How to Exploit Scene Constraints to Improve Object Categorization Algorithms for Industrial Applications?

Steven Puttemans, Toon Goedemé

Abstract

State-of-the-art object categorization algorithms are designed to be heavily robust against scene variations like illumination changes, occlusions, scale changes, orientation and location differences, background clutter and object intra-class variability. However, in industrial machine vision applications where objects with variable appearance have to be detected, many of these variations are in fact constant and can be seen as constraints on the scene, which in turn can reduce the enormous search space for object instances. In this position paper we explore the possibility to fixate certain of these variations according to the application specific scene constraints and investigate the influence of these adaptations on three main aspects of object categorization algorithms: the amount of training data needed, the speed of the detection and the amount of false detections. Moreover, we propose steps to simplify the training process under such scene constraints.

References

  1. Abdel-Hakim, A. and Farag, A. (2006). Csift: A sift descriptor with color invariant characteristics. In CVPR, pages 1978-1983.
  2. Bay, H., Tuytelaars, T., and Van Gool, L. (2006). Surf: Speeded up robust features. ECCV, pages 404-417.
  3. Dollár, P., Tu, Z., Perona, P., and Belongie, S. (2009). Integral channel features. In BMVC.
  4. Felzenszwalb, P., Girshick, R., and McAllester, D. (2010). Cascade object detection with deformable part models. In CVPR, pages 2241-2248.
  5. Gall, J. and Lempitsky, V. (2009). Class-Specific Hough Forests for Object Detection. In CVPR, pages 1022- 1029.
  6. Hsieh, J., Liao, H., Fan, K., Ko, M., and Hung, Y. (1997). Image registration using a new edge-based approach. CVIU, pages 112-130.
  7. Leibe, B. and Schiele, B. (2004). Scale-invariant object categorization using a scale-adaptive mean-shift search. Pattern Recognition, pages 145-153.
  8. Lewis, J. (1995). Fast normalized cross-correlation. In Vision interface, volume 10, pages 120-123.
  9. Mindru, F., Tuytelaars, T., Gool, L., and Moons, T. (2004). Moment invariants for recognition under changing viewpoint and illumination. CVIU, 94:3-27.
  10. Van Beeck, K., Goedemé, T., and Tuytelaars, T. (2012). A warping window approach to real-time vision-based pedestrian detection in a truck's blind spot zone. In ICINCO, volume 2, pages 561-568.
  11. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In CVPR, pages I-511.
Download


Paper Citation


in Harvard Style

Puttemans S. and Goedemé T. (2013). How to Exploit Scene Constraints to Improve Object Categorization Algorithms for Industrial Applications? . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 827-830. DOI: 10.5220/0004342108270830


in Bibtex Style

@conference{visapp13,
author={Steven Puttemans and Toon Goedemé},
title={How to Exploit Scene Constraints to Improve Object Categorization Algorithms for Industrial Applications?},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={827-830},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004342108270830},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - How to Exploit Scene Constraints to Improve Object Categorization Algorithms for Industrial Applications?
SN - 978-989-8565-47-1
AU - Puttemans S.
AU - Goedemé T.
PY - 2013
SP - 827
EP - 830
DO - 10.5220/0004342108270830