Visible/IR Battle Field Image Registration using Local Hausdorff Distance

Feature inconsistency and low contract and noise in the infrared image background consist of the principle difficulty in the IR/Visible battle field image registration. Feature-based approaches are more powerful and versatile to process poor quality IR images. Multi-scale hierarchical edge detection and edge focusing and salience measure are used in the feature horizon extraction. The common features extracted from images of two modalities can be still different in detail. Therefore, the transformation space match methods with the Hausdorff distance measure is more suitable than the direct feature matching methods. We have introduced image quadtree partition technique to the Hausdorff distance matching, that dramatically reduces the size of the search space. Image registration of real world visible/IR images of battle fields is shown.