Abstract
Deep Learning methods have achieved great successes in pedestrian detection owing to their ability of learning discriminative features from pixel level. However, most of the popular methods only consider using the deep structure as a single feature extractor (one attribute) which may confuse positive with hard negative samples. To address this ambiguity, this work jointly learns three different attributes, including parts, deformation and similarity attributes. This paper proposes a new deep network which jointly optimizes the three attributes and formulates them to form a binary classification task. Extensive experiments show that the proposed method outperforms competing methods on the challenging Caltech and ETH benchmarks.
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
References
Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. IJCV 63(2), 153–161 (2005)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: ICCV (2009)
Dollar, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: BMVC (2009)
Dollar, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. TPAMI 36, 1532–1545 (2014)
Zhang, S., Bauckhage, C., Cremers, A.: Informed haarlike features improve pedestrian detection. In: CVPR, pp. 947–954 (2013)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9), 1627–1645 (2010)
Ouyang, W., Wang, X.: A discriminative deep model for pedestrian detection with occlusion handling. In: CVPR (2012)
Ouyang, W., Zeng, X., Wang, X.: Modeling mutual visibility relationship in pedestrian detection. In: CVPR (2013)
Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: CVPR (2013)
Ouyang, W., Wang, X.: Joint deep learning for pedestrian detection. In: ICCV (2013)
Luo, P., Tian, Y., Wang, X., Tang, X.: Switchable deep network for pedestrian detection. In: CVPR, pp. 899–906 (2014)
Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2011)
Tian, Y., Luo, P., Wang, W.: Pedestrian detection aided by deep learning semantic tasks (2014). arXiv preprint arXiv:1412.0069
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14, 1771–1800 (2002)
Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. PAMI 34(4), 743–761 (2012)
Ess, A., Leibe, B., Gool, L.V.: Depth and appearance for mobile scene analysis. In: ICCV (2007)
Torralba, A., Fergus, R., Weiss, Y.: Small codes and large image databases for recognition. In: CVPR (2008)
Wang, J., Kumar, S., Chang, S.-F.: Semi-supervised hashing for large-scale image retrieval. In: CVPR (2010)
Wang, J., Kumar, S., Chang, S.-F.: Sequential projection learning for hashing with compact codes. In: ICML (2010)
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS (2008)
Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. IJCV 63(2), 153–161 (2005)
Sermanet, P., Kavukcuoglu, K., Chintala, S., Lecun, Y.: Pedestrian detection with unsupervised and multi-stage feature learning. In: CVPR (2013)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Wojek, C., Schiele, B.: A performance evaluation of single and multi-feature people detection. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 82–91. Springer, Heidelberg (2008)
Felzenszwalb, P., Grishick, R.B., McAllister, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. PAMI 32, 1627–1645 (2010)
Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: CVPR (2010)
Dollar, P., Belongie, S., Perona, P.: The fastest pedestrian detector in the west. In BMVC, 2010
Dollár, P., Appel, R., Kienzle, W.: Crosstalk cascades for frame-rate pedestrian detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 645–659. Springer, Heidelberg (2012)
Park, D., Ramanan, D., Fowlkes, C.: Multiresolution models for object detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 241–254. Springer, Heidelberg (2010)
Acknowledgments
This work was supported by the National Natural Science Foundation of China under Grants Nos. 61302173, 61461022.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qiu, C., Zhang, Y., Wang, J., He, Z. (2016). Pedestrian Detection Aided by Deep Learning Attributes Task. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds) Pattern Recognition. CCPR 2016. Communications in Computer and Information Science, vol 662. Springer, Singapore. https://doi.org/10.1007/978-981-10-3002-4_17
Download citation
DOI: https://doi.org/10.1007/978-981-10-3002-4_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3001-7
Online ISBN: 978-981-10-3002-4
eBook Packages: Computer ScienceComputer Science (R0)