Abstract
In this work, a framework is proposed for pedestrian classification based on spatial recurrences in the form of recurrence plots. This representation is more general and potentially more discriminative than a histogram of co-occurrences, since the correlation information between different spatial locations is maintained rather than just summarized into histograms. Recurrences are defined over “states” that encode some visual information at spatial locations over a grid. The framework is general in that it accommodates states of arbitrary nature, any similarity distance between pairs of states, arbitrary grids, and varying degree of recurrence summarization. As revealed experimentally, the resulting descriptor is competitive to recent approaches and compares favourably to an state-of-the-art co-occurrence-based descriptor under several occlusion conditions, and in related problems such as pedestrian view recognition, in particular under stringent quantization conditions. One interesting additional finding is that splitting the recurrent information into multiple recurrence plots turns out to be more discriminative than condensing it into fewer plots.
Similar content being viewed by others
References
Daimler pedestrian benchmarks website: http://www.science.uva.nl/research/isla/downloads/pedestrians/. Accessed 24 June 2012
Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: people detection and articulated pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 1014–1021 (2009)
Bourdev, L., Maji, S., Malik, J.: Describing people: a poselet-based approach to attribute classification. In: IEEE 13th International Conference on Computer Vision (ICCV 2011) (2011)
Burges, C.J.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2, 121–167 (1998)
Cao, L., Dikmen, M., Fu, Y., Huang, T.: Gender labels on the CBCL pedestrian image database. http://www.ifp.illinois.edu/~cao4/data/gender_pedestrian_mm08.zip. Accessed 24 June 2012
Cao, L., Dikmen, M., Fu, Y., Huang, T.: Gender recognition from body. In: Proceedings of the 16th ACM international conference on Multimedia (MM’2008), pp. 725–728. ACM, New York (2008). doi:10.1145/1459359.1459470
Center for biological and computational learning (CBCL) at MIT: CBCL pedestrian image database website. http://cbcl.mit.edu/software-datasets/PedestrianData.html. Accessed 24 June 2012
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886–893 (2005)
Dollár, P., Tu, Z., Tao, H., Belongie, S.: Feature mining for image classification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), pp. 1–8 (2007)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 304–311 (2009)
Eckmann, J.P., Kamphorst, S.O., Ruelle, D.: Recurrence plots of dynamical systems. Europhys. Lett. 4(9), 973–977 (1987)
Enzweiler, M., Gavrila, D.M.: Monocular pedestrian detection: survey and experiments. IEEE Trans. Pattern Anal. Mach. Intell. 31, 2179–2195 (2009)
Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008). Software available at http://www.csie.ntu.edu.tw/~cjlin/liblinear
Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 1778–1785 (2009)
Fawcett, T.: An introduction to ROC analysis. Pattern Recognit. Lett. 27, 861–874 (2006)
Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vis. 61, 55–79 (2005)
Gavrila, D., Philomin, V.: Real-time object detection for ‘smart’ vehicles. In: IEEE 7th International Conference on Computer Vision (ICCV 1999), vol. 1, pp. 87–93 (1999)
Huang, J., Ling, C.X.: Using AUC and accuracy in evaluating learning algorithms. IEEE Trans. Knowl. Data Eng. 17(3), 299–310 (2005)
Ito, S., Kubota, S.: Object classification using heterogeneous co-occurrence features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) 11th European Conference on Computer Vision (ECCV 2010). Lecture Notes in Computer Science, vol. 6312, pp. 209–222. Springer, Berlin (2010)
Kozakaya, T., Ito, S., Kubota, S., Yamaguchi, O.: Cat face detection with two heterogeneous features. In: IEEE 16th International Conference on Image Processing (ICIP 2009), pp. 1213–1216 (2009)
Maji, S., Berg, A., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)
Marwan, N., Kurths, J., Saparin, P.: Generalised recurrence plot analysis for spatial data. Phys. Lett. A 360(4–5), 545–551 (2007)
Marwan, N., Romano, M.C., Thiel, M., Kurths, J.: Recurrence plots for the analysis of complex systems. Phys. Rep. 438(5–6), 237–329 (2007)
Mocenni, C., Facchini, A., Vicino, A.: Identifying the dynamics of complex spatio-temporal systems by spatial recurrence properties. Proc. Natl. Acad. Sci. USA 107(18), 8097–8102 (2010)
Munder, S., Gavrila, D.: An experimental study on pedestrian classification. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1863–1868 (2006)
Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.: Pedestrian detection using wavelet templates. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 1997), pp. 193–199 (1997). doi:10.1109/CVPR.1997.609319
Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), pp. 1–8. IEEE Computer Society, Los Alamitos (2007)
Serra-Toro, C., Traver, V.J.: A new pedestrian detection descriptor based on the use of spatial recurrences. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) Computer Analysis of Images and Patterns. Lecture Notes in Computer Science, vol. 6855, pp. 97–104. Springer, Berlin (2011)
Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)
Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010), pp. 1030–1037 (2010)
Watanabe, T., Ito, S., Yokoi, K.: Co-occurrence histograms of oriented gradients for pedestrian detection. In: Wada, T., Huang, F., Lin, S. (eds.) Advances in Image and Video Technology. Lecture Notes in Computer Science, vol. 5414, pp. 37–47. Springer, Berlin (2009)
Yuan, J., Yang, M., Wu, Y.: Mining discriminative co-occurrence patterns for visual recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2011), pp. 2777–2784 (2011)
Zhang, W., Zelinsky, G., Samaras, D.: Real-time accurate object detection using multiple resolutions. In: IEEE 11th International Conference on Computer Vision (ICCV 2007), pp. 1–8 (2007)
Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast human detection using a cascade of histograms of oriented gradients. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 1491–1498 (2006)
Acknowledgements
The authors acknowledge the Spanish research programme Consolider Ingenio-2010 CSD2007-00018, and Fundació Caixa-Castelló Bancaixa under project P1⋅1A2010-11. Carlos Serra-Toro is funded by Generalitat Valenciana under the “VALi+d program for research personnel in training” with grant code ACIF/2010/135. Part of this work was done while he was in a research stay funded by Generalitat Valenciana with grant code BEFPI/2012/030.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Serra-Toro, C., Traver, V.J. & Montoliu, R. Spatial Recurrences for Pedestrian Classification. J Math Imaging Vis 47, 108–123 (2013). https://doi.org/10.1007/s10851-012-0382-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-012-0382-7