Abstract
We present a cost-sensitive learning framework for pedestrian detection in still images based on the novel Joint Local Orientation Histograms (JLOH) features and the Asymmetric Gentle AdaBoost. The JLOH features capture the co-occurrence of local histograms and make it possible to classify the difficult examples. The proposed Asymmetric Gentle AdaBoost takes account of the situation that the rare positive targets have to be distinguished from enormous negative patterns in practical applications. The quantitative evaluation on the well-defined INRIA data set demonstrates the effectiveness of our methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 886–893. IEEE Press, New York (2005)
Gavrila, D.M.: Pedestrian Detection from a Moving Vehicle. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 37–49. Springer, Heidelberg (2000)
Zhao, L., Thorpe, C.: Stereo and Neural Network-Based Pedestrian Detection. IEEE Trans. on Intelligent Transportation Systems 1, 148–154 (2000)
Seemann, E., Leibe, B., Mikolajczyk, K., Schiele, B.: An Evaluation of Local Shape-Based Features for Pedestrian Detection. In: Proc. British Machine Vision Conference, pp. 949–958. BMVA Press, Worcs (2005)
Leibe, B., Seemann, E., Schiele, B.: Pedestrian Detection in Crowded Scenes. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 878–885. IEEE Press, NewYork (2005)
Mikolajczyk, K., Leibe, B., Schiele, B.: Multiple Object Class Detection with a Generative Model. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 26–36. IEEE Press, New York (2006)
Viola, P.A., Jones, M.J.: Rapid Object Detection Using a Boosted Cascade of Simple Features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 511–518. IEEE Press, New York (2001)
Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. In: Proc. IEEE Conf. Computer Vision And Pattern Recognition, pp. 1491–1498. IEEE Press, New York (2006)
Laptev, I.: Improvements of Object Detection Using Booste Histograms. In: Proc. British Machine Vision Conference, pp. 949–958. BMVA Press, Worcs (2006)
Sabzmeydani, P., Mori, G.: Detecting Pedestrians by Learning Shapelet Features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8. IEEE Press, New York (2007)
Tuzel, O., Porikli, F., Meer, P.: Region Covariance: A Fast Descriptor for Detection and Classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006)
Munder, S., Gavrila, D.M.: An Experimental Study on Pedestrian Classification. IEEE Trans. on Pattern Analysis and Machine Intelligence 28, 1863–1868 (2006)
Wu, B., Ai, H., Huang, C., Lao, S.: Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost. In: Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 79–84. IEEE Press, New York (2004)
Liu, C., Shum, H.: Kullback-Leibler Boosting. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 587–594. IEEE Press, New York (2003)
Li, S., Zhang, Z.: Floatboost Learning and Statistical Face Detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 26, 1112–1123 (2004)
Huang, C., Ai, H., Li, Y., Lao, S.: High-Performance Rotation Invariant Multiview Face Detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 29, 671–686 (2007)
Viola, P.A., Jones, M.J.: Fast and Robust Classification Using Asymmetric Adaboost and a Detector Cascade. In: 14th Conf. on Advances in Neural Information Processing Systems, pp. 1311–1318. MIT Press, Cambridge (2002)
Hou, X., Liu, C.L., Tan, T.: Learning Boosted Asymmetric Classifiers for Object Detection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 330–338. IEEE Press, New York (2006)
Mita, T., Kaneko, T., Hori, O.: Joint Haar-Like Features for Face Detection. In: Proc. IEEE Int. Conf. on Computer Vision, pp. 1619–1626. IEEE Press, New York (2005)
Dollar, P., Tu, Z., Tao, H., Belongie, S.: Feature Mining for Image Classification. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–8. IEEE Press, New York (2007)
Masnadi-Shirazi, H., Vasconcelos, N.: Asymmetric Boosting. In: Proc. 24th Int. Conf. on Machine Learning, pp. 609–619. ACM Press, New York (2007)
Xiao, R., Zhu, L., Zhang, H.: Boosting Chain Learning for Object Detection. In: Proc. IEEE Int. Conf. on Computer Vision, pp. 709–715. IEEE Press, New York (2003)
Friedman, J., Hastie, T., Tibshirani, R.: Additive Logistic Regression: A Statistical View of Boosting. The Annals of Statistics 28, 337–374 (2000)
Sabzmeydani, P., Mori, G.: http://www.cs.sfu.ca/~mori/research/papers/sabzmeydani_shapelet_cvpr07.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ge, J., Luo, Y. (2009). Asymmetric Learning for Pedestrian Detection Based on Joint Local Orientation Histograms. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5551. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01507-6_88
Download citation
DOI: https://doi.org/10.1007/978-3-642-01507-6_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01506-9
Online ISBN: 978-3-642-01507-6
eBook Packages: Computer ScienceComputer Science (R0)