Agricultural fields classification in semi-arid central Tunisia using SPOT 7 image

This paper reports on classification methods applied and tested for land use classification in a semi-arid environment. Our study, conducted on two irrigated sites located in the Kairouan region, the largest irrigated region in Tunisia, compared Support Vector Machine (SVM) and Maximum Likelihood classification of SPOT-7 data. To produce a per-field classification a Mean-Shift Segmentation has been performed on the pansharpened SPOT-7 images. A field survey has been conducted. Accuracy assessment was done to evaluate the performance of the proposed using collect ground truth data on land use and extend of all the agricultural fields within the study areas obtained through filed survey.

[1]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Dorin Comaniciu,et al.  Robust analysis of feature spaces: color image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  David Meyer,et al.  Support Vector Machines ∗ The Interface to libsvm in package e1071 , 2001 .

[4]  Mitchel Alioscha-Pérez,et al.  Efficient Learning of Spatial Patterns with Multi-Scale Conditional Random Fields for Region-Based Classification , 2014, Remote. Sens..

[5]  Wei Zheng,et al.  Classification of colonic tissues using near-infrared Raman spectroscopy and support vector machines. , 2008, International journal of oncology.

[6]  Xiaojun Yang,et al.  Parameterizing Support Vector Machines for Land Cover Classification , 2011 .

[7]  Nathan S. Netanyahu,et al.  Mean shift-based clustering of remotely sensed data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[8]  Hiroaki Kuze,et al.  Performance Analyzing of High Resolution Pan-sharpening Techniques: Increasing Image Quality for Classification using Supervised Kernel Support Vector Machine , 2011 .

[9]  Shridhar D. Jawak,et al.  A Comprehensive Evaluation of PAN-Sharpening Algorithms Coupled with Resampling Methods for Image Synthesis of Very High Resolution Remotely Sensed Satellite Data , 2013 .