AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Computational Visual Media Article
PDF (7.4 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Parallelized deformable part models with effective hypothesis pruning

Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China.
Show Author Information

Abstract

As a typical machine-learning based detection technique, deformable part models (DPM) achieve great success in detecting complex object categories. The heavy computational burden of DPM, however, severely restricts their utilization in many real world applications. In this work, we accelerate DPM via parallelization and hypothesis pruning. Firstly, we implement the original DPM approach on a GPU platform and parallelize it, making it 136 times faster than DPM release 5 without loss of detection accuracy. Furthermore, we use a mixture root template as a pre-filter for hypothesis pruning, and achieve more than 200 times speedup over DPM release 5, apparently the fastest implementation of DPM yet. The performance of our method has been validated on the Pascal VOC 2007 and INRIA pedestrian datasets, and compared to other state-of-the-art techniques.

Keywords

GPUparallel computingdeformable part models (DPM)hypothesis pruningvisual detection

References

[1]
Dalal, N.; Triggs, B. Histograms of oriented gradients for human detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 886-893, 2005.
[2]
Viola, P.; Jones, M. Rapid object detection using a boosted cascade of simple features. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, I-511-I-518, 2001.
[3]
Lienhart, R.; Maydt, J. An extended set of Haar-like features for rapid object detection. In: Proceedings of International Conference on Image Processing, Vol.1, I-900-I-903, 2002.
[4]
Felzenszwalb, P. F.; Girshick, R. B.; McAllester, D.; Ramanan, D. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 32, No. 9, 1627-1645, 2010.
Crossref Google Scholar
[5]
Felzenszwalb, P.; Girshick, R.; McAllester, D.; Ramanan, D. Visual object detection with deformable part models. Communications of the ACM Vol. 56, No. 9, 97-105, 2013.
Crossref Google Scholar
[6]
Zhu, X.; Ramanan, D. Face detection, pose estimation, and landmark localization in the wild. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2879-2886, 2012.
[7]
Yan, J.; Zhang, X.; Lei, Z.; Liao, S.; Li, S. Z. Robust multi-resolution pedestrian detection in traffic scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 3033-3040, 2013.
Crossref
[8]
Yang, Y.; Ramanan, D. Articulated pose estimation with flexible mixtures-of-parts. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1385-1392, 2011.
Crossref
[9]
Wang, L.; Wu, J.; Zhou, Z.; Liu, Y.; Zhao, X. Recognition by detection: Perceiving human motion through part-configured feature maps. In: Proceedings of IEEE International Conference on Multimedia and Expo Workshops, 1-6, 2014.
Crossref
[10]
Gadeski, E.; Fard, H. O.; Borgne, H. L. GPU deformable part model for object recognition. Journal of Real-Time Image Processing, 1-13, 2014.
Crossref Google Scholar
[11]
Felzenszwalb, P. F.; Huttenlocher, D. P. Pictorial structures for object recognition. International Journal of Computer Vision Vol. 61, No. 1, 55-79, 2005.
Crossref Google Scholar
[12]
Fischler, M. A.; Elschlager, R. A. The representation and matching of pictorial structures. IEEE Transactions on Computers Vol. C-22, No. 1, 67-92, 1973.
Crossref Google Scholar
[13]
Felzenszwalb, P. F.; Girshick, R. B.; McAllester, D. Cascade object detection with deformable part models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2241-2248, 2010.
Crossref
[14]
Amit, Y.; Geman, D. A computational model for visual selection. Neural Computation Vol. 11, No. 7, 1691-1715, 1999.
Crossref Google Scholar
[15]
Felzenszwalb, P. F.; McAllester, D. A.; Ramanan, D. A discriminatively trained, multiscale, deformable part model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008.
Crossref
[16]
Pedersoli, M.; Vedaldi, A.; Gonzàlez, J.; Roca, X. A coarse-to-fine approach for fast deformable object detection. Pattern Recognition Vol. 48, No. 5, 1844-1853, 2015.
Crossref Google Scholar
[17]
Dubout, C.; Fleuret, F. Exact acceleration of linear object detectors. In: Lecture Notes in Computer Science, Vol. 7574. Fitzgibbon, A.; Lazebnik, S.; Perona, P.; Sato, Y.; Schmid, C. Eds. Springer Berlin Heidelberg, 301-311, 2012.
[18]
Lampert, C. H.; Blaschko, M. B.; Hofmann, T. Efficient subwindow search: A branch and bound framework for object localization. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 31, No. 12, 2129-2142, 2009.
Crossref Google Scholar
[19]
Kokkinos, I. Rapid deformable object detection using dual-tree branch-and-bound. In: Proceedings of Advances in Neural Information Processing Systems 24, 2681-2689, 2011.
[20]
Yan, J.; Lei, Z.; Wen, L.; Li, S. Z. The fastest deformable part model for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2497-2504, 2014.
Crossref
[21]
Wilt, N. The CUDA Handbook: A Comprehensive Guide to GPU Programming. Pearson Education, 2013.
[22]
Ryoo, S.; Rodrigues, C. I.; Baghsorkhi, S. S.; Stone, S. S.; Kirk, D. B; Hwu, W.-m. W. Optimization principles and application performance evaluation of a multithreaded GPU using CUDA. In: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 73-82, 2008.
Crossref
[23]
Sanders, J.; Kandrot, E. CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Professional, 2010.
[24]
Girshick, R. B.; Felzenszwalb, P. F.; McAllester, D. Discriminatively trained deformable part models (release 5). 2012. Available at https://people.eecs. berkeley.edu/∼rbg/latent/.
[25]
Everingham, M.; Van Gool, L.; Williams, C. K. I.; Winn, J.; Zisserman, A. The PASCAL visual object classes (VOC) challenge. International Journal of Computer Vision Vol. 88, No. 2, 303-338, 2010.
Crossref Google Scholar
Computational Visual Media
Volume 2 Issue 3,
September 2016
Pages 245-256
DOI: 10.1007/s41095-016-0051-7
Cite this article:
Zhou Z-M, Zhao X. Parallelized deformable part models with effective hypothesis pruning. Computational Visual Media, 2016, 2(3): 245-256. https://doi.org/10.1007/s41095-016-0051-7

742

Views

26

Downloads

3

Crossref

N/A

Web of Science

3

Scopus

0

CSCD

Altmetrics
Revised: 29 January 2016
Accepted: 01 April 2016
Published: 15 June 2016
© The Author(s) 2016

This article is published with open access at Springerlink.com

The articles published in this journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http:// creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Other papers from this open access journal are available free of charge from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www. editorialmanager.com/cvmj.
Return