Infrared image and visible light image fusion method based on early visual information processing

Abstract

The invention discloses an infrared image and visible light image fusion method based on early visual information processing. The method comprises the following steps: S1, carrying out dynamic receptive field processing of On central neurons and Off central neurons; s2, obtaining a fusion image A and a fusion image B: fusing the On central neuron response of the visible light image, the Off central neuron response of the infrared image and the original visible light image to obtain the image A; and fusing the On central neuron response of the infrared image, the Off central neuron response ofthe visible light image and the original infrared image to obtain an image B; and S3, adding the fused image A and B to obtain a final fusion result. Salient target information in the infrared image and background information in the visible light image can be effectively fused, and more effective features are provided for computer vision tasks under the night vision conditions of subsequent high-value target detection and recognition and the like.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, and relates to the fusion of infrared images and visible light images, in particular to an infrared image and visible light image fusion method based on early visual information processing. Background technique [0002] The fusion of infrared images and visible light images is an important image enhancement technology, which fuses the features of different bands together to obtain an image with more information. Visible light images always show the background in great detail, while infrared images clearly show a potentially camouflaged target for visual detection and identification. The fusion of visible and infrared images can reveal more information than a single image. For decades, the problem of image fusion has been developed under different schemes, among which representative technical routes include methods based on multi-scale feature decomposition, methods b...

AI Technical Summary

Problems solved by technology

References: Waxman AM, Gove A N, Fay D A, et al. Color night vision: opponent processing in the fusion of visible and IR imagery [J]. Neural Networks, 1997, 10(1): 1-6., but Waxman et al. The image fused by the human method loses part of the information of the source image, and the color performance of the image is not natural enough, so it is difficult to give a satisfactory result in terms of visual effects

Images