• Time: Feb, 5th, 14:30
  
• Place: Meeting Room num 1, 13th floor, CASIA
  
• Title: “Wavelet based analysis of high resolution remote sensing

images. Application to texture orientation, change detection and segmentation”

• Abstract:
  

This talk is interested with the processing of very high resolution remote sensing images based on texture analysis. With the development of Very High Spatial Resolution sensors, it is now possible to identify textures inside an ‘entity’ (like an agricultural parcel for instance). These entities, resulting from a combination of items, could be characterized by their spatial arrangement. In this talk, we investigate the contribution of wavelet based analysis to image classification, change detection and segmentation. At first, we propose a method to identify vineyards as well as estimate row orientation of each plot. The key idea is to find the rotation angle that best concentrates energy in a given direction of a wavelet decomposition. Secondly, we present an application of change detection. Our approach consists in defining a measure of the observed change which is based on the distribution of the wavelet coefficients of 2 different images. Lastly, we propose a method for unsupervised segmentation which requires few input parameters. The originality of the approach consists in jointly dealing with watershed segmentation and wavelet decomposition.

• Reference:

A. Lefebvre, T. Corpetti, L. Hubert-Moy. A measure for change detection in very high resolution remote sensing images based on texture analysis. In IEEE International Conference on Image Processing, ICIP ‘09, complete references to appear, Cairo, Egypt, November 2009.