Speeding Up Object Detection - Fast Resizing in the Integral Image Domain

Michael Gschwandtner, Andreas Uhl, Andreas Unterweger

2014

Abstract

In this paper, we present an approach to resize integral images directly in the integral image domain. For the special case of resizing by a power of two, we propose a highly parallelizable variant of our approach, which is identical to bilinear resizing in the image domain in terms of results, but requires fewer operations per pixel. Furthermore, we modify a parallelized state-of-the-art object detection algorithm which makes use of integral images on multiple scales so that it uses our approach and compare it to the unmodified implementation. We demonstrate that our modification allows for an average speedup of 6.38% on a dual-core processor with hyper-threading and 12.6% on a 64-core multi-processor system, respectively, without impacting the overall detection performance. Moreover, we show that these results can be extended to a whole class of object detection algorithms.

References

  1. Ahonen, T., Hadid, A., and Pietikäinen, M. (2004). Face Recognition with Local Binary Patterns. In Pajdla, T. and Matas, J., editors, Computer Vision - ECCV 2004, volume 3021 of Lecture Notes in Computer Science, pages 469-481. Springer Berlin Heidelberg.
  2. Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2008). Speeded-up robust features (surf). Comput. Vis. Image Underst., 110:346-359.
  3. Bilgic, B., Horn, B. K., and Masaki, I. (2010). Efficient integral image computation on the GPU. In 2010 IEEE Intelligent Vehicles Symposium (IV), pages 528-533, San Diego, CA, USA. IEEE.
  4. Crow, F. C. (1984). Summed-area tables for texture mapping. In Proceedings of the 11th annual conference on Computer graphics and interactive techniques, SIGGRAPH 7884, pages 207-212, New York, NY, USA. ACM.
  5. Heckbert, P. S. (1986). Filtering by repeated integration. In Proceedings of the 13th annual conference on Computer graphics and interactive techniques, SIGGRAPH 7886, pages 315-321, New York, NY, USA. ACM.
  6. Hensley, J., Scheuermann, T., Coombe, G., Singh, M., and Lastra, A. (2005). Fast summed-area table generation and its applications. Computer Graphics Forum, 24(3):547-555.
  7. Hussein, M., Porikli, F., and Davis, L. (2008). Kernel integral images: A framework for fast non-uniform filtering. In IEEE Conference on Computer Vision and Pattern Recognition 2008 (CVPR 2008), pages 1-8, Anchorage, AK, USA. IEEE.
  8. Intel (2012). Intel 64 and IA-32 Architectures Software Developer's Manual, Volume 2B: Instruction Set Reference, N-Z. http://www.intel.com/Assets/PDF/manual/253667.pdf.
  9. Seshadrinathan, K., Soundararajan, R., Bovik, A., and Cormack, L. (2010). Study of Subjective and Objective Quality Assessment of Video. IEEE Transactions on Image Processing, 19(6):1427-1441.
  10. Viola, P. and Jones, M. (2001). Robust Real-time Object detection. In International Journal of Computer Vision, volume 57, pages 137-154.
  11. Willow Garage (2012). willowgarage.com/.
  12. Yu, C., Dian-ren, C., Xu, Y., and Yang, L. (2010). Fast TwoDimensional Otsu's Thresholding Method Based on Integral Image. In 2010 International Conference on Multimedia Technology (ICMT), pages 1-4, Ningbo, China. IEEE.
Download


Paper Citation


in Harvard Style

Gschwandtner M., Uhl A. and Unterweger A. (2014). Speeding Up Object Detection - Fast Resizing in the Integral Image Domain . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 64-72. DOI: 10.5220/0004678000640072


in Bibtex Style

@conference{visapp14,
author={Michael Gschwandtner and Andreas Uhl and Andreas Unterweger},
title={Speeding Up Object Detection - Fast Resizing in the Integral Image Domain},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={64-72},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004678000640072},
isbn={978-989-758-003-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - Speeding Up Object Detection - Fast Resizing in the Integral Image Domain
SN - 978-989-758-003-1
AU - Gschwandtner M.
AU - Uhl A.
AU - Unterweger A.
PY - 2014
SP - 64
EP - 72
DO - 10.5220/0004678000640072