Study Of Multi-sensor Image Fusion Based On Frame Decomposition

Multi-sensor image fusion is an important branch of multi-sensor information fusion, and is a technique to combine information from multiple source images of the same scene/object. Multiple source images of the same scene are usually from various sensors or gained by the same sensor in the different time. By using multi-sensor, the fused image overcomes the limitation and otherness of single sensor image in geometry, spectrum, space resolution, etc. As a result of this processing, the fused image contains a more complete and accurate description of the scene than the individual source image, and is more useful for human and machine perception or further image processing tasks such as object recognition and feature extraction. In adverse environmental conditions (such as smoke, fog, rain, low light, motion) or when one imaging sensor may not provide enough information needed for recognition or scene interpretation, we can get an improved image through image fusion. Now multi-sensor image fusion is widely applied in some fields, such as medicine, remote sensing, computer vision, weather forecast, automatic object detection, etc.This thesis focuses on the problem of multi-sensor image fusion, and has pertinence and usefulness. The paper researches the following contents:Firstly, we study the algorithm, realization and performance of simple image fusion method, image fusion method based on Laplacian pyramid decomposition, and image fusion method based on wavelet decomposition.Secondly, wavelet frame can obtain compactness, smoothness and symmetry simultaneously, while orthogonal wavelet cannot, and has the better stability to the reconstruction of signal and the robustness to noise. A novel approach for image fusion based on frame decomposition is proposed and has successfully used in image fusion.Thirdly, the fusion rules and fusion operators are very important for image fusion. Different fusion rules are studied in this paper, and a novel region-based measure fusion rule is given.Fourthly, This paper gives the image fusion tests of various methods. Using different fusion rules, this paper compares the performance of two fusion methods based on wavelet decomposition. The detailed comparison indicates that the new approach has an advantage over the orthogonal wavelet decomposition for image fusion.