Abstract
In this paper, we propose a fast and novel detection method based on several samples to localize objects in target images or video. Firstly, we use several samples to train a voting space which is constructed by cells at corresponding positions. Each cell is described by a Gaussian distribution whose parameters are estimated by maximum likelihood estimation method. Then, we randomly choose one sample as a query image. Patches of target image are recognized by densely voting in the trained voting space. Next, we use a mean-shift method to refine multiple instances of object class. The high performance of our approach is demonstrated on several challenging data sets in both efficiency and effectiveness.
Similar content being viewed by others
References
Senjian An, P. Peursum, Wanquan Liu, and Svetha Venkatesh, “Efficient algorithms for subwindow search in object detection and localization,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Miami, 2009), pp. 264–271.
G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. Bray, “Visual categorization with bags of keypoints,” in Proc. European Conf. on Computer Vision (Prague, 2004), pp. 1–22.
C. H. Lampert, M. B. Blaschko, and T. Hofmann, “Efficient subwindow search: a branch and bound framework for object localization,” IEEE Trans. Pattern Anal. Mach. Intellig. 31 (12), 2129–2142 (2009).
A. Lehmann, B. Leibe, and L. van Gool, “Feature-centric efficient subwindow search,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Miami, 2009), pp. 940–947.
J. Mutch and D. G. Lowe, “Multiclass object recognition with sparse, localized features,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (New York, 2006), pp. 11–18.
A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, “Generic object recognition with boosting,” IEEE Trans. Pattern Anal. Mach. Intellig. 28 (3), 416–431 (2006).
N. Razavi, J. Gall, and L. V. Gool, “Scalable multiclass object detection,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Colorado Springs, 2011), pp. 1505–1512.
Sudheendra Vijayanarasimhan and K. Grauman, “Efficient region search for object detection,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Colorado Springs, 2011), pp. 1401–1408.
J. Zhang, S. Lazebnik, and C. Schmid, “Local features and kernels for classification of texture and object categories: a comprehensive study,” Int. J. Comput. Vision 73 (2), 213–238 (2007).
Yimeng Zhang and Tsuhan Chen, “Weakly supervised object recognition and localization with invariant high order features,” in Proc. British Machine Vision Conf. (Swansea, 2010), pp. 47.1-47.11.
E. Shechtman and M. Irani, “Matching local self-similarities across images and videos,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Minneapolis, June 2007), pp. 1–8.
Hae Jong Seo and Peyman Milanfar, “Training-free, generic object detection using locally adaptive regression kernels,” IEEE Trans. Pattern Anal. Mach. Intellig. 32 (9), 1688–1704 (2010).
A. Sibiryakov, “Fast and high-performance template matching method,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (Colorado Springs, 2011), pp. 1–8.
L. Pishchulin, A. Jain. C. Wojek, M. Andriluka, T. Thormahlen, and B. Schiele, “Learning people detection models from few training samples,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (Colorado Springs, 2011), pp. 1–8.
Xinggang Wang, Xiang Bai, Tianyang Ma, Wenyu Liu, and Longing Jan Latecki, “Fan shape model for object detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (Providence, RI, 2012), pp. 1–8.
N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (San Diego, 2005), pp. 1–8.
P. Felzenszwalb, D. McAllester, and D. Ramanan, “A discriminatively trained, multiscale,deformable part model,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (Anchorage, 2008), pp. 1–8.
Danhang Tang, Yang Liu, and Tae-Kyun Kin, “Fast pedestrian detection by cascaded random forest with dominant orientation templates,” in Proc. British Machine Vision Conf. (Guildfort, 2012), pp. 58.1–58.11.
Q. Zhu, S. Avidan, Mei-Chen Yeh, and Kwang-Ting Cheng, “Fast hunman detection using a cascade of histograms of oriented gradients,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (New York, 2006), pp. 1–8.
D. H. Ballard, “Generalizing the hough transform to detect arbitrary shapes,” Pattern Recogn. 13 (2), 111–122 (1981).
D. Chaitanya, R. Deva, and F. Charless. “Discriminative models for multi-class object layout,” Int. J. Comput. Vision 95 (1), 1–12 (2011).
B. Leibe, A. Leonardis, and B. Schiele, “Robust object detection by interleaving categorization and segmentation,” Int. J. Comput. Vision 77 (1–3), 259–289 (2008).
K. Mikolajczyk, B. Leibe, and B. Schiele, “Multiple object class detection with a generative model,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (New York, 2006), pp. 26–36.
F. Jurie and B. Triggs, “Createing efficient codebooks for visual recognition,” in Proc. IEEE Int. Conf. on Computer Vision (San Diego, 2005), Vol. 1, pp. 604–610.
Pei Xu, Mao Ye, Min Fu, and Xudong Li, “Object detection based on several samples with trained hough spaces,” Commun. Comput. Inf. Sci. 321, 235–242 (2012).
Pei Xu, Mao Ye, Xue Li, Lishen Pei, and Pengwei Jiao, “Object detection using voting spaces trained by few samples,” Opt. Eng. 52 (9), (2013).
O. Pele and M. Werman, “The quadratic-chi histogram distance family,” in Proc. Europ. Conf. Computer Vision (Heraklion, 2010), pp. 749–762.
M. Godec, P. M. Roth, and H. Bischof, “Hough-based tracking of non-rigid objects,” in Proc. IEEE Int. Conf. on Computer Vision (Barcelona, Nov. 2011), pp. 81–88.
M. Jordan, J. Kleinberg, and B. Scholkopf, Pattern Recognition and Machine Learning (Springer, 2006).
J. MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proc. 5th Berkeley Symp. on Mathematical Statistics and Probability (Berkeley, CA, 1967), pp. 281–297.
H. Rowley, S. Baluja, and T. Kanade, “Neural networkbased face detection,” IEEE Trans. Pattern Anal. Mach. Intellig. 20 (1), 22–38 (1998).
G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, Labeled Faces in the Wild: a Database for Studying Face Recognition in Unconstrained Environments (Univ. Massachusetts, Amherst, 2007).
A. Kappor and J. Winn, “Located hidden random fields: learning discriminative parts for object detection,” in Proc. European Conf. on Computer Vision (Graz, May 2006), vol. 3954, pp. 302–315.
C. E. Thomaz and G. A. Giraldi, “A new ranking method for principal components analysis and its application to face image analysis,” Image Vision Comput. 28 (6), 902–913 (2010).
S. Agarwal, A. Awan, and D. Roth, “Learning to detect objects in images via a sparse, part based representation,” IEEE Trans. Pattern Anal. Mach. Intellig. 26 (11), 1475–1490 (2004).
B. Wu and R. Nevatia, “Simultaneous object detection and segmentation by boosting local shape feature based classifier,” IEEE Trans. Pattern Anal. Mach. Intellig. 26 (11), 1475–1490 (2004).
M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” in Proc. IEEE Int. Conf. on Computer Vision (Beijing, 2005), pp. 1395–1402.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Pei Xu received his BS degree in computer science and technology from Si Chuan University of Science and Engineering, Zi Gong, China, in 2008 and his MS degree in condensed matter physics from University of Electronic Science and Technology of China, Chengdu, China, in 2011. He is currently a PhD student in University of Electronic Science and Technology of China, Chengdu, China. His current research interests include machine learning and computer vision.
Mao Ye received his PhD degree in mathematics from Chinese University of Hong Kong in 2002. He is currently a professor and director of CVLab at University of Electronic Science and Technology of China. His current research interests include machine learning and computer vision. In these areas, he has published over 70 papers in leading international journals or conference proceedings.
Hongyi Chen received his BS degree in mathematics from University of Electronic Science and Technology of China, Chengdu, China, in 2011. He is currently a postgraduate student in the University of Electronic Science and Technology of China, Chengdu, China. His current research interests are machine vision, visual surveillance, and object detection.
Lishen Pei received her BS degree in computer science and technology from Anyang Teachers College, Anyang, China, in 2010. She is currently an MS student in the University of Electronic Science and Technology of China, Chengdu, China. Her current research interests include action detection and action recognition in computer vision.
Yumin Dou received his master’s degree in Computer Science from Chengdu University of Technology in 2010. He is now a Ph.D. candidate at the School of Computer Science and Engineering of University of Electronic Science and Technology University of China. His research interests include pattern recognition and computer vision.
Rights and permissions
About this article
Cite this article
Xu, P., Ye, M., Pei, L. et al. Fast object detection based on several samples by training voting space. Pattern Recognit. Image Anal. 25, 565–576 (2015). https://doi.org/10.1134/S1054661815040227
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661815040227