skip to main content
10.1145/3007669.3007721acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicimcsConference Proceedingsconference-collections
poster

Beyond Sliding Windows: Saliency Prior Based Random Partition for Fast Pedestrian Detection

Published: 19 August 2016 Publication History

Abstract

Recently many powerful complicated features have been used for pedestrian detection successfully but they are not fit for real applications because of heavily consuming time caused by production of complicate feature extraction and millions of candidate object probing. The formal is critical for pedestrian detection, so for solving this problem, effective region proposal strategy was proposed. Such approaches generate candidate regions either by segmentation or by shape classification, and they still generate several thousand regions each image, that is too many for fast pedestrian detection. In this paper, a novel search strategy, saliency prior based random partition, is proposed to generate nearly two hundred regions and consume less time than selective search at the same recall. And we prefer the Deformable Part Model [8], one of the most popular object detectors, as the pedestrian detector. At last, we combine the salient prior and the part based detector by Bayesian inference. Experiment results on INRIA person dataset and Caltech person dataset have demonstrated that our approach has outperformed the selective search method.

References

[1]
Y. Ding and J. Xiao. Contextual boost for pedestrian detection. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2895--2902. IEEE, November 2012.
[2]
A. R. Dollár Piotr and K. Wolf. Crosstalk cascades for frame-rate pedestrian detection. In Computer Vision--ECCV 2012, pages 645--659. Springer, 2012.
[3]
B. S. Dollár Piotr and P. Pietro. The fastest pedestrian detector in the west. In Proc. BMVC, pages 68.1--11. Springer, 2010.
[4]
A. Hossein and L. Ivan. Object detection using strongly-supervised deformable part models. In Computer Vision--ECCV 2012, pages 836--849. Springer, 2012.
[5]
Y. D. J.J. Yan, Lei Zhen and L. S. Z. Multi-pedestrian detection in crowded scenes: A global view. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 3124--3129. IEEE, 2012.
[6]
N. M. X. H. M.M. Cheng, G.X. Zhang and S. Hu. Global contrast based salient region detection. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 409--416. IEEE, 2011.
[7]
S. C. Paisitkriangkrai Sakrapee and H. A. V. Den. Efficient pedestrian detection by directly optimizing the partial area under the roc curve. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages 1057--1064. IEEE, 2013.
[8]
M. D. P.F. Felzenszwalb, R.B. Girshick and R. Deva. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern. Analysis. Machine. Intelligence, 32(9):1627--1645, November 2010.
[9]
M. D. P.F. Felzenszwalb, R.B. Girshick and R. Deva. Pedestrian detection: An evaluation of the state of the art. IEEE Trans. Pattern. Analysis. Machine. Intelligence, 34(4):743--761, November 2012.
[10]
J. Sam and E. Mark. Learning effective human pose estimation from inaccurate annotation. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 1465--1472. IEEE, 2011.
[11]
J. R. R. G. T. van de Sande K. E. A., Uijlings and A. W. M. Smeulders. Segmentation as selective search for object recognition. In IEEE International Conference on Computer Vision. IEEE, 2011.
[12]
X. Z. W.L. Ouyang and X. Wang. Modeling mutual visibility relationship in pedestrian detection. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages 3222--3229. IEEE, November 2013.
[13]
W. F. Xiao Wang, Jun Chen. Pedestrian detection from salient regions. In IEEE International Conference on Image Processing. IEEE, 2014.
[14]
W. O. X.Y. Zeng and X. Wang. Multi-stage contextual deep learning for pedestrian detection. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages 121--128. IEEE, 2013.
[15]
Y. Yi and R. Deva. Articulated pose estimation with flexible mixtures-of-parts. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 1385--1392. IEEE, 2011.

Cited By

View all
  • (2020)Self-Supervised Collaborative Multi-Network for Fine-Grained Visual Categorization of Tomato DiseasesIEEE Access10.1109/ACCESS.2020.30393458(211912-211923)Online publication date: 2020

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and Service
August 2016
360 pages
ISBN:9781450348508
DOI:10.1145/3007669
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

In-Cooperation

  • Xidian University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 August 2016

Check for updates

Author Tags

  1. deformable part model
  2. pedestrian detection
  3. random partition
  4. saliency detection

Qualifiers

  • Poster
  • Research
  • Refereed limited

Conference

ICIMCS'16

Acceptance Rates

ICIMCS'16 Paper Acceptance Rate 77 of 118 submissions, 65%;
Overall Acceptance Rate 163 of 456 submissions, 36%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 28 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2020)Self-Supervised Collaborative Multi-Network for Fine-Grained Visual Categorization of Tomato DiseasesIEEE Access10.1109/ACCESS.2020.30393458(211912-211923)Online publication date: 2020

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media