New color correction method of multi-view images for view rendering in free-viewpoint television

  • Authors:

  • Feng Shao;Gangyi Jiang;Mei Yu

  • Affiliations:

  • Faculty of Information Science and Engineering, Ningbo University, Ningbo, China;Faculty of Information Science and Engineering, Ningbo University, Ningbo, China;Faculty of Information Science and Engineering, Ningbo University, Ningbo, China

  • Venue:
  • WSEAS Transactions on Computers
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Color inconsistency between views is an important problem to be solved in multi-view video imaging application, such as free viewpoint television. Up to now, some color correction methods have been proposed mainly for consistent color appearance or high coding efficiency, in which the mean, variance, or covariance information are used to transfer color information. In this paper, by using color restoration and linear regression technique, a new color correction method of multi-view images is proposed for view rendering. We first separate foreground and background from scene by mean-removed disparity estimation. Then color restoration is used to reconstruct the original color information for foreground and background. And then linear regression technique is used to estimate correction parameters for color restored image. Finally, color correction and view rendering between reference image and color corrected image are implemented. Experimental results show that he proposed method can achieve better performances of color correction and view rendering.