Feasibility study of forest wood-boring pest detection base on hyperspectral LiDAR

Abstract

ABSTRACT Forest pests impose significant threats to tree productivity and ecosystem stability. Most studies focussed on foliage water, tree defoliate and mortality, which lag behind pest outbreak. To address this issue, we developed hyperspectral LiDAR (HSL) system based on an acousto-optic tunable filter (AOTF) to examine the echo intensity of tree trunks. First, we demonstrated the echo power of the cylindrical surface is approximately equivalent to that of the plate surface within 60° incidence angle, which provide the theoretical reference for trunk surface echo intensity calibration with a white panel. Second, we propose a two-step method to detect the attacked parts from barks. The first step is rapid pest detection conducted by the echo intensity ratio of damaged area and normal area. While the ratio is around one, the second step is pest detection based on support vector machine classifier with reflectance. When the reflectivity of five spectral channels is used as input parameters, 100% rapid detection accuracy of damage area is achieved. We also use the radiance under seven channels to achieve 100% classification of tree species and attack features. The results show that this HSL is effective in wood-boring pest detection and contributes to forest applications.