Visual Categorization of Children and Adult Walking Styles
We present an approach for visual discrimination of children from adults in video using characteristic regularities present in their locomotion patterns. The framework employs computer vision to analyze correlated, scale invariant locomotion properties for classifying different styles of walking. Male and female subjects for the experiments include six children (3–5 yrs) and nine adults (30–52 yrs). For the analysis, we coordinate a minimalist point-representation of the human body with a space-time analysis of head and ankle trajectories to characterize the modality. Together the properties of relative stride length and stride frequency are shown to clearly differentiate children from adult walkers. The highly correlated log-linear relationships for the stride properties are exploited to reduce the categorization problem to a linear discrimination task. Using a trained two-class linear perceptron, we were able to achieve a correct classification rate of 93-95% on our dataset. Our approach emphasizing the natural modal behavior in human motion offers a useful and general methodology as the basis for designing efficient motion recognition systems using limited visual features.
KeywordsStride Length Visual Categorization Stride Frequency Computer Vision System Human Locomotion
Unable to display preview. Download preview PDF.
- 1.A. Baumberg and D. Hogg. Learning flexible models from image sequences. In Proc. European Conf. Comp. Vis., pages 299–308, 1994.Google Scholar
- 2.W. Boda, W. Tapp, and T. Findley. Biomechanical comparison of treadmill and overground walking. In Proc. Can. Soc. for Biomech., pages 88–89, 1994.Google Scholar
- 3.C. Bregler and J. Malik. Tracking people with twists and exponential maps. In Proc. Comp. Vis. and Pattern Rec., pages 8–15, 1998.Google Scholar
- 5.D. Gavrila. Pedestrian detection from a moving vehicle. In Proc. European Conf. Comp. Vis., pages 37–49, 2000.Google Scholar
- 7.I. Haritaoglu, D. Harwood, and L. Davis. W4: Who? When? Where? What? A real time system for detecting and tracking people. In Proc. Int. Conf. Auto. Face and Gesture Recog., pages 222–227, 1998.Google Scholar
- 9.V. Inman, H. Ralston, and F. Todd. Human Walking. Williams & Wilkins, Baltimore, 1981.Google Scholar
- 10.J. Little and J. Boyd. Describing motion for recognition. In Proc. Symp. Comp. Vis., pages 235–240. IEEE, 1995.Google Scholar
- 11.S. Niyogi and E. Adelson. Analyzing and recognizing walking figures in XYT. In Proc. Comp. Vis. and Pattern Rec., pages 469–474. IEEE, 1994.Google Scholar
- 12.M. Oren, C. Papageorgiour, P. Sinha, E. Osuma, and T. Poggio. Pedestrian detection using wavelet templates. In Proc. Comp. Vis. and Pattern Rec., pages 193–99. IEEE, 1997.Google Scholar
- 14.K. Rohr. Towards model-based recognition of human movements in image sequences. Comp. Vis., Graph., and Img. Proc., 59(1):94–115, 1994.Google Scholar