Abstract
This paper addresses the performance improvement of efficient sub-window search algorithms for object detection. The current algorithms are for flexible rectangle-shaped sub-window with high computation costs. In this paper, a restriction is applied on the sub-window shape from rectangle into square in order to reduce the number of possible sub-windows with an expectation to improve the computation speed. However, this may come with a consequence of accuracy loss for some objects. In addition, another variance of sub-window shape is also tested which based on the ratio between the height and width of an image. The experiment results on the proposed algorithms were analysed and compared with the performance of the original algorithms to determine whether the speed improvement is significantly large while making the accuracy loss acceptable. It was found that some new algorithms show a good speed improvement while maintaining small accuracy loss. Furthermore, there is an algorithm designed from a combination of a new algorithm and an original algorithm which gains the benefit from both algorithms and produces the best performance among all new algorithms.
Similar content being viewed by others
References
An S, Peursum P, Liu W, Venkatesh S (2009) Efficient algorithms for subwindow search in object detection and localization. In: IEEE conference on computer vision and pattern recognition, 2009, pp 264–271
An S, Peursum P, Liu W, Venkatesh S, Chen X (2010) Exploiting Monge structures in optimum subwindow search. In: IEEE conference on computer vision and pattern recognition, 2010, pp 926–933
Bentley J (1984) Programming pearls: perspective on performance. Commun ACM 27(11):1087–1092. doi:10.1145/1968.381154
Brown M, Lowe DG (2003) Recognising panoramas. In: Proceedings of 9th IEEE international conference on computer vision, 2003, pp 1218–1225
Chapelle O, Haffner P, Vapnik VN (1999) Support vector machines for histogram-based image classification. IEEE Transact Neural Netw 10(5):1055–1064
Cong G, Xudong J (2009) Face recognition using sift features. In: 16th IEEE international conference on image processing, 2009, pp 3313–3316
Cortes C, Vapnik V (1995) Support-vector networks. Machine Learning 20(3):273–297. doi:10.1007/bf00994018
Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines: and other kernel-based learning methods. Cambridge University Press, UK
Everingham M, Zisserman A, Williams CKI, Van Gool L (2006) The PASCAL visual object classes challenge 2006 (VOC 2006) results. http://www.pascal-network.org/challenges/VOC/voc2006/. Accessed 10 March 2011
Gee-Sern H, Chyi-Yeu L, Jia-Shan W (2009) Real-time 3-D object recognition using scale invariant Feature Transform and stereo vision. In: 4th international conference on autonomous robots and agents, 2009. ICARA 2009, pp 239–244
Heikkila J, Silven O (1999) A real-time system for monitoring of cyclists and pedestrians. In: 2nd IEEE workshop on visual surveillance, 1999, pp 74–81
Jae-Young C, Kyung-Sang S, Young-Kyu Y (2007) Multiple vehicles detection and tracking based on scale-invariant feature transform. In: Intelligent transportation systems conference, 2007. ITSC 2007. IEEE, pp 528–533
Lampert CH (2010) An efficient divide-and-conquer cascade for nonlinear object detection. In: IEEE conference on computer vision and pattern recognition, 2010, pp 1022–1029
Lampert CH, Blaschko MB, Hofmann T (2008) Beyond sliding windows: object localization by efficient subwindow search. In: IEEE conference on computer vision and pattern recognition, 2008, pp 1–8
Lampert CH, Blaschko MB, Hofmann T (2009) Efficient subwindow search: a branch and bound framework for object localization. IEEE Transact Pattern Anal Mach Intell 31(12):2129–2142
Lehmann A, Leibe B, van Gool L (2009) Feature-centric efficient subwindow search. In: 12th IEEE international conference on computer vision, 2009, pp 940–947
Leoputra WS, Venkatesh S, Tan T (2009) Comparative evaluation of pedestrian detection methods for mobile bus surveillance. In: IEEE international conference on acoustics, speech and signal processing, 2009, pp 3525–3528
Lichun Z, Junwei C, Yue L, Wang P (2008) Face recognition using scale invariant feature transform and support vector machine. In: 9th international conference on young computer scientists, 2008, pp 1766–1770
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91–110. doi:10.1023/b:visi.0000029664.99615.94
Scholkopf B, Smola AJ (2001) Learning with Kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge
Vapnik VN (1995) The nature of statistical learning theory. Springer-Verlag, New York
Yeh T, Lee JJ, Darrell T (2009) Fast concurrent object localization and recognition. In: IEEE conference on computer vision and pattern recognition, 2009, pp 280–287
Yuchi H, Qingshan L, Metaxas DN (2011) A component-based framework for generalized face alignment. IEEE Transact Syst Man Cybern Part B: Cybern 41(1):287–298
Zhiqi Z, Yu C, Salvi D, Oliver K, Waggoner J, Song W (2010) Free-shape subwindow search for object localization. In: IEEE conference on computer vision and pattern recognition, 2010, pp 1086–1093
Acknowledgments
We are grateful to the comments given by the reviewers. The presentation of this paper is significantly improved based on their feedback.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liang, A., An, S. & Liu, W. Efficient sub-window search with fixed shape sub-windows. Int. J. Mach. Learn. & Cyber. 4, 41–49 (2013). https://doi.org/10.1007/s13042-012-0074-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-012-0074-z