Abstract
Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are expected to be lower. An analogous reasoning applies for image sequences. If there is a pedestrian located within a frame, the same pedestrian is expected to appear close to the same location in neighbor frames. Therefore, such a location has chances of receiving high classification scores during several frames, while false positives are expected to be more spurious. In this paper we propose to exploit such correlations for improving the accuracy of base pedestrian classifiers. In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood. More specifically, we train pedestrian classifiers using a stacked sequential learning (SSL) paradigm. We use a new pedestrian dataset we have acquired from a car to evaluate our proposal at different frame rates. We also test on well known dataset, Caltech. The obtained results show that our SSL proposal boosts detection accuracy significantly with a minimal impact on the computational cost. Interestingly, SSL improves more the accuracy at the most dangerous situations, i.e. when a pedestrian is close to the camera.
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
Similar content being viewed by others
Notes
- 1.
Publicly available in: http://www.cvc.uab.es/adas/site/?q=node/7.
References
Chen, G., Ding, Y., Xiao, J., Han, T.: Detection evolution with multi-order contextual co-occurrence. In: CVPR, Portland, Oregon, USA (2013)
Cohen, W., de Carvalho, V.: Stacked sequential learning. In: IJCAI, Scotland (2005)
Cui, X., Liu, Y., Shan, S., Chen, X., Gao, W.: 3d Haar-like features for pedestrian detection. In: ICME, Bejing, China (2007)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, San Diego, CA, USA (2005)
Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428–441. Springer, Heidelberg (2006)
Ding, Y., Xiao, J.: Contextual boost for pedestrian detection. In: CVPR, USA (2012)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. T-PAMI 34(4), 743–761 (2012)
Enzweiler, M., Gavrila, D.M.: A multi-level mixture-of-experts framework for pedestrian classification. T-IP 20(10), 2967–2979 (2011)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. T-PAMI 32(9), 1627–1645 (2010)
Gerónimo, D., López, A.: Vision-Based Pedestrian Protection Systems for Intelligent Vehicles. Springer, New York (2013)
Gerónimo, D., Sappa, A., Ponsa, D., López, A.: 2D–3D based on-board pedestrian detection system. CVIU 114(5), 583–595 (2010)
Jones, M., Snow, D.: Pedestrian detection using boosted features over many frames. In: CVPR, Anchorage, AK, USA (2008)
Ke, Y., Sukthankar, R., Hebert, M.: Efficient visual event detection using volumetric features. In: ICCV, Beijing, China (2005)
Lafferty, J., McCallum, A., Pereira, F.: Real-time pedestrian detection with deformable part models. In: IV, Madrid, Spain (2012)
Marin, J., Vázquez, D., López, A., Amores, J., Kuncheva, L.: Occlusion handling via random subspace classifiers for human detection. Cyber (2013)
Marin, J., Vázquez, D., López, A., Amores, J., Leibe, B.: Random forests of local experts for pedestrian detection. In: ICCV, Sydney, Australia (2013)
Ramanan, D.: Part-based models for finding people and estimating their pose (2009)
Vázquez, D., López, A., Marín, J., Ponsa, D., Gerónimo, D.: Virtual and real world adaptation for pedestrian detection. T-PAMI 36(4), 797–809 (2013)
Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: ICCV, Nice, France (2003)
Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: CVPR, San Francisco, CA, USA (2010)
Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: ICCV, Kyoto, Japan (2009)
Wojek, C., Walk, S., Schiele, B.: Multi-cue onboard pedestrian detection. In: CVPR, Miami Beach, FL, USA (2009)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-l1 optical flow. In: DAGM, Heidelberg, Germany (2007)
Acknowledgments
This work is supported by the Spanish MICINN projects TRA2011-29454-C03-01 and TIN2011-29494-C03-02.
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
González, A., Vázquez, D., Ramos, S., López, A.M., Amores, J. (2015). Spatiotemporal Stacked Sequential Learning for Pedestrian Detection. In: Paredes, R., Cardoso, J., Pardo, X. (eds) Pattern Recognition and Image Analysis. IbPRIA 2015. Lecture Notes in Computer Science(), vol 9117. Springer, Cham. https://doi.org/10.1007/978-3-319-19390-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-19390-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19389-2
Online ISBN: 978-3-319-19390-8
eBook Packages: Computer ScienceComputer Science (R0)