近年來，影像分類方法逐漸由像元式發展為物件式分類，其藉由像元間之空間關係建立影像物件，並納入影像物件之光譜、形狀、及紋理等物件特徵作為分類依據，進而提高影像分類之成效。本研究嘗試將二維物件式影像分類架構延伸至三維光達點雲分類，期望藉由物件分類之觀念提升光達資料自動分類目標物之能力。本研究首先將光達點雲資料自動分割為獨立的三維點雲物件，接續利用自行設計之物件特徵進行特徵萃取，最後以物件特徵自動化分類點雲。實驗中分別以空載及地面光達資料進行測試。在空載光達部份，研究中選用結構物、樹及車輛作為分類標的，於整體分類精度與Kappa值分別達到98.40 % 與0.9638 之分類成效；在地面光達部份，本研究選用建物、小型結構物、樹、樹幹與樹叢等類別作為分類目標，整體分類精度與Kappa值分別為84.28% 與0.7221。由實驗結果可知，以物件為基礎之光達點雲分類，能藉由描述點群具有的空間特性輔助點雲資料之判釋，不僅有效提升分類成果之完整性，在分類品質上亦能有不錯的表現。

Recently, image classification methods have transferred from pixel-based to object-based. Under the consideration of specific spatial features of objects, such as spectral, shape, texture, or the subordinative relations among them, object-based image analysis (OBIA) could improve the efficiency of image classification. In order to raise the capability of automatic recognition of land features from LiDAR data, 2D object-based classification method is extended for 3D point cloud classification of LiDAR data in this study. First, point cloud is segmented to independent 3D objects by various methods. Second, object features designed by this study are calculated. At last, the point clouds are classified automatically according to the object features . This study applies airborne LiDAR and ground-based LiDAR to automatic land feature classification. On the part of airborne LiDAR, structures, trees and cars were chosen to be the targets of classification. The overall accuracy and kappa value ran up to 98.40 % and 0.9638 respectively. On the other hand, on the part of ground-based LiDAR, buildings, small structures, trees, trunks and groves were chosen to be the targets. The overall accuracy and kappa value were 84.28 % and 0.7221 respectively. The results show that utilizing the object-based concept to classify LiDAR point cloud can give assistance to point cloud recognition by means of depicting the spatial characters of these objects. The classification results then, therefore, improve not only the completeness, but also the quality.