An Image Fusion Method Based on Gradient Domain Oriented Filtering and Improved pcnn

Abstract

The invention relates to an image fusion method based on gradient domain guided filtering and improved PCNN, and belongs to the field of image processing. Firstly, the source image is detected according to the three complementary image features of image structure, sharpness and contrast saliency, and an initial decision graph is obtained. This decision graph model can effectively and accurately measure the saliency of features, greatly improving the method's performance. Then, in order to make full use of the spatial consistency of the image and suppress the block effect in the image at the same time, the gradient domain-oriented filtering is used to optimize the initial decision graph, and the optimized decision graph is obtained; secondly, the optimized decision graph and the image to be fused are weighted operation to obtain the optimal decision map; finally, in order to make the fused image more in line with the visual characteristics of the human eye, the improved PCNN is used to process the optimized decision map to obtain the final fusion map. The invention solves the problems of complex method, low efficiency and excessive dependence on manual design of the traditional image fusion method, and at the same time, the fusion quality of the image is further improved.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a multi-source image fusion method, which can be applied to various civil image processing systems. Background technique [0002] Image fusion refers to the process of merging the important information of two or more multi-source images using a certain technology. As an important part of image fusion technology, the image fusion of infrared and visible light images has higher definition, greater information, more comprehensive information about targets and scenes, and is more suitable for human visual perception. It has been used in military, industrial and civil applications. application in other fields. In the civil field, the application of infrared and visible light fusion technology in the car night vision system can improve the safety of the car in severe weather conditions such as thick fog and heavy rain. [0003] In recent years, due to the related achievements of deep ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of halo artifacts and low contrast in the fused image obtained by the fusion method, we make full use of the edge smoothing and edge gradient preservation characteristics of the guided filter and the (pulse coupled neural network, PCNN) PCNN model's characteristics that are conducive to visual perception. A fusion method based on gradient domain guided filter and improved PCNN (GDGF-PCNN) is proposed, which can better preserve the edge, texture and detail information of the image, and avoid the target edge Halo artifact phenomenon, and more conducive to visual observation, to achieve a very good fusion effect

Images