Complexity-aware live streaming system

Multimedia streaming is one of the most attractive services over the Internet, for which bandwidth is a primary constraint. For live streaming, however, the computational resource also becomes a critical issue. Our goal is to develop a control mechanism for the allocation of both bandwidth and computational resource on the live streaming server. In our previous works, we proposed a method to adjust the computational resource frame by frame based on the quality levels defined in the XviD MPEG-4 encoder. In this paper, we take a different approach in which the allocation of computational resource is adjusted block by block, aiming at a more accurate scheme for controlling the encoding complexity. We also develop a mechanism to determine the encoding parameters that optimize the video quality at given time constraints. The proposed system is applicable to multimedia home gateways, surveillance, IP-based TV, and on-line sports game relays.

• Type: Conference
• Year: 2005
• Where: ICIP
• Authors: Meng-Ting Lu, Chang-Kuan Lin, Jason Yao, Homer H. Chen
• Keywords: Computational Resource, Computational Resource Frame, ICIP 2005, Image Processing, Live Streaming