a b s t r a c tThis work proposes a segmentation method that isolates individual tree crowns using airborne LiDAR data. The proposed approach captures the topological structure of the forest in hierarchical data structures, quantifies topological relationships of tree crown components in a weighted graph, and finally partitions the graph to separate individual tree crowns. This novel bottom-up segmentation strategy is based on several quantifiable cohesion criteria that act as a measure of belief on weather two crown components belong to the same tree. An added flexibility is provided by a set of weights that balance the contribution of each criterion, thus effectively allowing the algorithm to adjust to different forest structures.The LiDAR data used for testing was acquired in Louisiana, inside the Clear Creek Wildlife management area with a RIEGL LMS-Q680i airborne laser scanner. Three 1 ha forest areas of different conditions and increasing complexity were segmented and assessed in terms of an accuracy index (AI) accounting for both omission and commission. The three areas were segmented under optimum parameterization with an AI of 98.98%, 92.25% and 74.75% respectively, revealing the excellent potential of the algorithm. When segmentation parameters are optimized locally using plot references the AI drops to 98.23%, 89.24%, and 68.04% on average with plot sizes of 1000 m 2 and 97.68%, 87.78% and 61.1% on average with plot sizes of 500 m 2 .More than introducing a segmentation algorithm, this paper proposes a powerful framework featuring flexibility to support a series of segmentation methods including some of those recurring in the tree segmentation literature. The segmentation method may extend its applications to any data of topological nature or data that has a topological equivalent.

A plethora of information contained in full-waveform (FW) Light Detection and Ranging (LiDAR) data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM) using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW) algorithms. Subsequently, the Random forests (RF) and Conditional inference forests (CF) models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak) and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR) using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF) and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR) and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due to the similar characteristics of blue oak and interior live oak. Uncertainty estimates from the BMLR method compensate for this downside by providing classification results in a probabilistic sense and rendering users with more confidence in interpreting and applying classification results to real-world tasks such as forest inventory. Overall, this study recommends the CF method for feature selection and suggests that BMLR could be a superior alternative to classical machining learning methods.

Abstract:The estimation of tree biomass and the products that can be obtained from a tree stem have focused forest research for more than two centuries. Traditionally, measurements of the entire tree bole were expensive or inaccurate, even when sophisticated remote sensing techniques were used. We propose a fast and accurate procedure for measuring diameters along the merchantable portion of the stem at any given height. The procedure uses unreferenced photos captured with a consumer grade camera. A photogrammetric point cloud (PPC) is produced from the acquired images using structure from motion, which is a computer vision range imaging technique. A set of 18 loblolly pines (Pinus taeda Lindl.) from east Louisiana, USA, were photographed, subsequently cut, and the diameter measured every meter. The same diameters were measured on the point cloud with AutoCAD Civil3D. The ground point cloud reconstruction provided useful information for at most 13 m along the stem. The PPC measurements are biased, overestimating real diameters by 17.

This paper evaluates the effects of post-communist economic transition on forest resources in Romania. Using data from 1993 and 2003, our research describes a sample of forested landscape units based on seven environmental attributes. These attributes were then compared to four technical attributes associated with forest management planning. The comparative analysis revealed that many forest stand attributes were significantly affected between 1993 and 2003, potentially by the forest ownership change, while most of the forest management attributes were not. Our results suggest that a dramatic change in forestry legislation does not necessarily result in a dramatic change in the descriptive characteristics of forest resources in that jurisdiction but, rather, in the structure of the forest.Key words: economic transition, Eastern Europe, forestry, policy, non-parametric statistics RÉSUMÉCet article évalue les effets de la transition économique post-communiste sur les ressources forestières de la Roumanie. À partir des données de 1993 et de 2003, nos recherches décrivent un échantillon des unités du paysage forestier selon sept caractéristiques environnementales. Ces caractéristiques ont été comparées par la suite à quatre caractéristiques techniques associées à la planification de l'aménagement forestier. L'analyse comparative a révélé que plusieurs caractéris-tiques des peuplements forestiers ont été modifiées de façon significative entre 1993 et 2003, probablement par suite du changement de tenure, tandis que la plupart des caractéristiques d'aménagement forestier ne l'ont pas été. Nos résultats suggèrent qu'un changement drastique de la législation forestière n'entraîne pas nécessairement un changement radical des caractéristiques descriptives des ressources forestières dans le cas de cette juridiction, mais plutôt dans la structure de la forêt.