dc.contributor.author | Shanableh, Tamer | |
dc.contributor.author | Assaleh, Khaled | |
dc.date.accessioned | 2017-05-04T04:43:43Z | |
dc.date.available | 2017-05-04T04:43:43Z | |
dc.date.issued | 2015 | |
dc.identifier.citation | Shanableh, T. & Assaleh, K. (2015). H.264/AVC motion vector concealment solutions using online and offline polynomial regression. Signal, Image and Video Processing, 9(3), 581-588. doi:10.1007/s11760-013-0489-3 | en_US |
dc.identifier.issn | 1863-1711 | |
dc.identifier.uri | http://hdl.handle.net/11073/8827 | |
dc.description.abstract | This paper introduces two polynomial regression solutions for error concealment by predicting the values of motion vectors of lost macroblocks. The two solutions are online and offline polynomial regression modeling. In the former solution, the regression model is built during the decoding process whilst in the latter solution; the model is built during the encoding or the transcoding process and then used at the decoder for concealment. Both solutions make use of the spatially and temporally neighboring motion vectors for building the regression models. The advantages and disadvantages of the proposed solutions are elaborated upon. In comparison to existing work, the experimental results show that the proposed solutions have clear advantages of computational time requirements and motion vector prediction accuracy. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | Springer | en_US |
dc.relation.uri | http://doi.org/10.1007/s11760-013-0489-3 | en_US |
dc.subject | Video compression | en_US |
dc.subject | Error concealment | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Regression | en_US |
dc.title | H.264/AVC Motion Vector Concealment Solutions Using Online and Offline Polynomial Regression | en_US |
dc.type | Article | en_US |
dc.type | Postprint | en_US |
dc.type | Peer-Reviewed | en_US |
dc.identifier.doi | 10.1007/s11760-013-0489-3 | |