REAL-TIME IMPLEMENTATION OF LWT BASED NOVEL IR AND VI FUSION ALGORITHM USING RASPBERRY PI PLATFORM

Abstract

One of the most important and active areas of image processing research is visible and thermallight image fusion. Moreover, real-time visible and thermal-light image fusion has been utilized in multiple kinds of applications such as surveillance devices, military applications, medical diagnosis, remote sensing, etc. Hence, this paper suggests a real-time application of visible and infrared (V-I) image fusion using lift wavelet transform (LWT) and implemented on the Raspberry Pi. The proposed morphological operations-based unsharp masking enhancement technique overcomes the low contrast issue of the fused image. Next, the LWT provides the good feature (smooth and detail) layers of visible image (VI) and infrared image (IRI) when compared to other transformations. Due to this, we have overcome the problem of spatial distortions in the fused image. Moreover, the proposed novel fusion techniques such as, mean-weighted fusion rule based on filters and max-weighted fusion rule based on filters generate the fused image with improved texture information and overcome the problem of edge information loss. The real-time application of the V-I image fusion is implemented through the portable hardware device Raspberry Pi. Finally, the experimental results show that the suggested framework has produced a fused image with improved visual quality, rich edge information, high contrast, low spatial distortions, and more texture information, when compared to the results of existing methodologies.