Color-Based Object Recognition on a Grid

摘要

Abstract. Multimedia data is rapidly gaining importance along with recent developments such as the increasing deployment of surveillance cameras in public locations, and the need for automatic comparison of forensic video evidence. In a few years time, analyzing the content of multimedia data will be a problem of phenomenal proportions, as digital video may produce data at rates beyond 100 Mb/s, and multimedia archives steadily run into Petabytes of storage space. Consequently, for urgent problems in multimedia content analysis, Grid computing is rapidly becoming indispensable. This paper explores the viability of wide-area Grid systems in adhering to the heavy demands of a real-time task in multimedia content analysis. Specifically, we show the application of a robot dog, capable of recognizing objects from a set of 1,000 learned objects, while connected to a large-scale Grid system comprising of cluster systems in Europe and Australia. Our results indicate that we have reached the moment at which real-time image and video analysis on large-scale Grids is becoming a reality. Moreover, our approach shows the effective integration of stateof-the-art results from two largely distinct research fields: multimedia content analysis and Grid computing. 1