Extraction of Tree Crowns Damaged by Tsai Liu Via Spectral-spatial Classification Using UAV-based Hyperspectral Images

Background: Tree crown extraction is an important research topic in forest resource monitoring. In particular, it is a prerequisite for disease detection and mapping the degree of damage caused by forest pests. Unmanned aerial vehicle (UAV)-based hyperspectral imaging is effective for surveying and monitoring forest health. This article proposes a spectral-spatial classification framework that uses UAV-based hyperspectral images and combines a support vector machine (SVM) with an edge-preserving filter (EPF) for completing classification more finely to automatically extract tree crowns damaged by Tsai Liu () in Jianping county of Liaoning province, China.

Results: Experiments were conducted using UAV-based hyperspectral images, and the accuracy of the results was assessed using the mean structure similarity index (MSSIM), the overall accuracy (OA), kappa coefficient, and classification accuracy of damaged . Optimized results showed that the OA of the spectral-spatial classification method can reach 93.17%, and the extraction accuracy of damaged tree crowns is 7.50-9.74% higher than that achieved using the traditional SVM classifier.

Conclusion: This study is one of only a few in which a UAV-based hyperspectral image has been used to extract tree crowns damaged by . Moreover, the proposed classification method can effectively extract damaged tree crowns; hence, it can serve as a reference for future studies on both forest health monitoring and larger-scale forest pest and disease assessment.