Analysis of Time-Series Spectral Index Data to Enhance Crop Identification Over a Mediterranean Rural Landscape

Spectral index time series can provide valuable phenological information into the classification process for the precise crop mapping, in order to reduce misclassification rates associated with low interclass and high intraclass spectral variability. Stochastic hidden Markov models (HMMs) are efficient yet computationally demanding classification approach which can simulate crop dynamics, exploiting the spectral information of their phenological states and the relations between these states. This letter aims to present a methodology which achieves accurate classification results while maintaining a low computational cost. A classification framework based on HMMs was developed, and different spectral indices were generated from the time series of Landsat ETM+ and RapidEye imagery, for modeling crop vegetation dynamics over a Mediterranean rural area, with high spatiotemporal crop heterogeneity. To further improve the HMMs indices classification, separability analysis and two different decision fusion strategies were tested. The assessment of the classification accuracy, along with an evaluation of the computational cost, indicated that the green-red vegetation index produced the most favorable results among the individual spectral indices. Although the decision fusion based on an integration of a reliability factor increased the overall accuracy by 3.1%, this came at the cost of computational time, compared to the separability analysis model which required less processing time.