Neural Network Approach for Training Models for Multispectral Images
Dragan Stevic., Igor Hut., Nikola Dojcinovic., Jugoslav Jokovic University of Pristina, Kneza Miloša 7 38220 Kosovska Mitrovica, Serbia., University of Belgrade,Kraljice Marije 16, 11120 Belgrade, Serbia., MySkin, Inc, Kosovska 17, 11000 Belgrade, Serbia., University of Nis, Aleksandra Medvedeva 14 18000 Niš, Serbia
Abstract: In this paper we have presented the neural network-based approach for LANDSAT vegetation classification with multispectral image set. We have given many training models which came out with the measures such as accuracy and a good framework.
Keywords: Remote Sensing, Neural Networks, Multispectral Images Neural Network Approach for Training Models for Multispectral Images
[1] Walthall, C. (2004) A comparison of empirical and neural network approaches for estimating corn and soybean leaf area index from Landsat ETM+ imagery. Remote Sensing of Environment, 92, 465–474 [DOI: 10.1016/j.rse.2004.06.003]. [2] Govender, M., Chetty, K. & Bulcock, H. (2007) A review of hyperspectral remote sensing and its application in vegetation and water resource studies. Water SA, 33, 145–152 [DOI: 10.4314/wsa.v33i2.49049]. [3] Cochrane, M.A. (2000). Using Vegetation Re Ectance Variability for Species Level Classication of Hyperspectral Data, Vol. 21, pp. 2075–2087. [4] No title [Online]. Available: geo.arc.nasa.gov/sge/landsat/l7.html. [5] N Aeronautics. Landsat 7 Science Data Users Handbook Landsat 7 Science Data Users Handbook (1972). [6] Chen, C.H. & Peter Ho, P.-G. (2008) Statistical pattern recognition in remote sensing. Pattern Recognition, 41, 2731–2741 [DOI: 10.1016/j.patcog.2008.04.013]. [7] Kolios, S. & Stylios, C.D. (2013) Identification of land cover/land use changes in the greater area of the Preveza peninsula in Greece using Landsat satellite data. Applied Geography, 40, 150–160 [DOI: 10.1016/j.apgeog.2013.02.005].
