GTI method for wilt oak trees detection

Abstract

In this paper we proposed a method for detecting wilt oak trees. There were used images regarding Japanese Oak forests captured during summer and autumn of years 2007, 2008 and 2009, from airborne (with AISA view) and from low-altitude [1] (with VNIR HS Sensor). GTI method permits of dividing into 2 subsets (wilt and healthy), pixels of an image taking care also about autumnal characteristics of leaves, using reflectance graphs of each pixel in function of wavelength. There are 2 different strategies: finding a static threshold with many observations or running an algorithm (MCC) to find a dynamic threshold. The second approach is better for dark and subject to accentuated atmospheric effects images.