Segmentation of Built up area from SPOT 5 multispectral satellite images

Segmentation of Built up area from a satellite image is an initial step for a variety of applications. In this paper we propose a novel approach for segmenting built up area mask from SPOT 5 multi spectral satellite images with 2.5 meter resolution. The proposed algorithm uses information theoretic and multi resolution techniques for segmentation. The results of proposed algorithm demonstrated it's effectiveness for the segmentation of built up area from large sized satellite images. The validation results for segmentation using sensitivity, positive predictive value and dice coefficient show a significant improvement over supervised classification results of a commercial software. Also it was observed that the wavelet transform produced better results than the scale space technique when used in the proposed algorithm for multi resolution decomposition.

[1]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[2]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[3]  Y. Iikura,et al.  Pyramid linking for satellite image classification , 1995, 1995 International Geoscience and Remote Sensing Symposium, IGARSS '95. Quantitative Remote Sensing for Science and Applications.

[4]  D. Lasselin,et al.  Evaluation of the geographic information potential of SPOT5 , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[5]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

[6]  Silvana G. Dellepiane,et al.  Segmentation of coherence maps for flood damage assessment , 2005, IEEE International Conference on Image Processing 2005.

[7]  M. Benjelloun,et al.  A k-Means Clustering Algorithm Initialization for Unsupervised Statistical Satellite Image Segmentation , 2006, 2006 1ST IEEE International Conference on E-Learning in Industrial Electronics.

[8]  Ashok Samal,et al.  An Automatic Bridge Detection Technique for Multispectral Images , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Chen Zheng,et al.  A comparative study of pixel level and region level classification of land use types using QuickBird imagery , 2010, 2010 Second IITA International Conference on Geoscience and Remote Sensing.

[10]  Qingsheng Liu,et al.  Using SPOT 5 high spatial resolution image to detect vegetation patches at Gudong oil field , 2011, 2011 Seventh International Conference on Natural Computation.

[11]  Derya Maktav,et al.  Land use/land cover classification for applied urban planning - the challenge of automation , 2011, 2011 Joint Urban Remote Sensing Event.

[12]  Rehna Kalam,et al.  Enhancing K-Means Algorithm for Image Segmentation , 2011, 2011 International Conference on Process Automation, Control and Computing.

[13]  M. Sharmila,et al.  Automatic road extraction using high resolution satellite images based on level set and mean shift methods , 2013, 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT).