Girgit: A Dynamically Adaptive Vision System for Scene Understanding

Abstract : Abstract. Modernvisionsystemsmustrunincontinuallychangingcontexts.For example, a system to detect vandalism in train stations must function during the day and at night. The vision components for acquisition and detection used dur- ing daytime may not be the same as those used at night. The system must adapt to a context by replacing running components such as image acquisition from color to infra-red. This adaptation must be dynamic with detection of context, decision on change in system configuration, followed by the seamless execution of the new configuration. All this must occur while minimizing the impact of dy- namic change on validity of detection and loss in performance. We present Girgit, a context-aware vision system for scene understanding, that dynamically orches- trates a set of components. A component encapsulates a vision-related algorithm such as from the OpenCV library. Girgit inherently provides loading/caching of multiple component instances, system reconfiguration, management of incoming events to suggest actions such as component re-configuration and replacement of components in pipelines. Given the surplus architectural layer for dynamic adap- tation one may ask, does Girgit degrade scene understanding performance? We perform several empirical evaluations on Girgit using metrics such as frame-rate and adaptation time to answer this question. For instance, the average adaptation time between change in configurations is less than 2 μs with caching, while 8 ms without caching. This in-turn has negligible effect on scene understanding perfor- mance with respect to static C++ implementations for most practical purposes.
Type de document :
Communication dans un congrès
James L. Crowley and Bruce A. Draper and Monique Thonnat. ICVS - International Conference on Computer Vision Systems - 2011, Sep 2011, Sophia Antipolis, France. Springer, 6962, pp.193-202, 2011, Lecture Notes in Computer Science. 〈10.1007/978-3-642-23968-7_20〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00616642
Contributeur : Leonardo Manuel Rocha <>
Soumis le : mardi 23 août 2011 - 15:49:02
Dernière modification le : jeudi 11 janvier 2018 - 16:22:53

Identifiants

Collections

Citation

Leonardo Manuel Rocha, Sabine Moisan, Jean-Paul Rigault, Sen Sagar. Girgit: A Dynamically Adaptive Vision System for Scene Understanding. James L. Crowley and Bruce A. Draper and Monique Thonnat. ICVS - International Conference on Computer Vision Systems - 2011, Sep 2011, Sophia Antipolis, France. Springer, 6962, pp.193-202, 2011, Lecture Notes in Computer Science. 〈10.1007/978-3-642-23968-7_20〉. 〈inria-00616642〉

Partager

Métriques

Consultations de la notice

494