Accurate estimates of tree and forest biomass are essential for a wide range of applications. Automated treetop detection and tree crown discrimination using LiDAR data can greatly facilitate forest biomass estimation. Previous work has focused on homogenous or single-species forests, while few studies have focused on mixed forests. In this study, a new method for treetop detection is proposed in which the treetop is the cluster center of selected points rather than the highest point. Based on treetop detection, tree crowns are discriminated through comparison of three-dimensional shape signatures. The methods are first tested using simulated LiDAR point clouds for trees, and then applied to real LiDAR data from the Soquel Demonstration State Forest, California, USA. Results from both simulated and real LiDAR data show that the proposed method has great potential for effective detection of treetops and discrimination of tree crowns.

De nombreux travaux ont montré le potentiel de la télédétection parscanner laser aéroporté pour caractériser les massifs forestiers.Cependant, l'application aux forêts complexes de montagne reste encorepeu documentée. On se propose donc de tester les deux principalesméthodes permettant d'extraire des paramètres forestiers sur desdonnées acquises en zone montagneuse et de les adapter aux contraintesspéci fiques à cet environnement. En particulier on évaluera d'unepart l'apport conjoint de la régression à vecteurs de support et de laréduction de dimension pour l'estimation de paramètres de peuplement,et d'autre part l'intérêt d'un apprentissage non supervisé pour ladétection d'arbres. / Numerous studies have shown the potential of airborne laser scanningfor the mapping of forest resources. However, the application of thisremote sensing technique to complex forests encountered in mountainousareas requires further investigation. In this thesis, the two mainmethods used to derive forest information are tested with airbornelaser scanning data acquired in the French Alps, and adapted to theconstraints of mountainous environments. In particular,a framework for unsupervised training of treetop detection isproposed, and the performance of support vector regression combinedwith dimension reduction for forest stand parameters estimation isevaluated.