Growth in network capacity has provided new opportunities for bitrate intensive, interactive applications, such as computer games, to stream from a powerful server to a thin client. While typical thin client applications have relatively casual interaction (i.e. typing or mouse clicking) with infrequent display updates (i.e. character updates or scrolling text), computer games, on the other hand, are typically marked by intense interaction (i.e. avatar movement and shooting) and frequently changing displays (i.e. 360 degree panning). While previous work in adapting traditional video to available network capacities has shown that motion and scene complexity are crucial in order to maximize video quality, traditional video differs significantly from game video. This work provides detailed measurements of the motion and scene complexity for a wide variety of video games. Novel algorithms to measure motion and scene complexity are presented and then applied to over twenty-five games from a range of game genres. Direct comparisons of motion and scene complexity are made to traditional video, with differences highlighted in order to help thin client systems perform better when streaming video games. Preliminary performance measurements of current thin client systems are presented, evaluating the efficacy of streaming video games in the context of the motion and scene complexity measurements provided.

Download:

• Full paper (pdf)
• Slides (pptx)
• Game Information (html)
• Notes (text)
• Game Videos (tools, stats, mpeg) (tar, gzip, 11.5 Gbytes)
• Tools Only (zip)

See also:

• Network Games Publications