We propose a real-time contents edition system that allows the input of multiple audio-visual streams and simultaneous encoding into MPEG-4 video objects, editing, and delivery. This system is designed to enable the provision of content based on live video from multiple locations. Our system consists of editing, streaming, and display modules. Streaming and display modules can join/depart from the system while it is operating. To distribute high quality live video movies in different environments, content can also be encoded adaptively in various environments. In this paper, we present an overview of our real-time contents edition system. We also describe the algorithm used to decide whether inter-frame compression should be done frame-by-frame. The suitability of our algorithm was shown in an experimental implementation of the DV-MPEG transducer.
