The Image Fusion of Compressive Sensing with Adaptive Deviation Feature

  • Ye Zhang, Jian Zhang
  • Published 2018 in 2018 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS)


In this paper, an adaptive fusion rule combining high frequency feature of image is proposed.First,making a NSCT decomposition to the infrared image and visible light image, and after that to fuse them using regional energy criterion for the low-frequency sub-bands to obtain a better fusion result than the traditional low frequency coefficients. Next,Since the decomposed high-frequency sub-band coefficients have high sparsity,they are compressed by CS and adopted adaptive fusion rule according to the standard deviation feature.Finally, it gets fusion image by reconstruction of compressive sensing and inverse NSCT transform for data which has been fused. The experimental results show that this paper solves the shortcomings of the traditional image fusion algorithm based on the compressive sensing method (CS), which makes the final fusion image take into account the background information and infrared target information of the image to be fused, effectively improve the integration effect and subjective feelings.


    0 Figures and Tables

      Download Full PDF Version (Non-Commercial Use)