Abstract
This paper proposes a boosting-like deep learning (BDL) framework for pedestrian detection. The fusion of handcrafted and deep learned features is considered to extract more effective representations. Due to overtraining on the limited training samples, over-fitting and convergence stability are two major problems of deep learning. We propose the boosting-like algorithm to enhance the system convergence stability through adjusting the updating rate according to the classification condition of samples in the training process. We theoretically give the derivation of our algorithm. Our approach achieves 15.85% and 3.81% reduction in the average miss rate compared with ACF and JointDeep on the largest Caltech dataset, respectively.
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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 886–893. IEEE Press, San Diego (2005)
Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: Proceedings of Ninth IEEE International Conference on the Computer Vision, pp. 53–161. IEEE Press, Nice (2003)
Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. J. International Journal of Computer Vision 80, 2137–2144 (2006)
Sermanet, P., Kavukcuoglu, K., Chintala, S., Lecun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3626–3633. IEEE Press, Rhode Island (2012)
Wanli, O.Y., Xiaogang, W.: Joint deep learning for pedestrian detection. In: 14th IEEE International Conference on the Computer Vision, pp. 266–274. IEEE Press, Sydney (2013)
Ess, A., Leibe, B., Gool, L.V.: Depth and appearance for mobile scene analysis. In: Proceedings of 11th IEEE International Conference on the Computer Vision, pp. 1–8. IEEE Press, Rio de Janeiro (2007)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An Evaluation of The State of The Art. J. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 743–761 (2012)
Dollar, P., Appel, R., Belongie, S., et al.: Fast Feature Pyramids for Object Detection. J. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 1532–1545 (2014)
LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based Learning Applied to Document Recognition. J. Proceeding of the IEEE 86, 2278–2324 (1998)
Chen, Y.N., Han, C.C., Wang, C.T., et al.: The application of a convolution neural network on face and license plate detection. In: Proc. 18th Int. Conf. Pattern Recognition, pp. 552–555. IEEE Computer Society Press, Hong Kong (2006)
Sermanet, P., Kavukcuoglu, K., Chintala, S., et al.: Pedestrian detection with unsupervised multi-stage feature learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3626–3633. IEEE Press, Rhode Island (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, L., Zhang, B., Yang, W. (2015). Boosting-Like Deep Convolutional Network for Pedestrian Detection. In: Yang, J., Yang, J., Sun, Z., Shan, S., Zheng, W., Feng, J. (eds) Biometric Recognition. CCBR 2015. Lecture Notes in Computer Science(), vol 9428. Springer, Cham. https://doi.org/10.1007/978-3-319-25417-3_68
Download citation
DOI: https://doi.org/10.1007/978-3-319-25417-3_68
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25416-6
Online ISBN: 978-3-319-25417-3
eBook Packages: Computer ScienceComputer Science (R0)