An efficient color transfer algorithm for recoloring multiband night vision imagery

A color transfer method is presented to give fused multiband nighttime imagery a natural daytime color appearance in a simple and efficient way. Instead of using the traditional nonlinear lαβ space, the proposed method transfers the color distribution of the target image (daylight color image) to the source image (fused multiband nighttime imagery) in the linear YCBCR color space. The YCBCR transformation is simpler and more suitable for image fusion compared to the lαβ conversion. The YCBCR transformation can be extended into a general formalism. And the paper mathematically proves that, for color transfer, using color spaces conforming to this general YCBCR space framework can produce same recoloring results as using the YCBCR space. Experimental results demonstrate that the YCBCR based color transfer method works surprisingly well for transferring natural color characteristics of daylight color images to false color fused multiband nighttime imagery, and moreover, can also be successfully applied to recoloring a variety of color images.

[1]  Ke Wang,et al.  Merging infrared and color visible images with an contrast enhanced fusion method , 2007, SPIE Defense + Commercial Sensing.

[2]  Gemma Piella,et al.  A general framework for multiresolution image fusion: from pixels to regions , 2003, Inf. Fusion.

[3]  Alexander Toet,et al.  Portable real-time color night vision , 2008, SPIE Defense + Commercial Sensing.

[4]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[5]  I. Daubechies,et al.  Biorthogonal bases of compactly supported wavelets , 1992 .

[6]  Weiqi Jin,et al.  Real-time color transfer system for low-light level visible and infrared images in YUV color space , 2007, SPIE Defense + Commercial Sensing.

[7]  Vassilis Tsagaris,et al.  Fusion of visible and infrared imagery for night color vision , 2005, Displays.

[8]  Qingquan Li,et al.  A comparative analysis of image fusion methods , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Yufeng Zheng,et al.  A local-coloring method for night-vision colorization utilizing image analysis and fusion , 2008, Inf. Fusion.

[10]  Zhenhua Li,et al.  Color transfer based remote sensing image fusion using non-separable wavelet frame transform , 2005, Pattern Recognit. Lett..

[11]  Alexander Toet.  Transferring color to single-band intensified night vision images , 2004, SPIE Defense + Commercial Sensing.

[12]  Rick S. Blum,et al.  A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application , 1999, Proc. IEEE.

[13]  Touradj Ebrahimi,et al.  The JPEG 2000 still image compression standard , 2001, IEEE Signal Process. Mag..

[14]  Alexander Toet,et al.  Natural colour mapping for multiband nightvision imagery , 2003, Inf. Fusion.

[15]  Alexander Toet,et al.  Method for applying daytime colors to nighttime imagery in realtime , 2008, SPIE Defense + Commercial Sensing.

[16]  Ke Wang,et al.  Applying daytime colors to night-time imagery with an efficient color transfer method , 2007, SPIE Defense + Commercial Sensing.

[17]  James A. Ferwerda,et al.  Applied perception , 2001, IEEE Computer Graphics and Applications.

[18]  Sanjeeb Dash,et al.  JPEG compression history estimation for color images , 2003, IEEE Transactions on Image Processing.

[19]  Allen M. Waxman,et al.  Fusion of multi-sensor imagery for night vision: color visualization, target learning and search , 2000, Proceedings of the Third International Conference on Information Fusion.

[20]  D. Ruderman,et al.  Statistics of cone responses to natural images: implications for visual coding , 1998 .

[21]  Klaus Mueller,et al.  Transferring color to greyscale images , 2002, ACM Trans. Graph..