Tree species classification using deep learning and RGB optical images obtained by an unmanned aerial vehicle
- PDF / 1,710,640 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 28 Downloads / 191 Views
ORIGINAL PAPER
Tree species classification using deep learning and RGB optical images obtained by an unmanned aerial vehicle Chen Zhang1,2,3 · Kai Xia1,2,3 · Hailin Feng1,2,3 · Yinhui Yang1,2,3 · Xiaochen Du1,2,3
Received: 8 January 2020 / Accepted: 20 August 2020 © Northeast Forestry University 2020
Abstract The diversity of tree species and the complexity of land use in cities create challenging issues for tree species classification. The combination of deep learning methods and RGB optical images obtained by unmanned aerial vehicles (UAVs) provides a new research direction for urban tree species classification. We proposed an RGB optical image dataset with 10 urban tree species, termed TCC10, which is a benchmark for tree canopy classification (TCC). TCC10 dataset contains two types of data: tree canopy images with simple backgrounds and those with complex backgrounds. The objective was to examine the possibility of using deep learning methods (AlexNet, VGG16, and ResNet-50) for individual tree species classification.
Project funding: This study was supported by Joint Fund of Natural Science Foundation of Zhejiang-Qingshanhu Science and Technology City (Grant No. LQY18C160002), National Natural Science Foundation of China (Grant No. U1809208), Zhejiang Science and Technology Key R&D Program Funded Project (Grant No. 2018C02013), Natural Science Foundation of Zhejiang Province (Grant No. LQ20F020005). The online version is available at http://www.springerlink.com. Corresponding editor: Yu Lei. * Kai Xia [email protected] 1
School of Information Engineering, Zhejiang A&F University, Hangzhou 311300, People’s Republic of China
2
Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, People’s Republic of China
3
Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology, Hangzhou 311300, People’s Republic of China
The results of convolutional neural networks (CNNs) were compared with those of K-nearest neighbor (KNN) and BP neural network. Our results demonstrated: (1) ResNet-50 achieved an overall accuracy (OA) of 92.6% and a kappa coefficient of 0.91 for tree species classification on TCC10 and outperformed AlexNet and VGG-16. (2) The classification accuracy of KNN and BP neural network was less than 70%, while the accuracy of CNNs was relatively higher. (3) The classification accuracy of tree canopy images with complex backgrounds was lower than that for images with simple backgrounds. For the deciduous tree species in TCC10, the classification accuracy of ResNet-50 was higher in summer than that in autumn. Therefore, the deep learning is effective for urban tree species classification using RGB optical images. Keywords Urban forest · Unmanned aerial vehicle (UAV) · Convolutional neural network · Tree species classification · RGB optical images
Introduction In urban ecosystems, trees provide several ecological services such as climate regulation, air quality improvement an
Data Loading...
