Classification of Crops from remotely sensed Images: A review

摘要

Crops identification from remotely sensed images is essential due to use of remote sensing images as an input for agricultural & economic planning by government & private agencies. Available satellite sensors like AWIFS, LISS (IRS series), SPOT 5 and also LANDSAT,MODIS are good sources of multispectral data with different spatial resolutions & Hyperion, Hy-Map, AVIRIS are good sources of hyper-spectral data. The methodology for this work is selection of satellite data; use of suitable method for classification and checking the accuracy.From last four decades various researchers have been working on these issues up to some extent but still some challenges are there like multiple crops identification, differentiation of crops of same type this paper provides an overall review of the work done in this important area. Multispectral & hyper-spectral images contain spectral information about the crops.Good soft computing & analysis skills are required to classify & identify the class of interest from that datasets.Various researchers have been worked with supervised & unsupervised classification along with hard classifiers as well as soft computing techniques like fuzzy C mean, support vector machine & they have been found different results with different datasets