Abstract
The precise localization of pedestrians in images is a difficult problem with many practical applications in the fields of driver assistance, autonomous vehicles and visual surveillance. Localization can be treated as a subsequent step to pedestrian detection that aims at finding the exact position of pedestrians in an input image. In this work, two different approaches for pedestrian localization using neural networks with local receptive fields are presented. The first approach uses a trained ranking classifier to determine the relative order of image windows in regard to their localization quality (coverage) of the pedestrian. Localization is then performed via sampling of the window space in the vicinity of an initial detection. For the second approach, a binary classifier is trained to stepwise move an initial window towards the optimal position. Only few network evaluations are required for this method to converge, making it applicable for real-time detection systems. It is shown how the localization task can be split up into consecutive subtasks, which allows the training of a dedicated classifier for each subtask. This progressive localization scheme improves localization precision and simplifies evaluation of the resulting classifiers. Both approaches are evaluated in detail on the publicly available Daimler Pedestrian Detection Benchmark dataset and the results are compared to a standard detection approach based on non-maximum suppression.
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.
References
Blaschko, M.B., Lampert, C.H.: Learning to Localize Objects with Structured Output Regression. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 2–15. Springer, Heidelberg (2008)
Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., Hullender, G.: Learning to rank using gradient descent. In: Proc. Int. Conf. Machine Learning, pp. 89–96 (2005), doi:10.1145/1102351.1102363
Cohen, W.W., Schapire, R.E., Singer, Y.: Learning to Order Things. Journal of Artificial Intelligence Research 10(1), 243–270 (1999)
Dalal, N., Triggs, W.: Histograms of Oriented Gradients for Human Detection. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 886–893 (2004), http://eprints.pascal-network.org/archive/00000802/
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 304–311 (2009), doi:10.1109/CVPR.2009.5206631
Elliott, D.L.: A Better Activation Function for Artificial Neural Networks. Institute for Systems Research. Univ. of Maryland (1993)
Enzweiler, M., Gavrila, D.M.: Monocular Pedestrian Detection: Survey and Experiments. IEEE Trans. Pattern Anal. 12, 2179–2195 (2009)
Everingham, M., Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision 88(2), 303–338 (2009)
Fukushima, K.: Neocognitron: A Hierarchical Neural Network Capable of Visual Pattern Recognition. Neural Networks 1(2) (1988)
Gressmann, M., Loehlein, O., Palm, G.: Pedestrian Localization. In: Proceedings of 2011 IEEE 9th International Symposium on Intelligent Systems and Informatics, pp. 371–376 (2011), doi:10.1109/SISY.2011.6034355
Gressmann, M., Palm, G., Loehlein, O.: Surround view pedestrian detection using heterogeneous classifier cascades. In: Proceedings 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 1317–1324 (2011), doi:10.1109/ITSC.2011.6082895
Lampert, C., Blaschko, M., Hofmann, T.: Beyond Sliding Windows: Object Localization by Efficient Subwindow Search. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)
LeCun, Y.A., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient BackProp. In: Orr, G.B., Müller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol. 1524, pp. 9–50. Springer, Heidelberg (1998)
Lecun, Y., Kavukcuoglu, K.: Convolutional Networks and Applications in Vision. In: Proc. International Symposium on Circuits and Systems, pp. 253–256 (2010), doi:10.1109/ISCAS.2010.5537907
Munder, S., Gavrila, D.M.: An experimental study on pedestrian classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(11), 1863–1868 (2006)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Shashua, A., Gdalyahu, Y., Hayun, G.: Pedestrian Detection for Driving Assistance Systems: Single-frame Classification and System Level Performance. In: Proc. IEEE Conf. Intelligent Vehicle Symp., pp. 1–6 (2004), doi:10.1109/IVS.2004.1336346
Vaillant, R., Monrocq, C., Le Cun, Y.: An original approach for the localization of objects in images. In: Proc. Int. Conf. Artificial Neural Networks, pp. 26–30 (1993)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I-511–I-518 (2001)
Wang, X., Han, T.X.: An HOG-LBP Human Detector with Partial Occlusion Handling. In: Proc. IEEE Int. Conf. Computer Vision, pp. 32–39 (2009), doi:10.1109/ICCV.2009.5459207
Wohler, C., Anlauf, J.K.: An adaptable time-delay neural-network algorithm for image sequence analysis. IEEE Transactions on Neural Networks 10(6), 1531–1536 (1999)
Wojek, C., Schiele, B.: A performance evaluation of single and multi-feature people detection. In: Proc. DAGM Symp. Pattern Recognition, pp. 82–91 (2008), doi:10.1007/978-3-540-69321-5_9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Gressmann, M., Palm, G., Löhlein, O. (2013). Progressive Pedestrian Localization Using Neural Networks. In: Pap, E. (eds) Intelligent Systems: Models and Applications. Topics in Intelligent Engineering and Informatics, vol 3. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33959-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-33959-2_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33958-5
Online ISBN: 978-3-642-33959-2
eBook Packages: EngineeringEngineering (R0)