose challenges for the IM-based nDSM. In such instances, the regression function cannot make any improvements.

There is a need to replace outdated vegetation maps over Sweden’s mountain region; the ability and accuracy of creating such maps with automated methods and remotely sensed data has been a topic of recent research. While spectral information is a key data input for mapping mountain vegetation, the addition of three-dimensional (3D) data has also proven useful in classification. Point clouds from photogrammetric image matching (IM) or from airborne laser scanning (ALS) are potential 3D data sources. In this study, vegetation height and density metrics from IM and ALS data were classified both alone and in combination with SPOT 5 (Système Probatoire d’Observation de la Terre) satellite data and elevation data (elevation, slope, and a wetness index). A Random Forest classification was used to map alpine and subalpine vegetation over Abisko, Sweden. The most notable result in this study was higher producer’s accuracy of the mountain birch classification when using IM metrics alone (98%) as compared to ALS data alone (89%). Classification of IM, SPOT, and elevation data combined gave the same overall accuracy (83%) as when using ALS, SPOT, and elevation data combined (also 83%). While most of the alpine vegetation classes were poorly classified using either the IM or ALS metrics alone, the IM point cloud appeared to contain more information for lower-growing (<2 m) vegetation than the ALS point cloud.

This study aims to highlight the differences, in terms of robustness and efficiency, of the use of LIDAR point clouds compared to dense image matching (DIM) point clouds at urban areas that contain buildings with complex structure. The application is conducted over an area in the Greek island of Milos using two different types of data: (a) a dense point cloud which extracted by DIM using a variation of the stereo-method semi-global matching (SGM) at RGB digital aerial images, and (b) a georeferenced LIDAR point cloud. For the case of the DIM point cloud, the following steps were applied: aerial triangulation, rectification of the original images to epipolar images, extraction of disparity maps and application of a 3D similarity transformation. The evaluations that were executed included urban and rural areas. At first step, a direct cloud-to-cloud comparison between the georeferenced DIM and LIDAR point clouds was carried out. Then, the corresponding orthoimages generated by the DIM and LIDAR point clouds undergo a quality control. Although the results show that the LIDAR point clouds respond better at such complex scenes compared to DIM point clouds, the latter gave promising results. In this context, the Quality Assurance issue is also discussed so as to be more efficient towards the challenge of the increasingly greater demands for accurate and cost effective applications.

Individual tree detection (ITD) algorithms have often relied on airborne laser scanning (ALS) data for delineating trees. Digital Aerial Photogrammetry (DAP) has emerged as a viable alternative to ALS, leveraging sophisticated image-matching algorithms for 3D point cloud generation and subsequent ITD. However, so far, few studies have compared ITD results between ALS and DAP 3D data. We present a detailed comparison of five ITD algorithms using both ALS and DAP data in a subtropical Chir Pine forests, Pakistan. Our analysis, which included 284 field-measured trees, assessed two categories of ITD algorithms: those applied to raster-based Canopy Height Models (CHMs) and those which are directly applied to the point clouds. We evaluated work-flows using fixed window size (FWS) and variable window size (VWS) as well as, unsmoothed and smoothed CHMs generated from ALS and DAP data. Among window sizes, 3 × 3 FWS and 2 × 2 FWS performed best, yielding F Scores of 0.66 and 0.63 using unsmoothed CHMs from ALS and DAP data, respectively. Among point cloud methods, mean shift algorithms consistently outperformed others, achieving F Scores of 0.67 and 0.61 with ALS and DAP data, respectively. The Dalponte2016 algorithm exhibited superior performance in crown segmentation, consistently producing crown radii within 0.5 m of the reference field measured crowns, for ALS data and under 0.6 m for DAP data. Overall, both ALS and DAP achieved comparable results; however, ALS data yielded slightly higher F scores in tree matching and exhibited a stronger correlation with field data compared to DAP. Our findings suggest that DAP-derived point clouds, when normalized by precise DTMs such as those obtained from ALS data, can be effectively utilized for ITD in Chir Pine forests, offering compatibility comparable to ALS data.

Extracting moso bamboo parameters from single-source point cloud data has limitations. In this article, a new approach for extracting moso bamboo parameters using airborne laser scanning (ALS) and terrestrial laser scanning (TLS) point cloud data is proposed. Using the field-surveyed coordinates of plot corner points and the Iterative Closest Point (ICP) algorithm, the ALS and TLS point clouds were aligned. Considering the difference in point distribution of ALS, TLS, and the merged point cloud, individual bamboo plants were segmented from the ALS point cloud using the point cloud segmentation (PCS) algorithm, and individual bamboo plants were segmented from the TLS and the merged point cloud using the comparative shortest-path (CSP) method. The cylinder fitting method was used to estimate the diameter at breast height (DBH) of the segmented bamboo plants. The accuracy was calculated by comparing the bamboo parameter values extracted by the above methods with reference data in three sample plots. The comparison results showed that by using the merged data, the detection rate of moso bamboo plants could reach up to 97.30%; the R2 of the estimated bamboo height was increased to above 0.96, and the root mean square error (RMSE) decreased from 1.14 m at most to a range of 0.35-0.48 m, while the R2 of the DBH fit was increased to a range of 0.97-0.99, and the RMSE decreased from 0.004 m at most to a range of 0.001-0.003 m. The accuracy of moso bamboo parameter extraction was significantly improved by using the merged point cloud data.

During the past decade, airborne laser scanning (ALS) has established its status as the state-of-the-art method for detailed forest mapping and monitoring. Current operational forest inventory widely utilizes ALS-based methods. Recent advances in sensor technology and image processing have enabled the extraction of dense point clouds from digital stereo imagery (DSI). Compared with ALS data, the DSI-based data are cheap and the point cloud densities can easily reach that of ALS. In terms of point density, even the high-altitude DSI-based point clouds can be sufficient for detecting individual tree crowns. However, there are significant differences in the characteristics of ALS and DSI point clouds that likely affect the accuracy of tree detection. In this study, the performance of high-altitude DSI point clouds was compared with low-density ALS in detecting individual trees. The trees were extracted from DSI- and ALS-based canopy height models (CHM) using watershed segmentation. The use of both smoothed and unsmoothed CHMs was tested. The results show that, even though the spatial resolution of the DSI-based CHM was better, in terms of detecting the trees and the accuracy of height estimates, the low-density ALS performed better. However, utilizing DSI with shorter ground sample distance (GSD) and more suitable image matching algorithms would likely enhance the accuracy of DSI-based approach.

Digital aerial photogrammetry (DAP) has emerged as a potentially cost-effective alternative to airborne laser scanning (ALS) for forest inventory methods that employ point cloud data. Forest inventory derived from DAP using area-based methods has been shown to achieve accuracy similar to that of ALS data. At the tree level, individual tree detection (ITD) algorithms have been developed to detect and/or delineate individual trees either from ALS point cloud data or from ALS- or DAP-based canopy height models. An examination of the application of ITDs to DAP-based point clouds has not yet been reported. In this research, we evaluate the suitability of DAP-based point clouds for individual tree detection in the Pinus radiata plantation. Two ITD algorithms designed to work with point cloud data are applied to dense point clouds generated from small- and medium-format photography and to an ALS point cloud. Performance of the two ITD algorithms, the influence of stand structure on tree detection rates, and the relationship between tree detection rates and canopy structural metrics are investigated. Overall, we show that there is a good agreement between ALS- and DAP-based ITD results (proportion of false negatives for ALS, SFP, and MFP was always lower than 29.6%, 25.3%, and 28.6%, respectively, whereas, the proportion of false positives for ALS, SFP, and MFP was always lower than 39.4%, 30.7%, and 33.7%, respectively). Differences between small- and medium-format DAP results were minor (for SFP and MFP, differences between recall, precision, and F-score were always less than 0.08, 0.03, and 0.05, respectively), suggesting that DAP point cloud data is robust for ITD. Our results show that among all the canopy structural metrics, the number of trees per hectare has the greatest influence on the tree detection rates.

Automatic extraction of buildings from airborne laser scanning (ALS) point clouds is essential for 3D building reconstruction. This paper presents a two-part approach for extracting buildings from ALS data. First, building objects are extracted from ALS data by a marked point process using the Gibbs energy model of buildings and sampled by a reversible jump Markov chain Monte Carlo algorithm. Second, a refinement operation is performed to filter the non-building points and false building objects before extracting buildings from the detected building objects. Experimental results and evaluation using ISPRS benchmark data-sets showed the robustness of the proposed method.

Canopy height change (CHC) is one of the key characteristics of forest dynamics, associated with the fluctuations in forest above-ground biomass and carbon stocks. Field measurements and Airborne Laser Scanning (ALS) point clouds can be used to detect CHC; however, they have limited availability in space and time, making it challenging to map CHC over large areas. Alternatively, very high-resolution (VHR) satellite stereo imagery plays an increasingly vital role in estimating fine-scaled digital surface models (DSMs) across landscapes. However, its capability and potential to estimate canopy height model (CHM) and CHC has not been widely explored. Using ALS-derived CHM in 2011 and 2015 and the four-year CHC as references, we evaluated stereo-based CHM and CHC from WorldView-2 over five woody parks in Columbus, Ohio, USA. We also integrated stereo-based CHM with vegetation indices from Landsat 7 to improve CHM and CHC estimation with machine learning methods. Our results showed that VHR stereo imagery captured similar spatial patterns of CHM with ALS data but significantly overestimated CHM. Moreover, the ALS-derived CHC ranged from 1.6±1.9 m (mean ± standard deviation) to 3.1±1.2 m, as compared to from -1.3±0.7 m to 1.1±1.7 m for stereo-based CHC, indicating the limitation of CHC estimation by stereo imagery alone. Among six widely used machine learning methods, Gradient Boosting Regression method provided the most reliable estimates of CHM, with a correlation coefficient R of 0.64 and a root-mean-square error (RMSE) of 3.1 m (11.1%). Stereo-based CHM and vegetation indices explained more than 70% of CHM variability, substantially improving the estimation of 4-year CHC. Our results suggested that VHR stereo imagery alone has limitations in estimating CHM and CHC. The combination of remote-sensing structural (stereo-based CHM) and spectral (vegetation indices) information improves the CHM and CHC estimations.

Airborne laser scanning (ALS) point cloud has been widely used in various fields, for it can acquire three-dimensional data with a high accuracy on a large scale. However, due to the fact that ALS data are discretely, irregularly distributed and contain noise, it is still a challenge to accurately identify various typical surface objects from 3D point cloud. In recent years, many researchers proved better results in classifying 3D point cloud by using different deep learning methods. However, most of these methods require a large number of training samples and cannot be widely used in complex scenarios. In this paper, we propose an ALS point cloud classification method to integrate an improved fully convolutional network into transfer learning with multi-scale and multi-view deep features. First, the shallow features of the airborne laser scanning point cloud such as height, intensity and change of curvature are extracted to generate feature maps by multi-scale voxel and multi-view projection. Second, these feature maps are fed into the pre-trained DenseNet201 model to derive deep features, which are used as input for a fully convolutional neural network with convolutional and pooling layers. By using this network, the local and global features are integrated to classify the ALS point cloud. Finally, a graph-cuts algorithm considering context information is used to refine the classification results. We tested our method on the semantic 3D labeling dataset of the International Society for Photogrammetry and Remote Sensing (ISPRS). Experimental results show that overall accuracy and the average F1 score obtained by the proposed method is 89.84% and 83.62%, respectively, when only 16,000 points of the original data are used for training.

Top height (TH) is one of the most important features of forest stands that is used in forest resource management. Thus far, the TH has been mainly determined in forestry on the basis of field measurements. There are certain accepted theoretical guidelines on how the TH should be determined. However, due to high cost and time consumption, it is difficult to meet these assumptions with traditional field measurement methods. Currently, remote sensing is widely used in forest inventory, also for the determination of TH. However, it is still usually conducted by linking the remote sensing data—most often airborne laser scanning (ALS) point clouds—with ground-based measurements using the area-based approach. Different plot sizes and point cloud metrics are used to determine TH, making it difficult to compare the results. There is therefore a need for a universal methodology for determining TH directly from ALS data – one that is consistent with the methodology used for field measurement data. This paper presents the results of an experiment that was aimed at assessing the accuracy of TH determination on the basis of ALS data. A comparison of the six considered ALS-derived proxies of TH showed that the individual tree detection approach was the most accurate. The bias of this method, when calculated for 48 artificial forest stands, amounted to 0.15 m. The approach based on the lower percentiles of the distribution of point heights significantly underestimated the TH from −0.67 m to up to −1.9 m. On the basis of the obtained results, we claim that TH can be determined, based on ALS data without ground measurements, with an accuracy that is acceptable for forest practitioners and researchers.

Filtering of airborne laser scanning (ALS) point clouds into ground and nonground points is a core postprocessing step for ALS data. A hierarchical filtering method, which has high operating efficiency and accuracy because of the combination of multiscale morphology and progressive triangulated irregular network (TIN) densification (PTD), is proposed. In the proposed method, the grid is first constructed for the ALS point clouds, and virtual seed points are set by analyzing the shape and elevation distribution of points within the grid. Then, the virtual seed points are classified as ground or nonground using the multiscale morphological method. Finally, the virtual ground seed points are utilized to generate the initial TIN, and the filter is completed by iteratively densifying the initial TIN. We used various ALS data to test the performance of the proposed method. The experimental results show that the proposed filtering method has strong applicability for a variety of landscapes and, in particular, has lower commission error than the classical PTD filtering method in urban areas.

A base map provides essential geospatial information for applications such as urban planning, intelligent transportation systems, and disaster management. Buildings and roads are the main ingredients of a base map and are represented by polygons. Unfortunately, manually delineating their boundaries from remote sensing data is time consuming and labour intensive. Airborne laser scanning (ALS) point clouds provide dense and accurate 3D positional information. Automatic extraction of buildings and roads from 3D point clouds is challenging because of their irregular shapes, occlusions in the data, and irregularity of ALS point clouds. This study focuses on two particular objectives: (i) accurate classification of a large volume of ALS 3D point clouds; and (ii) smooth and accurate building and road outline extraction. To achieve the classification objective, we perform point-wise deep learning to classify an ALS point cloud of a complex urban scene in Surabaya, Indonesia. The point cloud is colored by airborne orthophotos. Training data is obtained from an existing 2D topographic base map by a semi-automatic method proposed in this research. A dynamic-graph convolutional neural network is used to classify the point cloud into four classes: bare land, trees, buildings, and roads. We investigate effective input feature combinations for outdoor point cloud classification. A highly acceptable classification result of 91.8% overall accuracy is achieved when using the full combination of RGB color and LiDAR features. To address the objective of outline extraction, we propose building and road outline extraction methods that run directly on ALS point cloud data. For accurate and smooth building outline extraction, we propose two different methods. First, we develop the ordered Hough transform (OHT), which is an extension of the traditional Hough transform, by explicitly incorporating the sequence of points to form the outline. Second, we propose a new method based on Medial Axis Transform (MAT) skeletons which takes advantage of the skeleton points to detect building corners. The OHT method is resistant to noise but it requires prior knowledge on a building’s main directions. On the contrary, the MAT-based method does not require such orientation initialization but is more sensitive to noise on building edges. We compare the results of our building outline extraction methods to an existing RANSAC-based method, in terms of geometric accuracy, completeness of building corners, and computation time, and demonstrate that the MAT-based approach has the highest geometric accuracy, results in more complete building corners, and is slightly faster than other methods. For road network extraction, we develop a method based on skeletonization, which results in complete and continuous road centerlines and boundaries. In our study area, several roads are disrupted and disconnected due to trees. We design a tree-constrained approach to fill road gaps and integrate road width estimated from a medial axis algorithm. Comparison to reference data shows that the proposed method is able to extract almost all existing roads in the study area, and even detects roads that were not present in the reference due to human errors. We conclude that our object extraction methods enable a complete automatic procedure, extracting more accurate building and road outlines from ALS point cloud data. This contributes to a higher automation readiness level for a faster and cheaper base map production.

Tree crown structural parameters are key inputs to studies spanning forest fire propagation, invasive species dynamics, avian habitat provision, and so on, but these parameters consistently are difficult to measure. While airborne laser scanning (ALS) provides uniform data and a consistent nadir perspective necessary for crown segmentation, the data characteristics of terrestrial laser scanning (TLS) make such crown segmentation efforts much more challenging. We present a data fusion approach to extract crown structure from TLS, by exploiting the complementary perspective of ALS. Multiple TLS point clouds are automatically registered to a single ALS point cloud by maximizing the normalized cross correlation between the global ALS canopy height model (CHM) and each of the local TLS CHMs through parameter optimization of a planar Euclidean transform. Per-tree canopy segmentation boundaries, which are reliably obtained from ALS, can then be adapted onto the more irregular TLS data. This is repeated for each TLS scan; the combined segmentation results from each registered TLS scan and the ALS data are fused into a single per-tree point cloud, from which canopy-level structural parameters readily can be extracted.

Ancient buildings carry important information, such as ancient politics, economy, culture, customs. However, with the course of time, ancient buildings are often damaged to different degrees, so the restoration of ancient buildings is of great importance from the historical point of view. There are three commonly used non-contact measurement methods, including UAV-based oblique photogrammetry, terrestrial laser scanning, and close-range photogrammetry. These methods can provide integrated three-dimensional surveys of open spaces, indoor and outdoor surfaces for ancient buildings. Theoretically, the combined use of the three measurement methods can provide 3D (three-dimensional) data support for the protection and repair of ancient buildings. However, data from the three methods need to be fused urgently, because if the image data is not used, it will lead to a lack of real and intuitive texture information, and if only image matching point clouds are used, their accuracy will be lower than that of terrestrial laser scanning point clouds, and it will also lead to a lack of digital expression for components with high indoor historical value of ancient buildings. Therefore, in this paper, a data fusion method is proposed to achieve multi-source and multi-scale 3D data fusion of indoor and outdoor surfaces. It takes the terrestrial laser point cloud as the core, and based on fine component texture features and building outline features, respectively, the ground close-range image matching point cloud and UAV oblique image matching point cloud are registered with the terrestrial laser point cloud. This method unifies the data from three measurements in the point cloud and realizes the high-precision fusion of these three data. Based on the indoor and outdoor 3D full-element point cloud formed by the proposed method, it will constitute a visual point cloud model in producing plans, elevations, sections, orthophotos, and other elements for the study of ancient buildings.