An optimal weighted averaging fusion strategy for thermal and visible images using dual tree discrete wavelet transform and self tunning particle swarm optimization

Abstract

Listen

Translate article

Image fusion plays a vital role in providing better visualization of image data. In this paper, we propose a new algorithm that optimally combines information from thermal images with a visual image of the same scene to create a single comprehensive fused image. In this work, an improved version of particle swarm optimization alogithm is proposed to optimally combine the thermal and visible images. The proposed algorithm is named self tunning particle swarm optimization (STPSO). Because of the importance of the fusion rule, a weighted averaging fusion rule is formulated that uses optimal weights resulting from STPSO for the fusion of both high frequency and low frequency coefficients obtained by applying Dual Tree Discrete Wavelet Transform (DT-DWT). The objective function in STPSO is formulated with the twin objectives of maximizing the Entropy and minimizing the Root Mean Square Error (RMSE), which differentiates our work from existing fusion techniques. The efficiency of our fusion algorithm is also evaluated by adding Gaussian white noise to the source images. The fusion results are compared with existing multi-resolution based fusion techniques, such as Laplacian Pyramid (LAP), Discrete Wavelet Transform (DWT) and Non Sub-Sampled Contourlet Transform (NSCT). The simulation results indicate that the proposed fusion framework results in better quality fused images when evaluated with subjective and objective metrics. Comparision of these results with those from PSO shows that our algorithm outperforms generic PSO.