Year: 2013
Type: conference-paper
Abstract: Data transfers scheduling is an important part of almost all distributed virtual walkthrough (DVW) applications. Its\nmain purpose is to preserve data transfer efficiency and render quality during scene exploration. The most limiting\nfactors here are network restrictions such as low bandwidth and high latency. Current scheduling algorithms\nuse multi-resolution data representation, priority determination and data prefetching algorithms to minimize these\nrestrictions. Advanced priority determination and data prefetching methods for DVW applications use mathematic\ndescription of motion to predict next position of each individual user. These methods depend on the recent motion\nof a user so that they can accurately predict only near locations. In the case of sudden but regular changes in user\nmotion direction (road networks) or fast moving user, these algorithms are not sufficient to predict future position\nwith required accuracy and at required distances. In this paper we propose a systematic solution to scheduling of\ndata transfer for DVW applications which uses next location prediction methods to compute download priority or\nadditionally prefetch rendered data in advance. Experiments show that compared to motion functions the proposed\nscheduling scheme can increase data transfer efficiency and rendered image quality during scene exploration.
Authors: Jaroslav Pribyl, Pavel Zemčík, T. Burian, Boris Kudlac
Institution: Brno University of Technology
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2407232437
