Video temporal error concealment using improved directional boundary matching algorithm

Authors: SEYED MOJTABA MARVASTI-ZADEH, HOSSEIN GHANEI-YAKHDAN

Abstract: Nowadays some systems such as multimedia systems try to present a high quality of digital videos every day. Because of the possible errors in communication channels, compressed video data would be damaged in the sending process. Error concealment is a useful technique for concealing the effects of sending errors at the decoder. In this paper, an improved directional boundary matching algorithm is presented, in which by using adjacent macroblocks (MBs) of the damaged MB a direction is identified for each boundary. Then every boundary of candidate MBs is compared to an identified direction. Finally, the candidate motion vector (MV) that has the minimum improved directional matching function is selected as the MV of the damaged MB. Furthermore, to increase the accuracy in damaged MV estimation, a specific weight is given to the boundaries of adjacent MBs. Conforming to the experimental results, the proposed algorithm not only outperforms subjective visual evaluation compared to classic boundary matching, outer boundary matching, and directional boundary matching algorithms, but also it is able to improve the objective quality of reconstructed video frames effectively.

Keywords: Temporal error concealment, motion vector estimation, boundary matching, macroblock

Full Text: PDF