JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Image Fusion using RGB and Near Infrared Image
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
  • Journal title : Journal of Broadcast Engineering
  • Volume 21, Issue 4,  2016, pp.515-524
  • Publisher : The Korean Institute of Broadcast and Media Engineers
  • DOI : 10.5909/JBE.2016.21.4.515
 Title & Authors
Image Fusion using RGB and Near Infrared Image
Kil, Taeho; Cho, Nam Ik;
  PDF(new window)
 Abstract
Infrared (IR) wavelength is out of visible range and thus usually cut by hot filters in general commercial cameras. However, some information from the near-IR (NIR) range is known to improve the overall visibility of scene in many cases. For example when there is fog or haze in the scene, NIR image has clearer visibility than visible image because of its stronger penetration property. In this paper, we propose an algorithm for fusing the RGB and NIR images to obtain the enhanced images of the outdoor scenes. First, we construct a weight map by comparing the contrast of the RGB and NIR images, and then fuse the two images based on the weight map. Experimental results show that the proposed method is effective in enhancing visible image and removing the haze.
 Keywords
near infrared;image fusion;image enhancement;dehazing;high dynamic range;
 Language
Korean
 Cited by
 References
1.
Y. M. Lu, C. Fredembach, M. Vetterli and S. Susstrunk, “Designing color filter arrays for the joint capture of visible and near-infrared images,” Proc. IEEE International Conferenece on Image Processing (ICIP), 2009.

2.
Z. Sadeghipoor, Y. M. Lu and S. Susstrunk, “Correlation-based joint acquisition and demosaicing of visible and near-infrared images,” Proc. IEEE International Conferenece on Image Processing (ICIP), 2011.

3.
X. Zhang, T. Sim and X. Miao, “Enhancing photographs with near infra-red images,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2008.

4.
L. Schaul, C. Fredembach and S. Susstrunk, “Color image dehazing using the near-infrared,” Proc. IEEE International Conferenece on Image Processing (ICIP), 2009.

5.
C. Feng, S. Zhuo, X. Zhang and L. Shen, “Near-infrared guided color image dehazing,” Proc. IEEE International Conferenece on Image Processing (ICIP), 2013.

6.
X. Luo, J. Zhang and Q. Dai, “Hybrid fusion and interpolation algorithm with near-infrared image,” Frontiers of Computer Science, 9(3), pp. 375-382, June, 2015. crossref(new window)

7.
D. Rufenact, C. Fredembach and S. Susstrunk, “Automatic and accurate shadow detection using near-infrared information,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), pp. 1672-1678, July, 2014. crossref(new window)

8.
K. He, J. Sun and X. Tang, “Single image haze removal using dark channel prior,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

9.
K. He, J. Sun and X. Tang, “Guided image filtering,” IEEE International Conference on European Conference on Computer Vision (ECCV), 2010.

10.
M. Brown and S. Susstrunk, “Multispectral SIFT for scene category recognition,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

11.
C. Liu, J. Yuen, A. Torralba, J. Sivic and W. Freeman, “SIFT flow dense correspondence across difference scenes,” IEEE International Conference on European Conference on Computer Vision (ECCV), 2008.

12.
Z. Farbman, R. Fattal, D. Lishinski and R. Szeliski, “Edge-preserving decompositions for mutli-scale tone and detail manipulation,” ACM Transactions on Graphics, 27(3), No. 67, August, 2008. crossref(new window)

13.
P. Debevec and J. Malik, “Recovering high dynamic range radiance maps from photographs,” Proc. ACM SIGGRAPH, 2008.