Content-based selective enhancement for streaming video

摘要: Video transmission over bandwidth-varying networks is becoming increasingly important due to emerging applications such as streaming of video the Internet. The fundamental obstacle in designing systems resides varying characteristics Internet (i.e. bandwidth variations and packet-loss patterns). In MPEG-4, a new scalability scheme, called fine-granular-scalability (FGS), was standardized, which able adapt real-time while using same pre-encoded stream. This paper presents novel technique that enables FGS coding scheme perform content-based enhancement prioritized specific regions. proposed selective mechanism gives framework flexibility differentiated bit-allocation enhance objects, an improved visual image quality can be obtained at various bit-rates. our system, we employed face detection algorithm, conjunction with method consistently leads better subjective under presented has been adopted MPEG-4 standard.