BROWSE
Detail
Conference Paper
Content-based utility function prediction for real-time MPEG-4 video transcoding
Cited - time in 
Share 
Share
- Authors
- Y. Wang, Jae-Gon Kim, S.-F. Chang
- Issue Date
- 2003-09
- Citation
- International Conference on Image Processing (ICIP) 2003, pp.189-192
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Utility function based transcoding is an efficient systematic solution for choosing optimal media transcoding operation to meet dynamic resource constraints (such as bandwidth). However, to date the real-time generation of utility function is not feasible due to computational complexity. In this paper we present a content-based utility function prediction framework for real-time MPEG-4 video transcoding. We develop a statistical approach combining real-time compressed-domain feature extraction, content-based pattern classification and regression. Our extensive experiment results demonstrate that the proposed method achieves very promising prediction accuracy - up to 89% in choosing the optimal transcoding operation with the highest quality from multiple alternatives meeting the same target bitrate.
- KSP Keywords
- Compressed Domain, Computational complexity, Domain feature, Dynamic resource, Experiment results, Feature extractioN, MPEG-4 video, Pattern classification, Prediction accuracy, Prediction framework, Real-time generation