Jackie Assa
Abstract
Illustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences. In this paper, we introduce a method that produces an action synopsis for presenting motion in still images. The method carefully selects key poses based on an analysis of a skeletal animation sequence, to facilitate expressing complex motions in a single image or a small number of concise views. Our approach is to embed the high-dimensional motion curve in a low-dimensional Euclidean space, where the main characteristics of the skeletal action are kept. The lower complexity of the embedded motion curve allows a simple iterative method which analyzes the curve and locates significant points, associated with the key poses of the original motion. We present methods for illustrating the selected poses in an image as a means to convey the action. We applied our methods to a variety of motions of human actions given either as 3D animation sequences or as video clips, and generated images that depict their synopsis.
Supplemental Material
- Agarwala, A., Dontcheva, M., Agrawala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D., and Cohen, M. 2004. Interactive digital photomontage. In ACM Transactions on Graphics, (SIGGRAPH), 294--302. Google Scholar
Digital Library
- Benabdelkader, C., Cutler, R., and Davis, L. 2004. Gait recognition using image self-similarity. EURASIP Journal on Applied Signal Processing 15, 4, 572--585. Google ScholarDigital Library
- Braun, M. 1992. Picturing Time. U. of Chicago, Reading, MA.Google Scholar
- Campbell, L. W., and Bobick, A. F. 1995. Recognition of human body motion using phase space constraints. In International Conference on Computer Vision, IEEE Computer Society, Washington, DC, USA, 624--630. Google ScholarDigital Library
- Cleveland, W., and Devlin, S. 1988. Locally weighted regression: An approach to regression analysis by local fitting. In J. of the American Statistical Association, vol. 83, 596--610.Google ScholarCross Ref
- Cooper, M., and Foote, J. 2002. Summarizing video using non-negative similarity matrix factorization. In IEEE Workshop on Multimedia Signal Processing.Google Scholar
- Cutting, J. E. 2002. Representing motion in a static image: constraints and parallels in art, science, and popular culture. Perception 31, 1165--1193.Google ScholarCross Ref
- Dementhon, D., Kobla, V., and Doermann, D. 1998. Video summarization by curve simplification. In Proceedings of the sixth ACM international conference on Multimedia, ACM Press, 211--218. Google ScholarDigital Library
- Elgammal, A., and Lee, C. 2004. Gait style and gait content: Bilinear model for gait recognition using gait re-sampling. In 6th International Conference on Automatic Face and Gesture Recognition, 624--630. Google ScholarDigital Library
- Fauvet, B., Bouthemy, P., Gros, P., and Spindler, F. 2004. A geometrical key-frame selection method exploiting dominant motion estimation in video. In Int. Conf. on Image and Video Retrieval, CIVR 2004, vol. 3115 of Lecture Notes in Computer Science, 419--427.Google ScholarCross Ref
- Gibson, S., Hubbold, R. J., Cook, J., and Howard, T. 2003. Interactive reconstruction of virtual environments from video sequences. Computers & Graphics 27, 2, 293--301.Google ScholarCross Ref
- Grochow, K., Martin, S., Hertzmann, A., and Popovic, Z. 2004. Style-based inverse kinematics. In ACM Transactions on Graphics, (SIGGRAPH), 522--531. Google ScholarDigital Library
- Irani, M., and Anandan, P. 1998. Video indexing based on mosaic representations. IEEE Trans. on Pattern Analysis and Machine Intelligence 86, 5, 905--921.Google Scholar
- Kayafas, G., and Jussim, E. 2000. Stopping Time: The Photographs of Harold Edgerton. Harry N Abrams, New York, NY.Google Scholar
- Kondo, K., and Matsuda, K. 2004. Keyframes extraction method for motion capture data. Journal for Geometry and Graphics 08, 081--090.Google Scholar
- Kovar, L., and Gleicher, M. 2004. Automated extraction and parameterization of motions in large data sets. ACM Trans. Graph. 23, 3, 559--568. Google ScholarDigital Library
- Kovar, L., Gleicher, M., and Pighin, F. 2002. Motion graphs. ACM Transactions on Graphics, (SIGGRAPH) 21, 3 (July), 473--482. Google ScholarDigital Library
- Kruskal, J. 1966. Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 29, 1--27.Google ScholarCross Ref
- Lee, J., Chai, J., Reitsma, P., Hodgins, J. K., and Pollard", N. 2002. Interactive control of avatars animated with human motion data. ACM Transactions on Graphics, (SIGGRAPH) 21, 3 (July), 491--500. Google ScholarDigital Library
- Lim, I. S., and Thalmann, D. 2001. Key-posture extraction out of human motion data by curve simplification. In 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2, 1167 -- 1169.Google Scholar
- Liu, F., Zhuang, Y., Wu, F., and Pan, Y. 2003. 3d motion retrieval with motion index tree. Comput. Vis. Image Underst. 92, 2-3, 265--284. Google ScholarDigital Library
- Loy, G., Sullivan, J., and Carlsson, S. 2003. Pose-based clustering in action sequences. In Workshop on Higher-Level Knowledge in 3D Modeling & Motion Analysis, 66--72. Google ScholarDigital Library
- Massey, M., and Bender, W. 1996. Salient stills: Process and practice. IBM Systems Journal 35, 3/4, 557-573. Google ScholarDigital Library
- Mcgee, V. C. 1978. Multidimensionnal scaling of n sets of similarity measures: A nonmetric individual differences approach. Multivariate Behaviour Research 3, 233--248.Google ScholarCross Ref
- Park, M. J., and Shin, S. Y. 2004. Example-based motion cloning. Computer Animation and Virtual Worlds 15, 3-4, 245--257. Google ScholarDigital Library
- Ramer, U. 1972. An iterative procedure for the polygonal approximation of plane curves. Computer Graphics and Image Processing 1, 3 (Nov.), 244--256.Google ScholarCross Ref
- Safonova, A., Hodgins, J. K., and Pollard, N. S. 2004. Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces. ACM Transactions on Graphics, (SIGGRAPH 23, 3, 514--521. Google ScholarDigital Library
- Shepard, R. 1962. Analysis of proximities: multidimensional scaling with an unknown distance function. Psychometrika 27, 125--139.Google ScholarCross Ref
- Szeliski, R., and Shum, H.-Y. 1997. Creating full view panoramic image mosaics and environment maps. In ACM Transactions on Graphics, (SIGGRAPH), 251--258. Google ScholarDigital Library
- Torgerson, W. 1952. Multidimensional scaling: I, theory and method. Psychometrika 17, 401--419.Google ScholarCross Ref
- Vermaak, J., Pirez, P., Gangnet, M., and Blake, A. 2002. Rapid summarisation and browsing of video sequences. In British Machine Vision Conference, BMVC, vol. 1.Google Scholar
- Wang, J., and Bodenheimer, B. 2003. An evaluation of a cost metric for selecting transitions between motion segments. In SCA '03: Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer animation, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, 232--238. Google ScholarDigital Library
- Ward, J. L. 1979. Perception and Pictorial Representation, vol. 1 of The Art of Computer Programming. Praeger, New York, ch. A piece of the action: Moving figures in still pictures, 246--271.Google Scholar
- Young, G., and Householder, A. S. 1941. A note on multidimensional psycho-physical analysis. Psychometrika, 331--333.Google Scholar
- Zelnik-Manor, L., and Irani, M. 2001. Event-based analysis of video. In IEEE Conference on Computer Vision and Pattern Recognition, 123--130.Google Scholar
Index Terms
- Action synopsis: pose selection and illustration
Recommendations
Action synopsis: pose selection and illustration
SIGGRAPH '05: ACM SIGGRAPH 2005 PapersIllustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences. In this paper, we introduce a method that produces an action synopsis for ...
Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition
In this paper, we learn explicit representations for dynamic shape manifolds of moving humans for the task of action recognition. We exploit locality preserving projections (LPP) for dimensionality reduction, leading to a low-dimensional embedding of ...
Charting-based subspace learning for video-based human action classification
We use charting, a non-linear dimensionality reduction algorithm, for articulated human motion classification in multi-view sequences or 3D data. Charting estimates automatically the intrinsic dimensionality of the latent subspace and preserves local ...
Comments