Moving object recognition in eigenspace representation: gait analysis and lip reading

This paper describes a new method to calculate the spatio-temporal correlation efficiently in a parametric eigenspace representation for moving object recognition. A parametric eigenspace compactly represents the temporal change of an image sequence by a trajectory in the eigenspace. This representation reduces the computational cost of correlation-based comparison between image sequences. Experiments for human gait analysis and lip reading show this method is computationally useful for motion analysis and recognition.

[1]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[2]  Hiroshi Murase,et al.  Learning and recognition of 3D objects from appearance , 1993, [1993] Proceedings IEEE Workshop on Qualitative Vision.

[3]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[4]  Erkki Oja,et al.  Subspace methods of pattern recognition , 1983 .

[5]  Edward H. Adelson,et al.  Analyzing and recognizing walking figures in XYT , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Randal C. Nelson,et al.  Detecting activities , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Jake K. Aggarwal,et al.  On the computation of motion from sequences of images-A review , 1988, Proc. IEEE.

[8]  Hiroshi Murase,et al.  Learning, positioning, and tracking visual appearance , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[9]  Hiroshi Murase,et al.  Illumination Planning for Object Recognition Using Parametric Eigenspaces , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  J. Cutting,et al.  Recognizing friends by their walk: Gait perception without familiarity cues , 1977 .

[11]  Yochai Konig,et al.  "Eigenlips" for robust speech recognition , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Alberto Del Bimbo,et al.  Behavioral object recognition from multiple image frames , 1992, Signal Process..

[13]  Thomas S. Huang,et al.  Image processing , 1971 .

[14]  Karl Rohr,et al.  Incremental recognition of pedestrians from image sequences , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.