Search

Classifying tree species from point clouds acquired by light detection and ranging (LiDAR) scanning systems is important in many applications, including remote sensing, virtual reality, and forestry inventory. Compared with terrestrial laser scanning systems, airborne laser scanning (ALS) systems can acquire large-scale tree point clouds from only a single scan. However, ALS point clouds have the disadvantages of low density, uneven distribution, and unclear branch structure, making the classification of tree species from ALS point clouds a challenging task. Recently, deep learning-based classification approaches, such as PointNet++, which can operate directly on 3-D point sets, have been intensively studied in scene classification. However, the classification precision of learning-based approaches for point clouds relies on point coordinates and features, such as normals. Unlike the face normals of regular objects, trees have complex branch structures and detailed leaves, which are difficult to capture using ALS systems. Hence, it might be inappropriate to use the normals of ALS tree points for classification. In this letter, we propose a novel convex hull-based feature descriptor for tree species classification using the deep learning network PointNet++. To evaluate the effectiveness of our approach, three additional feature descriptors (normal descriptor, alpha shape-based descriptor, and covariance descriptor) are also investigated with PointNet++. The results show that the convex hull-based feature descriptor can achieve 86.6% overall accuracy in tree species classification, which is notably higher than the other three descriptors.