Journal Home > Volume 2 , Issue 2

Hough Forests have demonstrated effective performance in object detection tasks, which has potential to translate to exciting opportunities in pattern search. However, current systems are incompatible with the scalability and performance requirements of an interactive visual search. In this paper, we pursue this potential by rethinking the method of Hough Forests training to devise a system that is synonymous with a database search index that can yield pattern search results in near real time. The system performs well on simple pattern detection, demonstrating the concept is sound. However, detection of patterns in complex and crowded street-scenes is more challenging. Some success is demonstrated in such videos, and we describe future work that will address some of the key questions arising from our work to date.


menu
Abstract
Full text
Outline
About this article

Rethinking random Hough Forests for video database indexing and pattern search

Show Author's information Craig Henderson1( )Ebroul Izquierdo1
Multimedia and Vision Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, E1 4NS, UK.

Abstract

Hough Forests have demonstrated effective performance in object detection tasks, which has potential to translate to exciting opportunities in pattern search. However, current systems are incompatible with the scalability and performance requirements of an interactive visual search. In this paper, we pursue this potential by rethinking the method of Hough Forests training to devise a system that is synonymous with a database search index that can yield pattern search results in near real time. The system performs well on simple pattern detection, demonstrating the concept is sound. However, detection of patterns in complex and crowded street-scenes is more challenging. Some success is demonstrated in such videos, and we describe future work that will address some of the key questions arising from our work to date.

Keywords: machine learning, Hough Forests, pattern detection, pattern search

References(25)

[1]
Gall, J.; Lempitsky, V. Class-specific Hough forests for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1022-1029, 2009.
DOI
[2]
Gall, J.; Yao, A.; Razavi, N.; Van Gool, L.; Lempitsky, V. Hough forests for object detection, tracking, and action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 33, No. 11, 2188-2202, 2011.
[3]
Breiman, L. Random forests. Machine Learning Vol. 45, No. 1, 5-32, 2001.
[4]
Barinova, O.; Lempitsky, V.; Kholi, P. On detection of multiple object instances using Hough transforms. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 34, No. 9, 1773-1784, 2012.
[5]
Payet, N.; Todorovic, S. Hough forest random field for object recognition and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 35, No. 5, 1066-1079, 2013.
[6]
Razavi, N.; Alvar, N. S.; Gall, J.; Van Gool, L. Sparsity potentials for detecting objects with the Hough transform. In: Proceedings of British Machine Vision Conference, 11.1-11.10, 2012.
DOI
[7]
Srikantha, A.; Gall, J. Hough-based object detection with grouped features. In: Proceedings of IEEE International Conference on Image Processing, 1653-1657, 2014.
DOI
[8]
Yokoya, N.; Iwasaki, A. Object detection based on sparse representation and Hough voting for optical remote sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 8, No. 5, 2053-2062, 2015.
[9]
Godec, M.; Roth, P. M.; Bischof, H. Hough-based tracking of non-rigid objects. Computer Vision and Image Understanding Vol. 117, 1245-1256, 2013.
[10]
Rematas, K.; Leibe, B. Efficient object detection and segmentation with a cascaded Hough Forest ISM. In: Proceedings of IEEE International Conference on Computer Vision Workshops, 966-973, 2011.
DOI
[11]
Waltisberg, D.; Yao, A.; Gall, J.; Van Gool, L. Variations of a Hough-voting action recognition system. In: Lecture Notes in Computer Science, Vol. 6388. Ünay, D.; Çataltepe, Z.; Aksoy, S. Eds. Springer Berlin Heidelberg, 306-312, 2010.
DOI
[12]
Yao, A.; Gall, J; Van Gool, L. A Hough transform-based voting framework for action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2061-2068, 2010.
DOI
[13]
Yu, G.; Yuan, J.; Liu, Z. Unsupervised random forest indexing for fast action search. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 865-872, 2011.
DOI
[14]
Gall, J.; Razavi, N.; Van Gool, L. An introduction to random forests for multi-class object detection. In: Proceedings of the 15th International Conference on Theoretical Foundations of Computer Vision: Outdoor and Large-scale Real-world Scene Analysis, 243-263, 2012.
DOI
[15]
Henderson, C.; Izquierdo, E. Minimal Hough forest training for pattern detection. In: Proceedings of International Conference on Systems, Signals and Image Processing, 69-72, 2015.
DOI
[16]
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.
[17]
Leibe, B.; Leonardis, A.; Schiele, B. Robust object detection with interleaved categorization and segmentation. International Journal of Computer Vision Vol. 77, No. 1, 259-289, 2008.
[18]
Thomas, A.; Ferrari, V.; Leibe, B.; Tuytelaars, T.; Van Gool, L. Using multi-view recognition and metadata annotation to guide a robot’s attention. The International Journal of Robotics Research Vol. 28, No. 8, 976-998, 2009.
[19]
Razavi, N.; Gall, J.; Van Gool, L. Backprojection revisited: Scalable multi-view object detection and similarity metrics for detections. In: Lecture Notes in Computer Science, Vol. 6311. Daniilidis, K.; Maragos, P.; Paragios, N. Eds. Springer Berlin Heidelberg, 620-633, 2010.
[20]
Li, F.-F.; Fergus, R.; Perona, P. Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. Computer Vision and Image Understanding Vol. 106, No. 1, 59-70, 2007.
[21]
Griffin, G.; Holub, A.; Perona, P. Caltech-256 object category dataset. Technical Report. California Institute of Technology, 2007. Available at http://authors.library.caltech.edu/7694/1/CNS-TR-2007-001.pdf.
[22]
Zobel, J.; Moffat, A. Inverted files for text search engines. ACM Computing Surveys Vol. 38, No. 2, Article No. 6, 2006.
[23]
Domingos, P.; Hulten, G. Mining high-speed data streams. In: Proceedings of the 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 71-80, 2000.
DOI
[24]
Ristin, M.; Guillaumin, M.; Gall, J.; Van Gool, L. Incremental learning of random forests for large-scale image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015.
[25]
Henderson, C.; Blasi, S. G.; Sobhani, F.; Izquierdo, E. On the impurity of street-scene video footage. In: Proceedings of the 6th International Conference on Imaging for Crime Prevention and Detection, 1-7, 2015.
DOI
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Revised: 24 November 2015
Accepted: 18 December 2015
Published: 01 March 2016
Issue date: June 2016

Copyright

© The Author(s) 2016

Acknowledgements

This work is funded by the European Union’s Seventh Framework Programme, specific topic “framework and tools for (semi-) automated exploitation of massive amounts of digital data for forensic purposes”, under grant agreement number 607480 (LASIE IP project). The authors extend their thanks to the Metropolitan Police at Scotland Yard, London, UK, for the supply of and permission to use CCTV images.

Rights and permissions

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