Automatic sampling and training method for wood-leaf classification based on tree terrestrial point cloud
This method offers an efficient and accurate solution for automating a fundamental step in forestry and biological research for plant point cloud data.
This paper proposes an automatic sampling and training method for classifying wood and leaf points in tree terrestrial point clouds. The method achieved an average correct classification rate of 0.9305 and a kappa coefficient of 0.7904, outperforming manual selection methods.
Terrestrial laser scanning technology provides an efficient and accuracy solution for acquiring three-dimensional information of plants. The leaf-wood classification of plant point cloud data is a fundamental step for some forestry and biological research. An automatic sampling and training method for classification was proposed based on tree point cloud data. The plane fitting method was used for selecting leaf sample points and wood sample points automatically, then two local features were calculated for training and classification by using support vector machine (SVM) algorithm. The point cloud data of ten trees were tested by using the proposed method and a manual selection method. The average correct classification rate and kappa coefficient are 0.9305 and 0.7904, respectively. The results show that the proposed method had better efficiency and accuracy comparing to the manual selection method.