Abstract
In this paper, we present an online co-training method called Triple Online Boosting Training (TOBT). TOBT comprehensively combines the advantages of online boosting and tri-training to accomplish the function of online learning and sample validation at the same time. With the help of the novel feature extraction scheme named Fast Feature Pyramid (FFP) reported recently, we develop a real-time online method for multi-scale object detection. This method is proposed for detecting all-sized instances of a certain class in entire image, which is different from other online detectors for tracking purposes. Various experiments based no benchmark datasets and real videos demonstrate the efficacy of the proposed method in the respect of processing speed and stability for changing object appearance and scenarios.
Chapter PDF
Similar content being viewed by others
References
Geronimo, D., Lõpez, A.M., Sappa, A.D., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. Pattern Anal. Mach. Intell. 32(7), 1239–1258 (2010)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian Detection: An Evaluation of the State of the Art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743–761 (2012)
Benenson, R., Omran, M., Hosang, J., Schiele, B.: Ten years of pedestrian detection, what have we learned? In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014 Workshops. LNCS, vol. 8926, pp. 613–627. Springer, Heidelberg (2015)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 511–518 (2001)
Dollár, P., Belongie, S., Perona, P.: The fastest pedestrian detector in the west. In: Proc. British Machine Vision Conf. (2010)
Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast Feature Pyramids for Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)
Grabner, H., Bischof, H.: On-line boosting and vision. In: Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 260–267 (2006)
Chang, W., Cho, C.: Online Boosting for Vehicle Detection. IEEE Trans. Systems, Man, and Cybernetics-Part B: Cybernetics 40(3), 892–902 (2010)
Qi, Z., Xu, Y., Wang, L., Song, Y.: Online multiple instance boosting for object detection. Neurocomputing 74, 1769–1775 (2011)
Visentini, I., Snidaro, L., Foresti, G.: Cascaded online boosting. Journal of Real-time image processing 5(4), 245–257 (2010)
Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: a benchmark. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 2411–2418 (2013)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proc. the 11th Annual Conference on Computational Learning Theory, pp. 92–100 (1998)
Goldman, S., Zhou, Y.: Enhancing supervised learning with unlabeled data. In: Proc. the 17th International Conference on Machine Learning (2000)
Zhou, Z., Li, M.: Tri-Training: exploiting unlabeled data using three classifiers. IEEE Trans. Knowledge and Data Engineering 17(11), 1529–1541 (2005)
Xu, J., He, H., Man, H.: DCPE co-training for classification. Neurocomputing 86, 75–85 (2012)
Li, M., Zhou, Z.: Improve computer-aided diagnosis with machine learning techniques using undiagnosed samples. IEEE Trans. Systems, Man and Cybernetics 37(6) (2007)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (2005)
Piotr’s Computer Vision Matlab Toolbox. http://vision.ucsd.edu/~pdollar/toolbox/doc/index.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, N., Jiang, F., Shan, Y., Liu, J., Liu, L., Li, X. (2015). Triple Online Boosting Training for Fast Object Detection. In: Zha, H., Chen, X., Wang, L., Miao, Q. (eds) Computer Vision. CCCV 2015. Communications in Computer and Information Science, vol 547. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48570-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-662-48570-5_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48569-9
Online ISBN: 978-3-662-48570-5
eBook Packages: Computer ScienceComputer Science (R0)
