Fast Rotation Invariant Object Detection with Gradient based Detection Models

Floris De Smedt, Toon Goedemé

2015

Abstract

Accurate object detection has been studied thoroughly over the years. Although these techniques have become very precise, they lack the capability to cope with a rotated appearance of the object. In this paper we tackle this problem in a two step approach. First we train a specific model for each orientation we want to cover. Next to that we propose the use of a rotation map that contains the predicted orientation information at a specific location based on the dominant orientation. This helps us to reduce the number of models that will be evaluated at each location. Based on 3 datasets, we obtain a high speed-up while still maintaining accurate rotated object detection.

References

  1. Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2008). Speeded-up robust features (surf). Comput. Vis. Image Underst., 110(3):346-359.
  2. Benenson, R., Mathias, M., Timofte, R., and Van Gool, L. (2012). Pedestrian detection at 100 frames per second. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2903-2910. IEEE.
  3. Benenson, R., Mathias, M., Tuytelaars, T., and Van Gool, L. (2013). Seeking the strongest rigid detector. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages 3666-3673. IEEE.
  4. CAVIAR (2003). Caviar: context aware vision using imagebased active recognition.
  5. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 886- 893. IEEE.
  6. De Smedt, F., Van Beeck, K., Tuytelaars, T., and Goedemé, T. (2013). Pedestrian detection at warp speed: Exceeding 500 detections per second. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on, pages 622-628. IEEE.
  7. Dollár, P. (2013). Piotrs image and video matlab toolbox (pmt). Software available at: http://vision. ucsd. edu/˜ pdollar/toolbox/doc/index. html.
  8. Dollár, P., Appel, R., Belongie, S., and Perona, P. (2014). Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell., 36(8):1532-1545.
  9. Dollár, P., Belongie, S., and Perona, P. (2010). The fastest pedestrian detector in the west. In BMVC.
  10. Dollár, P., Tu, Z., Perona, P., and Belongie, S. (2009). Integral channel features. In BMVC, volume 2, page 5.
  11. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pages 1-8. IEEE.
  12. Felzenszwalb, P. F., Girshick, R. B., and McAllester, D. (2010). Cascade object detection with deformable part models. In Computer vision and pattern recognition (CVPR), 2010 IEEE conference on, pages 2241-2248. IEEE.
  13. Lowe, D. G. (1999). Object recognition from local scaleinvariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, volume 2, pages 1150-1157. Ieee.
  14. Mathias, M., Timofte, R., Benenson, R., and Van Gool, L. (2013). Traffic sign recognitionhow far are we from the solution? In Neural Networks (IJCNN), The 2013 International Joint Conference on, pages 1-8. IEEE.
  15. Mittal, A., Zisserman, A., and Torr, P. H. (2011). Hand detection using multiple proposals. In BMVC, pages 1-11. Citeseer.
  16. Viola, P. and Jones, M. J. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2):137-154.
Download


Paper Citation


in Harvard Style

De Smedt F. and Goedemé T. (2015). Fast Rotation Invariant Object Detection with Gradient based Detection Models . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 400-407. DOI: 10.5220/0005308404000407


in Bibtex Style

@conference{visapp15,
author={Floris De Smedt and Toon Goedemé},
title={Fast Rotation Invariant Object Detection with Gradient based Detection Models},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={400-407},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005308404000407},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Fast Rotation Invariant Object Detection with Gradient based Detection Models
SN - 978-989-758-090-1
AU - De Smedt F.
AU - Goedemé T.
PY - 2015
SP - 400
EP - 407
DO - 10.5220/0005308404000407