6D vector orthogonal transformation and its application in multiview video coding

Abstract

Multiview video (MVV) is multiple video sequences that integrated different viewpoints data of the same three-dimensional (3D) scene. Each viewpoint data are taken from the ordinary video camera. Thus, the data are very large for the MVV. So compression is necessary in order to store and transmit effectively. Based on the theory of multi-dimensional vector matrix (MDVM), we propose a six-dimensional (6D) vector orthogonal transform nuclear matrix, and prove its orthogonality and energy concentration. We apply the theory to multiview video coding (MVC). This transformation is based on discrete cosine transform (DCT), which has the optimal performance for video data. We represent MVV data with a multi-dimensional (MD) mathematical model. The chosen MVV is earlier eight frames in YUV format from two viewpoints. We divide the Y, U and V components into cubes respectively, and combine the two views data into one cube, on which the transformation is conducted. Good results are obtained in terms of energy concentration. This paper provides a new method for handling MVV, and prepare for the next quantisation and coding.

Keywords:

• multiview video coding (MVC)
• discrete cosine transform (DCT)
• multi-dimensional vector matrix (MDVM)
• 6-dimensional (6D) transform

This work is supported by the National Science Foundation of China under grant no. 60911130128, and Scientific Forefront and Interdisciplinary Innovation Project of Jilin University under grant nos. 200903297 and 201103256.