Automatic difference vegetation index generator for spider mite-infested cotton detection using hyperspectral reflectance

Abstract: Spider mites are one of the main pest stresses on cotton, which cause serious economic losses in cotton production in Xinjiang Region.  This article explored the potential of ground based hyperspectral reflectance for mite-infestation detection.  Also, the possibility to reduce bands and simplify analyzing was studied.  In this regard, an automatic difference vegetable index was researched, which required only two bands and a simple subtraction operation.  A multi-objective genetic algorithm was proposed for band selection, and its performance was compared with the mainstream machine learning methods.  Experimental results showed that the proposed approach outperformed others in accuracy with less complexity.  All the results revealed that the proposed method has potential in mite- infestation detection in agricultural applications. Keywords: hyperspectral, spider mite, genetic algorithm, band selection DOI:  10.33440/j.ijpaa.20200302.88 Citation: Huang H S, Deng J Z, Lan Y B, Yang A Q, Jiang Y, Suo G Y, Chen P C.  Automatic difference vegetation index generator for spider mite- infested cotton detection using hyperspectral reflectance.  Int J Precis Agric Aviat, 2020; 3(2): 83–88.