ABSTRACT
This paper is focused on a central aspect in the design of our planned digital library for human movement, i.e. on the aspect of representation and recognition of human activity from video data. The method of representation is important since it has a major impact on the design of all the other building blocks of our system such as the user interface/query block or the activity recognition/storage block. In this paper we evaluate a representation method for human movement that is based on sequences of angular poses and angular velocities of the human skeletal joints, for storage and retrieval of human actions in video databases. The choice of a representation method plays an important role in the database structure, search methods, storage efficiency etc.. For this representation, we develop a novel approach for complex human activity recognition by employing multidimensional indexing combined with temporal or sequential correlation. This scheme is then evaluated with respect to its efficiency in storage and retrieval.
For the indexing we use postures of humans in videos that are decomposed into a set of multidimensional tuples which represent the poses/velocities of human body parts such as arms, legs and torso. Three novel methods for human activity recognition are theoretically and experimentally compared. The methods require only a few sparsely sampled human postures. We also achieve speed invariant recognition of activities by eliminating the time factor and replacing it with sequence information. The indexing approach also provides robust recognition and an efficient storage/retrieval of all the activities in a small set of hash tables.
- 1.C. Barron and I. A. Kakadiaris. Estimation anthropometry and pose from a single image. Proc. Conf. Computer Vision and Pattern Recognition, pages 669-676, June 2000.Google Scholar
- 2.C. Bregler and J. Mallik. Tracking people with twists and exponential maps. Proc. IEEE 1998 Int'l Conf. Computer Vision and Pattern Recognition (CVPR'98), pages 8-15, June 1998. Google ScholarDigital Library
- 3.S. K. Chang, Q. Y. Shi, and C. W. Yan. Iconic indexing by 2-d strings. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(3):413-427, July 1987. Google ScholarDigital Library
- 4.L. Concalves, E. Bernardo, E. Ursella, and P. Perona. Monocular tracking of human arm in 3d. Proc. 1995 International Conference on Computer Vision, 1995. Google ScholarDigital Library
- 5.A. Del-Bimbo, E. Vicario, and D. Zingoni. Symbolic description and visual querying of image sequences using spatiotemporal logic. IEEE Transactions on Knowledge and Data Engineering, 7(4):609-622, August 1995. Google ScholarDigital Library
- 6.D. Gavrila and L. Davis. Towards 3-d model-based tracking and recognition of human movements. Proc. of the 1995 Int. Workshop on Automatic Face and Gesture Recognition, 1995.Google Scholar
- 7.A. H. Guest. Dance notation: The process of recording movement on paper. London:Dance Books, 1984.Google Scholar
- 8.A. H. Guest. Chore-graphics: A comparison of dance notation systems from the fifteenth century to the present. Systems from the Fifteenth Century to the Present, Gordon and Breach Science Publishers S. A., 1989.Google Scholar
- 9.D. Herbison-Evans. Dance, video, notation and computers. Leonardo, 1988.Google Scholar
- 10.D. Hogg. A program to see a walking person. Image and Vision Computing, 5(20), 1983.Google Scholar
- 11.S. JU, M. Black, and Y. Yacoob. Cardboard people: A parameterized model of articulated motion. 2nd Int. Conf. on Automatic Face and Gesture Recognition, pages 38-44, 1996. Google ScholarDigital Library
- 12.E. Jungert. The observer's point of view, an extension of sympolic projections. Prof.In. Conf. of Theories and Methods of Spatio-Teporal Reasoning in Geopraphic Space, pages 179-195, September 1992. Google ScholarDigital Library
- 13.I. A. Kakadiaris and D. Metaxas. Model-based estimation of 3d human motion with occlusion based on active multi-viewpoint selection. Proc. 1996 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'96), 1996. Google ScholarDigital Library
- 14.T. K. Moon and W. C. Stirling. Mathematical Methods and Algorithms for Signal Processing. Prentice Hall Inc., 2000.Google Scholar
- 15.R. M. Murray, Z. Li, and S. S. Sastry. A Mathematical Approach to Robotic Manipulation. CRC Press Inc., 1994. Google ScholarDigital Library
- 16.T. M. Naoyuki Sawasaki and T. Uchiyama. Design and implementation of high-speed visual tracking system for real-time motion analysis. Proc. of ICPR 1996, pages 478-484, 1996. Google ScholarDigital Library
- 17.J. Regh and T. Kanade. Model-based tracking of self-occluding articulated objects. Proc. 1995 International Conference on Computer Vision, 1995. Google ScholarDigital Library
- 18.K. Rohr. Incremental recognition of pedestrians from image sequences. Proc. 1995 Comp. Soc. Conference on Computer Vision and Pattern Recognition, pages 8-13, June 1993.Google ScholarCross Ref
- 19.R. J. Schilling. Fundamentals of Robotic Analysis & Control. Prentice Hall Inc., 1990. Google ScholarDigital Library
- 20.J. Schlenzig, E. Hunter, and R. Jain. Vision based hand gesture interpretation using recursive estimation. Proceedings of the 28th Asilmoar Conference on Signals, Systems and Computers, 1994.Google ScholarCross Ref
- 21.J. Schwartz, Y. Lamdan, and H. Wolfson. Geometric hashing : A general and efficient model-based recognition scheme. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pages 335-344, 1988.Google Scholar
- 22.A. P. Sistla and O. Wolfson. Temporal triggers in active database systems. IEEE Transactions on Knowledge and Data Engineering, 7(3), June 1995. Google ScholarDigital Library
- 23.T. Starner and A. Pentland. Real time american sign language recognition from video using hidden markov models. Proceedings of the International Symposium on Computer Vision, 1996.Google Scholar
- 24.A. D. Wilson, A. F. Bobick, and J. Cassell. Temporal classification of natural gesture and application to video coding. IEEE Comp. Soc. Conf. on Computer Vision and Pattern Recognition, pages 948-854, June 1997. Google ScholarDigital Library
Index Terms
- Design of a digital library for human movement
Recommendations
Human Activity Recognition Using Multidimensional Indexing
In this paper, we develop a novel method for view-based recognition of human action/activity from videos. By observing just a few frames, we can identify the activity that takes place in a video sequence. The basic idea of our method is that activities ...
Human Body Parts Tracking Using Torso Tracking: Applications to Activity Recognition
ITNG '12: Proceedings of the 2012 Ninth International Conference on Information Technology - New GenerationsThis paper proposed an approach for human body part tracking which is based on torso tracking. The main goal in this paper is tracking main human body parts such as torso, head and hands. In the proposed method for human body part tracking, we are using ...
A spanning tree-based human activity prediction system using life logs from depth silhouette-based human activity recognition
CAIP'11: Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part IIn this work, we propose a Human Activity Prediction (HAP) system using activity sequence spanning trees constructed from a life-log created by a video sensor-based daily Human Activity Recognition (HAR) system using time-sequential Independent ...
Comments