An Objective Evaluation for Disparity Map Based on the Disparity Gradient and Disparity Acceleration

In this paper, we present a novel objective approach to evaluate the disparity map quality. The two indices which are disparity gradient and disparity acceleration are first proposed for the evaluation of the disparity map. These two indices are under the assumption that the disparity map should be smooth in the natural scene. The joint application of the two indices guarantees the effective and reliable evaluation. The experimental results demonstrate the perfect performance of the proposed approach especially under certain noise levels.

[1]  Borko Furht,et al.  Challenges and Opportunities in Video Coding for 3D TV , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[2]  D. Bouwhuis,et al.  Perceived depth and the feeling of presence in 3DTV , 1998 .

[3]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[4]  H. Kalva,et al.  Evaluation of 3DTV Service using Asymmetric View Coding Based on MPEG-2 , 2007, 2007 3DTV Conference.

[5]  Richard Szeliski,et al.  High-accuracy stereo depth maps using structured light , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  B. Julesz,et al.  A disparity gradient limit for binocular fusion. , 1980, Science.

[8]  Zhou Wang,et al.  Image Quality Assessment: From Error Measurement to Structural Similarity , 2004 .

[9]  A. Aksay,et al.  Towards compound stereo-video quality metric: a specific encoder-based framework , 2006, 2006 IEEE Southwest Symposium on Image Analysis and Interpretation.

[10]  Bülent Sankur,et al.  Statistical evaluation of image quality measures , 2002, J. Electronic Imaging.