Abstract
Abstract. Our work addresses the problem of classifying tree species from mobile LiDAR data. The work is a two step-wise strategy, including tree segmentation and tree species classification. In the tree segmentation step, a voxel-based upward growing filtering is proposed to remove terrain points from the mobile laser scanning data. Then, individual trees are segmented via a Euclidean distance clustering approach and Voxel-based Normalized Cut (VNCut) segmentation approach. In the tree species classification, a voxel-based 3D convolutional neural network (3D-CNN) model is developed based on intensity information. A road section data acquired by a RIEGL VMX-450 system are selected for evaluating the proposed tree classification method. Qualitative analysis shows that our algorithm achieves a good performance.
Highlights
In the case of urban areas, tree species classification is gaining increasing attention for safety studies, noise modelling, and environmental and ecological analysis because trees play a critical role in urban ecosystems for the maintenance of environmental quality, aesthetic beauty of urban landscape, and social service for inhabitants
The proposed method is a three step-wise strategy: (1) tree segmentation, which includes the separation of terrain points and non-terrain points via a voxel-based upward growing filtering, individual tree segmentation based on a Euclidean distance clustering approach and a voxel-based Normalized Cut approach, and (2) tree species classification based on 3D- CNN
To effectively conduct tree species classification on the segmented individual trees, we develop a 3D convolutional neural network (3D-CNN) model
Summary
In the case of urban areas, tree species classification is gaining increasing attention for safety studies, noise modelling, and environmental and ecological analysis because trees play a critical role in urban ecosystems for the maintenance of environmental quality, aesthetic beauty of urban landscape, and social service for inhabitants. Li et al (2016) developed a dual growing method for extracting individual trees from mobile LiDAR data. Guan et al (2014) proposed a Deep Boltzmann Machines (DBMs) based tree classification method, which classify ten tree species from the tree waveform representation, reflecting tree geometric structures in mobile LiDAR data. We develop an effective processing workflow for individual tree detection and species classification using mobile LiDAR data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have