Airborne LiDAR point clouds classification is meaningful for various applications. In this paper, an object-based analysis method is proposed to classify the point clouds in human settlements. In the process of classi...
详细信息
Airborne LiDAR point clouds classification is meaningful for various applications. In this paper, an object-based analysis method is proposed to classify the point clouds in human settlements. In the process of classification, surface growing algorithm is employed to segment the point clouds into different clusters first. The above segmentation is helpful to derive useful features such as area/size, position, orientation, proportion of multiple echoes, height jump between adjacent segments, topological relationship of neighboring segments etc. At last, rule-based classification is performed on the segmented point clouds. Two datasets are used to test the above method. The results suggest that our method will produce the overall classification accuracy larger than 93% and the Kappa coefficient larger than 0.89, which indicates the promising applications.
暂无评论