Image Fusion Based on Compressed Sensing

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 246)

Abstract

Compressive sensing (CS) has received a lot of interest due to its compression capability and lack of complexity on the sensor side. This paper presented a new image fusion based on compressed sensing. The method decomposes two or more original images using directionlet transform, and gets the sparse matrix by the directionlet coefficients sparse representation, and fuses the sparse matrices with the coefficients absolute value maximum scheme. The compressed sample can be received through randomly observed. The fused image is recovered from the reduced samples by solving the optimization. The study demonstrates that CS-based image fusion has a number of perceived advantages in comparison with image fusion in the infrared image domain. The simulations show that the proposed CS-based image fusion algorithm has the advantages of simple structure and easy implementation, and also can achieve a better fusion performance.

Keywords

Image fusion Compressive sensing Directionlet transform 

Notes

Acknowledgment

The authors are grateful to the anonymous referees for constructive comments. This study was funded by the Tianjin Normal University Doctoral Fund (52X09008).

References

  1. 1.
    Zhou Xin, Liu Rui-An, Chen Jin (2009) Infrared and visible image fusion enhancement technology based on multi-scale directional analysis. In: Image and Signal Processing, 17–19 October, 2009, pp. 1–3
  2. 2.
    Hall DL, Linas J (1997) An introduction to multisensor data fusion. Proc IEEE 85(10):6–23CrossRefGoogle Scholar
  3. 3.
    Toet A, Ruyven LV, Velaton J (1989) Merging thermal and visual images by a contrast pyramid. Opt Eng 28(7):789–792CrossRefGoogle Scholar
  4. 4.
    Yonghong J (1998) Fusion of landsat TM and SAR image based on principal component analysis. Rem Sens Tech Appl 13(1):4649–4654Google Scholar
  5. 5.
    Yu-chi L, Qi-hai L (2010) An image fusion algorithm based on directionlet transform. Nanotech Precis Eng 8(6):565–568Google Scholar
  6. 6.
    Velisavljevic V, Beferull-Lozano B, Vetterli M (2006) Directionlets: anisotropic multi-directional representation with separable filtering. IEEE Trans Image Process 15(7):1916–1933CrossRefMathSciNetGoogle Scholar
  7. 7.
    Jin Wei F, Ran-di YM (2011) Multi-focus fusion using dual-tree contourlet and compressed sensing. Opto-Electron Eng 38(4):87–94Google Scholar
  8. 8.
    Candes E, Wakin MB (2008) An introduction to compressive sampling. IEEE Signal Process Mag 48(4):21–30 (S1053-5888)CrossRefGoogle Scholar
  9. 9.
    Provost F, Lesage F (2009) The application of compressed sensing for photo-acoustic tomography. IEEE Trans Med Imag 28(4):585–594 (S0278-0062)CrossRefGoogle Scholar
  10. 10.
    Velisavljevic V (2009) Low-complexity iris coding and recognition based on directionlets. IEEE Trans Inform Forensics Secur 4(3):410–417CrossRefGoogle Scholar
  11. 11.
    Velisavljevic V, Beferull-Lozano B, Vetterli M (2007) Space-frequency quantization for image compression with directionlets. IEEE Trans Image Process 16(7):1761–1773CrossRefMathSciNetGoogle Scholar
  12. 12.
    Velisavljevic V, Beferull-Lozano B, Vetterli M (2007) Efficient image compression using directionlets. 6th international conference on information, communications & signal processing, Singapore, 1–13 December, 2007, pp. 1–5Google Scholar
  13. 13.
    Tao Wan, Nishan Canagarajah, Alin Achim. Compressive image fusion. IEEE international conference image process, San Diego, CA, 12–15 October, 2008, pp. 1308–11Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.College of Electronic and Communication EngineeringTianjin Normal UniversityTianjinChina

Personalised recommendations