جستجوی مقالات مرتبط با کلیدواژه « Canopy height model » در نشریات گروه « جنگلداری »

Estimating forest tree structural attributes such as height and diameter at breast height (DBH) is crucial for understanding the structure and management of forest resources. One important method for estimating these parameters is the individual tree detection (ITD) method using appropriate remote sensing data, such as airborne LiDAR data. However, it should be noted that different ITD methods have various limitations and capabilities and react differently to changes in forest tree species and the vertical structure of the canopy.

This study presents a hybrid individual tree detection method that combines raster-based and point-based methods in a multi-scale framework to identify single trees from LiDAR data. In this method, tree crown scale levels are obtained from morphological filters in the canopy height model (CHM). Segmentation is then performed using a multi-scale method, and the results are merged. To better separate adjacent and understory trees, the point cloud inside the segments is analyzed using the probability density function, and tree crown segments are modified. After detecting single trees, DBH and height parameters were estimated using ground control data and extracted features from LiDAR data with machine learning algorithms, including random forest (RF), support vector machine (SVM), and cubist (CB), in the form of 10-fold nested cross-validation (10-fold NCV). The Boruta feature selection algorithm was used to identify the most important metrics based on the LiDAR point cloud, which played an effective role in improving the performance of machine learning algorithms. Due to limited access to LiDAR and ground data from Iran’s forests, this study uses the NEWFOR single tree detection benchmark dataset, collected from forests of the Alpine region with a combination of different tree species and vertical canopy structures.

Although understory trees cannot be extracted with the same accuracy as overstory trees, the results of this study showed that, on average, the developed multi-scale individual tree detection (MSITD) method detected 89% of the tree crowns in the highest height layer and the highest number of small overstory trees with a detection rate of 48% in the lowest height layer (2-5 meters). The analysis of the machine learning algorithms’ results in estimating forest structural attributes showed that, despite slight differences in performance, the SVM algorithm performed better than the RF and CB algorithms in estimating both height and DBH attributes. For the height attribute, the mean values of RMSE, rRMSE, and R2 in the SVM algorithm were 1.75 m, 9%, and 0.85, respectively. For the DBH attribute, the values obtained for RMSE, rRMSE, and R2 were 4.74 cm, 19%, and 0.78, respectively.

The evaluation of the results showed that the methods presented in this study for identifying single trees and estimating forest tree structural attributes have high potential for practical applications.

Canopy gap delineation is essential for achieving a better comprehension of forest structure. This study aims to (a) extract canopy gaps using UAV data and (b) compare the performance of different canopy gap extraction methods in a managed stand in the northeast of Iran. A canopy height model (CHM) was produced by subtracting LIDAR digital terrain model from the UAV digital surface model. CHM classification performs to extract gaps by thresholding CHM (fixed height and CHM slope and relative height thresholds) and object-based classification on the UAV CHM and orthophoto. Ground truth is produced in the point and polygon forms through field measurements and visual interpretation of the UAV orthophoto. The geometry of the canopy gaps (Area, perimeter, and shape complexity) was calculated. Finally, the point and polygon base accuracy of delineated gaps assess for each of the methods. Point accuracy assessment suggests that 60% CHM slope produces the highest overall accuracy and Kappa coefficient of 91.7% and 0.874, respectively. About area accuracy assessment, the best match between delineated gaps and ground truth polygons was achieved by using relative height and 60% CHM slope thresholds. The lowest mean errors of GSCI produced by 70% CHM slope (0.15). Moreover, object-based classification showed the lowest mean error of area (33.76 m2) and perimeter (16.80 m). In conclusion, while area accuracy is considered the best fit of the delineated gap's geometry is gained by the object-based classification.

Orthphoto mosaic, and digital elevation models (DEMs) that created from UAV imagery can be used to delineate tree crowns. The goal of this research is to compare two segmentation techniques in the estimation of crown diameter. In this regard, two successful flights were carried out in two different seasons (leaf-off and leaf-on). Then we generated accurate CHM through a photogrammetric workflow using DTM and DSM. We used invert watershed (IWS) and multiresolution segmentation (MRS) to detect tree crowns on CHM and orthophoto mosaic, respectively. To compare the estimates of mean crown diameter from UAV images with actual values, 95 trees were measured. The results of comparing the estimated and field measured values showed that all two algorithms effectively delineate tree crowns. The results of linear regression showed there is a high agreement between estimated and measured values, which were (R2=0.88) for MRS and (R2=0.92) for IWS. The best result was obtained using IWS techniques (RMSE= 7.02 % and MAE = 5.97 %). T-test results showed that there are no significant differences between the field measurement and IWS estimated values. Although the t-test result showed there are significant differences between the means of MRS estimated and measured crown diameters, but based on RMSE (8.74 %) and MAE (8.11 %) of the MRS technique, the error of crown diameter estimation was small and therefore acceptable. Finally, the results showed that this methodology, as an accurate and low-cost process, could be used to estimate mean tree crown diameter.