Abstract
This paper introduces a method based on robust statistics to build reliable gait signatures from averaging silhouette descriptions, mainly when gait sequences are affected by severe and persistent defects. The term robust refers to the ability of reducing the impact of silhouette defects (outliers) on the average gait pattern, while taking advantage of clean silhouette regions. An extensive experimental framework was defined based on injecting three types of realistic defects (salt and pepper noise, static occlusion, and dynamic occlusion) to clean gait sequences, both separately in an easy setting and jointly in a hard setting. The robust approach was compared against two other operation modes: (1) simple mean (weak baseline) and (2) defect exclusion (strong benchmark). Three gait representation methods based on silhouette averaging were used: Gait Energy Image (GEI), Gradient Histogram Energy Image (GHEI), and the joint use of GEI and HOG descriptors. Quality of gait signatures was assessed by their discriminant power in a large number of gait recognition tasks. Nonparametric statistical tests were applied on recognition results, searching for significant differences between operation modes.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
This scheme admits a series of half cycles.
In the case of GEI, \(v(\cdot )\) computes normalized Euclidean distances between vectors of grayscale pixel values, thus \(v(\cdot )\in [0,255]\), while in GHEI and GEI \(+\) HoG, \(v(\cdot )\) measures absolute differences between features normalized in [0, 1].
This is a particular case of having at least four cycles.
Note that each series includes results from both defective and clean scenarios together.
Performance curves from the other two methods are pretty similar to those from GEI showed in this section.
References
Alcalá-Fdez, J., Fernandez, A., Luengo, J., Derrac, J., Garca, S., Snchez, L., Herrera, F.: Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J. Mult. Valued Logic Soft Comput. 17, 255–287 (2011)
Barnett, V., Lewis, T.: Outliers in Statistical Data, vol. 3. Wiley, New York (1994)
Black, M., Rangarajan, A.: On the unification of line processes, outlier rejection, and robust statistics with applications in early vision. Int. J. Comput. Vis. 19(1), 57–91 (1996)
Chen, C., Liang, J., Zhao, H., Hu, H., Tian, J.: Frame difference energy image for gait recognition with incomplete silhouettes. Pattern Recognit. Lett. 30(11), 977–984 (2009)
Gross, R., Shi, J.: The CMU motion of body (MoBo) database. Technical Report CMU-RI-TR-01-18. Robotics Institute, Carnegie Mellon University, Pittsburgh, PA (2001)
Han, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. 28(2), 316–322 (2006)
Hofmann, M., Rigoll, G.: Exploiting gradient histograms for gait-based person identification. In: IEEE Image Processing, pp. 4171–4175 (2013)
Hofmann, M., Sural, S., Rigoll, G.: Gait recognition in presence of occlusion: a new dataset and baseline algorithms. In: WSCG, pp. 99–104 (2011)
Hofmann, M., Wolf, D., Rigoll, G.: Identification and reconstruction of complete gait cycles for person identification in crowded scenes. In: VISAPP, pp. 594–597 (2011)
Huber, P.: Robust Statistics. Wiley, New York (1981)
Jin, W., She, M., Nahavandi, S., Kouzani, A.: A review of vision-based gait recognition methods for human identification. In: DICTA, pp. 320–327 (2010)
Lee, L., Dalley, G., Tieu, K.: Learning pedestrian models for silhouette refinement. In: IEEE International Conference on Computer Vision, vol. 1, pp. 663–670 (2003)
Liang, W., Tieniu, T., Huazhong, N., Weiming, H.: Silhouette analysis-based gait recognition for human identification. IEEE Trans. Pattern Anal. 25(12), 1505–1518 (2003)
Liu, J., Zheng, N., Xiong, L.: Silhouette quality quantification for gait sequence analysis and recognition. Signal Process. 89(7), 1417–1427 (2009)
Liu, Z., Sarkar, S.: Effect of silhouette quality on hard problems in gait recognition. IEEE Trans. Syst. Man Cybern. B 35(2), 170–183 (2005)
Makihara, Y., Mannami, H., Tsuji, A., Hossain, M., Sugiura, K., Mori, A., Yagi, Y.: The OU-ISIR gait database comprising the treadmill dataset. IPSJ Trans. Comput. Vis. Appl. 4, 53–62 (2012)
Maronna, R.A., Martin, D.R., Yohai, V.J.: Robust Statistics: Theory and Methods. Wiley, New York (2006)
Martín-Félez, R., Ortells, J., Mollineda, R.A.: Exploring the effects of video length on gait recognition. In: International Conference on Pattern Recognition, pp. 3411–3414 (2012)
Martín-Félez, R., Xiang, T.: Gait recognition by ranking. In: ECCV Lecture Notes on Computer Science, vol. 7572, pp. 328–341 (2012)
Ortells, J., Martín-Félez, R., Mollineda, R.A.: A complexity measure of gait perception. In: Pattern Recognition and Image Analysis, Lecture Notes on Computer Science, vol. 7887, pp. 492–499 (2013)
Rey, W.: Introduction to Robust and Quasi-Robust Statistical Methods. Springer, Heidelberg (1983)
Roy, A., Chattopadhyay, P., Sural, S., Mukherjee, J., Rigoll, G.: Modelling, synthesis and characterization of occlusion in videos. IET Comput. Vis. 9(6), 821–830 (2015)
Roy, A., Sural, S., Mukherjee, J., Rigoll, G.: Occlusion detection and gait silhouette reconstruction from degraded scenes. Signal Image Video Process. 5(4), 415–430 (2011)
Sarkar, S., Phillips, P., Liu, Z., Vega, I., Grother, P., Bowyer, K.: The humanId gait challenge problem: data sets, performance and analysis. IEEE Trans. Pattern Anal. 27(2), 162–177 (2005)
Schafer, R.C.: Clinical Biomechanics: Musculoskeletal Actions and Reactions. Williams & Wilkins, Philadelphia (1987)
Shu, G., Dehghan, A., Oreifej, O., Hand, E., Shah, M.: Part-based multiple-person tracking with partial occlusion handling. In: Proceedings on CVPR IEEE, pp. 1815–1821 (2012)
Sivapalan, S., Chen, D., Denman, S., Sridharan, S., Fookes, C.: Histogram of weighted local directions for gait recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 125–130 (2013)
Tukey, J.W.: Exploratory Data Analysis. Addison-Wesley, Boston (1977)
Whytock, T., Belyaev, A., Robertson, N.: Improving robustness and precision in GEI \(+\) HOG action recognition. In: Advances in Visual Computing, Lecture Notes in Computer Science, vol. 8033, pp. 119–128 (2013)
Whytock, T., Belyaev, A., Robertson, N.: On covariate factor detection and removal for robust gait recognition. Mach. Vis. Appl. 26(5), 661–674 (2015)
Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1(6), 80–83 (1945)
Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int. J. Comput. Vis. 75(2), 247–266 (2007)
Yu, S., Tan, D., Huang, K., Tan, T.: Reducing the effect of noise on human contour in gait recognition. In: Advances in Biometrics, Lecture Notes in Computer Science, vol. 4642, pp. 338–346 (2007)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: International Conference on Pattern Recognition, pp. 441–444 (2006)
Zhao, G., Cui, L., Li, H.: Gait recognition using fractal scale. Pattern Anal. Appl. 10(3), 235–246 (2007)
Zhou, Z., Prugel-Bennett, A., Damper, R.: A Bayesian framework for extracting human gait using strong prior knowledge. IEEE Trans. Pattern Anal. 28(11), 1738–1752 (2006)
Acknowledgments
This work has been supported by the grants P1-1B2012-22 and PREDOC/2012/05 from Universitat Jaume I, PROMETEOII/2014/062 from Generalitat Valenciana, and TIN2013-46522-P from Spanish Ministry of Economy and Competitiveness.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ortells, J., Mollineda, R.A., Mederos, B. et al. Gait recognition from corrupted silhouettes: a robust statistical approach. Machine Vision and Applications 28, 15–33 (2017). https://doi.org/10.1007/s00138-016-0798-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-016-0798-y