Extraction of the Vegetation Information Based on Temporal and Spectrum Information

This paper chooses 85 Ground Truths which include different types of features in ETM, using the ETM data in 2002 and geographic information of vegetation. The NDVI time sequence curves of the Ground Truths were obtained by MODIS data of Shaanxi province in 2003. Decision tree classification method combined with NDVI time sequence curves of Ground Truths was realized the classification of vegetation which based on temporal and spectrum information in Shanxi province. Finally, confusion matrix and Kappa coefficient were used to evaluate the accuracy of the classification. Results showed that the method was superior to the traditional classification methods, and results and other findings are consistent.