Feature Fusion Algorithm Based On DT-CWT

Approximate shift invariance, good directional selectivity, computational efficiency properties of DT-CWT make it a good candidate for representing texture features. In this paper, a method is proposed which efficiently uses the properties of DT-CWT in finding the directional and spatial/frequency characteristics of the patterns and classifying different texture patterns in terms of these characteristics. The arithmetic of the feature data fusion based D-S evidence theory is adopted to fuse the multisource DT-CWT texture of the object. Experimental results show that the proposed feature extraction and the feature data fusion based D-S evidence theory is effective in object detection in multisource low resolution remote-sensing images.