Event-driven Dynamic Platform Selection for Power-aware Real-time Anomaly Detection in Video

Calum G Blair, Neil M Robertson

2014

Abstract

In surveillance and scene awareness applications using power-constrained or battery-powered equipment, performance characteristics of processing hardware must be considered. We describe a novel framework for moving processing platform selection from a single design-time choice to a continuous run-time one, greatly increasing flexibility and responsiveness. Using Histogram of Oriented Gradients (HOG) object detectors and Mixture of Gaussians (MoG) motion detectors running on 3 platforms (FPGA, GPU, CPU), we characterise processing time, power consumption and accuracy of each task. Using a dynamic anomaly measure based on contextual object behaviour, we reallocate these tasks between processors to provide faster, more accurate detections when an increased anomaly level is seen, and reduced power consumption in routine or static scenes. We compare power- and speed- optimised processing arrangements with automatic event-driven platform selection, showing the power and accuracy tradeoffs between each. Real-time performance is evaluated on a parked vehicle detection scenario using the i-LIDS dataset. Automatic selection is 10% more accurate than power-optimised selection, at the cost of 12W higher average power consumption in a desktop system.

Paper Citation

in Harvard Style

Blair C. and Robertson N. (2014). Event-driven Dynamic Platform Selection for Power-aware Real-time Anomaly Detection in Video . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 54-63. DOI: 10.5220/0004737400540063

in Bibtex Style

@conference{visapp14,
author={Calum G Blair and Neil M Robertson},
title={Event-driven Dynamic Platform Selection for Power-aware Real-time Anomaly Detection in Video},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={54-63},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004737400540063},
isbn={978-989-758-009-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Event-driven Dynamic Platform Selection for Power-aware Real-time Anomaly Detection in Video
SN - 978-989-758-009-3
AU - Blair C.
AU - Robertson N.
PY - 2014
SP - 54
EP - 63
DO - 10.5220/0004737400540063