ADAPTIVE IMAGE SENSOR SAMPLING FOR LIMITED MEMORY MOTION DETECTION

David Gibson, Henk Muller, Neill Campbell

Abstract

In this paper we propose that the combination of a state-of-the-art high frequency, low energy demanding microprocessor architecture combined with a highly programmable image sensor can offer a substantial reduction in cost and energy requirement when carrying out low-level visual event detection and object tracking. The XMOS microprocessor consists of a single or multi-core concurrent architecture that runs at between 400 and 1600 MIPS with 64KB per-core of on chip RAM. Modern highly programmable image sensors such as the Kodak KAC-401 can capture regions-of-interest (ROI) at rates in excess of 1500fps. To compare the difference between two 320 by 240 pixel images one would usually require 150KB of RAM, by combining the above components as a computational camera this constraint can be overcome. In the proposed system the microprocessor programs the sensor to capture images as a sequence of high frame rate regions-of-interest. These regions can be processed to determine the presence of motion as differences of ROIs over time. By providing additional cores extensive image processing can be carried out and ROI pixels can be composited onto an LCD to give output images of 320 by 240 pixels at near standard frame rates.

References

  1. Barron, J. L. and Fleet, D. J. and Beauchemin, S. (1994). Performance of optical flow techniques. In International Journal of Computer Vision, volume 12, pages 43-77.
  2. Davis, J. and Bobick, A. (1997). The representation and recognition of action using temporal templates. In International Conference on Computer Vision and Pattern Recognition.
  3. Lichtsteiner, P. and Posch, C. and Delbruck, T. (2007). An 128x128 120db 15us-latency temporal contrast vision sensor. In IEEE Journal Solid State Circuits.
  4. Shi, J. and Tomasi, C. (1994). Good features to track. In International Conference on Computer Vision and Pattern Recognition.
  5. Shotton, J. and Fitzgibbon, A. and Cook, M. and Sharp, T. and Finocchio, M. and More, R. and Kipman, A. and Blake, A. (2011). Real-time human pose recognition in parts from single depth images. In International Conference on Computer Vision and Pattern Recognition.
  6. Shraml, S. and Belbachir, A. N. (2010). A spatio-temporal clustering method using real-time motion analysis on event-based 3d vision. In International Conference on Computer Vision and Pattern Recognition.
  7. Viola, P. and Jones, M. J. and Snow, D. (2005). Detecting pedestrians using patterns of motion and appearance. In International Journal of Computer Vision, volume 63, pages 153-161.
  8. Wells, W. M. (1986). Efficient synthesis of gaussian filters by cascaded uniform filters. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 8, pages 234-239.
Download


Paper Citation


in Harvard Style

Gibson D., Muller H. and Campbell N. (2012). ADAPTIVE IMAGE SENSOR SAMPLING FOR LIMITED MEMORY MOTION DETECTION . In Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: PECCS, ISBN 978-989-8565-00-6, pages 399-402. DOI: 10.5220/0003824603990402


in Bibtex Style

@conference{peccs12,
author={David Gibson and Henk Muller and Neill Campbell},
title={ADAPTIVE IMAGE SENSOR SAMPLING FOR LIMITED MEMORY MOTION DETECTION},
booktitle={Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: PECCS,},
year={2012},
pages={399-402},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003824603990402},
isbn={978-989-8565-00-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: PECCS,
TI - ADAPTIVE IMAGE SENSOR SAMPLING FOR LIMITED MEMORY MOTION DETECTION
SN - 978-989-8565-00-6
AU - Gibson D.
AU - Muller H.
AU - Campbell N.
PY - 2012
SP - 399
EP - 402
DO - 10.5220/0003824603990402