Multi-source image fusion method

Abstract

The invention discloses a multi-source image fusion method. The method comprises the following steps of: in an early feature extraction stage, combining wavelet kernel-based support transform with anti-aliasing contourlet, wherein on one hand, direction information which cannot be extracted by the support transform is increased, and on the other hand, an aliasing phenomenon generated in contourlet transform is eliminated; and in an image fusion stage, performing fusion judgment on low frequency signals of each fused image by establishing a high frequency judgment device by adopting a pulse coupled neural network, and performing the fusion judgment on high frequency signals of each fused image by adopting an absolute value maximum selection rule. Therefore, effective fusion of high and low frequency signals is realized.

Description

technical field [0001] The invention relates to the field of image fusion, in particular to a multi-source image fusion method. Background technique [0002] The processing of image fusion in the prior art is usually at the pixel level, feature level, and decision-making level. Pixel-level image fusion is mainly for the initial image data, and its purpose is mainly image enhancement, image segmentation and image classification, so as to provide better input information for manual interpretation of images or further feature-level fusion, pixel-level image fusion, relying on Due to the sensitivity of sensor sensing devices, high-resolution sensors are required for long-distance images; feature-level image fusion refers to the process of extracting feature information from each sensor image, and performing comprehensive analysis and processing. The extracted feature information is The sufficient representation or sufficient statistics of pixel information. Typical feature info...

AI Technical Summary

Problems solved by technology

Pixel-level image fusion is mainly for the initial image data, and its purpose is mainly image enhancement, image segmentation and image classification, so as to provide better input information for manual interpretation of images or further feature-level fusion, pixel-level image fusion, relying on Due to the sensitivity of sensor sensing devices, high-resolution sensors are required for long-distance images; feature-level image fusion refers to the process of extracting feature information from each sensor image, and performing comprehensive analysis and processing. The extracted feature information is The sufficient representation or sufficient statistics of pixel information. Typical feature information includes edges, shapes, contours, corners, textures, similar brightness regions, etc. Feature fusion is not all image information, and often ignores the image while expressing features. Overall; decision-level image fusion is the process of logical or statistical reasoning of information from multiple images. The establishment of a decision function often requires a large number of samples for long-term decision function verification operations. Decision-level fusion for images requires Takes a lot of time and uses a lot of memory

Images