Uniprojective Features for Gait Recognition
Recent studies have shown that shape cues should dominate gait recognition. This motivates us to perform gait recognition through shape features in 2D human silhouettes. In this paper, we propose six simple projective features to describe human gait and compare eight kinds of projective features to figure out which projective directions are important to walker recognition. First, we normalize each original human silhouette into a square form. Inspired by the pure horizontal and vertical projections used in the frieze gait patterns, we explore the positive and negative diagonal projections with or without normalizing silhouette projections and obtain six new uniprojective features to characterize walking gait. Then this paper applies principal component analysis (PCA) to reduce the dimension of raw gait features. Finally, we recognize unknown gait sequences using the Mahalanobis-distance-based nearest neighbor rule. Experimental results show that the horizontal and diagonal projections have more discriminative clues for the side-view gait recognition and that the projective normalization generally can improve the robustness of projective features against the noise in human silhouettes.
KeywordsGait recognition projective features PCA
Unable to display preview. Download preview PDF.
- 1.Collins, R., Gross, R., Shi, J.: Silhouette-based human identification from body shape and gait. In: Proc. Automatic Face and Gesture Recognition, pp. 366–371 (2002)Google Scholar
- 2.Cunado, D., Nixon, M., Carter, J.: Automatic extraction and description of human gait model for recognition purposes. CVIU 90(1), 1–41 (2003)Google Scholar
- 3.Cutting, J.E., Kozlowski, L.T.: Recognizing friends by their walk: Gait perception without familarity cues. Bulletin of the Psychonomic Society 9(5), 353–356 (1977)Google Scholar
- 5.Liu, Y., Collins, R., Tsin, Y.: Gait sequence analysis using frieze patterns. In: Proc. ECCV (2002)Google Scholar
- 7.Sarkar, S., Philips, P., Liu, Z., Vega, I., Grother, P., Bowyer, K.: The human gait challenge problem: data sets, performance and analysis. PAMI 27(2), 162–177 (2005)Google Scholar
- 8.Tan, D., Huang, K., Yu, S., Tan, T.: Efficient night gait recognition based on template matching. In: Proc. ICPR, pp. 1000–1003 (2006)Google Scholar
- 9.Urtasun, R., Fua, P.: 3d tracking for gait characterization and recognition. In: Proc. Automatic Face and Gesture Recognition, pp. 17–22 (2004)Google Scholar
- 10.Veeraraghavan, A., Roy-Chowdhury, A., Chellappa, R.: Matching shape sequences in video with applications in human movement analysis. PAMI 27(12), 1896–1909 (2005)Google Scholar
- 11.Wang, L., Tan, T., Hu, W., Ning, H.: Silhouette analysis-based gait recognition for human identification. PAMI 25(12), 1505–1518 (2003)Google Scholar
- 12.Yu, S., Tan, D., Tan, T.: Modelling the effect of view angle variation on appearance-based gait recognition. In: Proc. ACCV, pp. 807–816 (2006)Google Scholar