Abstract
This paper presents a generic framework for on-line reconfiguration of a multi-camera active-vision system for time-varying-geometry object/subject action recognition. The proposed methodology utilizes customizable pipeline architecture to select optimal camera poses in real time. Subject visibility is optimized via a depth-limited search algorithm. All stages are developed with real-time operation as the central focus. A human action-sensing implementation example demonstrates viability. Controlled experiments, first with a human analogue and, subsequently, with a real human, illustrate the workings of the proposed framework. A tangible increase in action-recognition success rate over other strategies, particularly those with static cameras, is noteworthy. The proposed framework is also shown to operate in real-time. Further experiments examine the effect of scaling the number of obstacles and cameras, sensing-system mobility, and library actions on real-time performance.
Similar content being viewed by others
References
Capin, T.K., Pandzic, I.S., Thalmann, N.M., Thalmann, D.: A dead-reckoning algorithm for virtual human figures. In: Proceedings of the 1997 Virtual Reality Annual International Symposium (VRAIS ’97), Albuquerque, NM., USA (1997)
Tarabanis, K.A., Allen, P.K., Tsai, R.Y.: A survey of sensor planning in computer vision. IEEE Trans. Robot. Autom. 11(1), 86–104 (1995)
Szeliski, R.: Computer Vision: Algorithms and Applications, 1st edn. Springer-Verlag LLC., New York (2010)
Chellappa, R., Roy-Chowdhury, A.K., Zhou, S.K.: Human Activity Recognition, pp. 53–92. Morgan & Claypool Publishing, San Rafael (2005)
Veres, G.V., Gordon, L., Carter, J.N., Nixon, M.S.: What image information is important in silhouette-based gait recognition? In: IEEE Conference on Computer Vision and Pattern Recognition. Washington, D.C. (2004)
deRuiter, H., Benhabib, B.: Object-of-interest selection for model-based 3d pose tracking with background clutter. In: Proceedings of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering (CISSE07) (2008)
Wang, X., Wang, S., Bi, D.: Distributed visual-target-surveillance system in wireless sensor networks. IEEE Trans. Syst. Man Cybern. B Cybern. 39(5), 1134–1146 (2009)
Lee, C.-S., Elgammal, A.: Dynamic shape outlier detection for human locomotion. Comput. Vis. Image Underst. 113(3), 332–344 (2009)
Lu, J., Zhang, E.: Gait recognition for human identification based on ICA and fuzzy SVM through multiple views fusion. Pattern Recogn. Lett. 28(16), 2401–2411 (2007)
Roy, A., Sural, S.: A fuzzy inferencing system for gait recognition. In: Proceedings of the 28th North American Fuzzy Information Processing Society Annual Conference, Cincinnati, OH (2009)
Lam, T.H.W., Lee, R.S.T.: A new representation for human gait recognition: Motion Silhouettes Image (MSI). Lect. Notes Comput. Sci. 3832, 612–618 (2005)
Ioannidis, D., Tzovaras, D., Moustakas, K.: Gait identification using the 3D protrusion transform. In: Proceedings of the IEEE International Conference on Image Processing (ICIP07). San Antonio, TX (2007)
Xu, D., Yan, S., Tao, D., Zhang, L., Li, X., Zhang, H.: Human gait recognition with matrix representation. IEEE Trans. Circuits Syst. Video Technol. 16(7), 896–903 (2006)
Guo, B., Nixon, M.S.: Gait feature subset selection by mutual information. IEEE Trans. Syst. Man Cybern., Part A, Syst. Humans 39(1), 36–46 (2009)
Liu, Z., Sarkar, S.: Effect of silhouette quality on hard problems in gait recognition. IEEE Trans. Syst. Man Cybern. B Cybern. 35(2), 170–183 (2005)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing, and carrying condition on gait recognition. In: International Conference on Pattern Recognition, Hong Kong (2006)
Mittal, A.: Generalized multi-sensor planning. In: European Conference on Computer Vision. Graz, Austria (2006)
Miura, J., Ikeuchi, K.: Task-oriented generation of visual sensing strategies in assembly tasks. IEEE Trans. Pattern Anal. Mach. Intell. 20(2), 126–138 (1998)
Bakhtari, A.: Multi-Target Surveillance in Dynamic Environments: Sensing-System Reconfiguration. Toronto, ON, Canada (2006)
Gu, X., Marefat, M.M., Ciarallo, F.W.: A robust approach for sensor placement in automated vision dimensional inspection. In: IEEE International Conference on Robotics and Automation, Michigan (1999)
Cowan, C.K., Kovesik, P.D.: Automated sensor placement from vision task requirements. IEEE Trans. Pattern Anal. Mach. Intell. 10(3), 407–416 (1988)
Sakane, S., Ishii, M., Kakikura, M.: Occlusion avoidance of visual sensors based on a hand-eye action simulator system: HEAVEN. Adv. Robot. 2(2), 149–165 (1987)
Sakane, S., Sato, T., Kakikura, M.: Model-based planning of visual sensors using a Hand-eye action simulator: HEAVEN. In: Conference on Advanced Robotics, Versailles, France (1987)
Reed, M.K., Allen, P.K.: Constraint-based sesor planning for scene modeling. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1460–1467 (2000)
Pito, R.: A solution to the next best view problem for automated surface acquisition. IEEE Trans. Pattern Anal. Mach. Intell. 21(10), 1016–1030 (1999)
Hodge, L., Kamel, M.: An agent-based approach to multi-sensor coordination. IEEE Trans. Syst. Man Cybern., Part A, Syst. Humans 33(5), 648–662 (2003)
Murrieta-Cid, R., Tovar, B., Hutchinson, S.: A sampling-based motion planning approach to maintain visibility of unpredictable targets. J. Auto. Rob. 19(3), 285–300 (2005)
Naish, M.D., Croft, E.A., Benhabib, B.: Coordinated dispatching of proximity sensors for the surveillance of maneuvering targets. J. Rob. CIM. 19(3), 283–299 (2003)
Bakhtari, A., Benhabib, B.: An active vision system for multi-target surveillance in dynamic environments. IEEE Trans. Syst. Man Cybern. 37(1), 190–198 (2007)
Bakhtari, A., Mackay, M., Benhabib, B.: Active-vision for the autonomous surveillance of dynamic, multi-object environments. J. Intell. Robot. Syst. 54(4), 567–593 (2009)
Gall, J., Stoll, C., de Aguiar, E., Theobalt, C., Rosenhahn, B., Seidel, H.P.: Motion capture using joint skeleton tracking and surface estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09), (2009)
Mackay, M., Fenton, R.G., Benhabib, B.: Time-varying-geometry object surveillance using a multi-camera active-vision system. JSSIS 1(3), 679–704 (2008)
Mackay, M., Benhabib, B.: Active-vision system reconfiguration for form recognition in the presence of dynamic obstacles. In: Lecture Notes on Computer Science, Conference on Articulated Motion and Deformable Objects, Andratx, Mallorca, Spain (2008)
Tomori, Z., Gargalik, R., Hrmo, I.: active segmentation in 3D using kinect sensor. In: Proceedings of the 20th International Conference on Computer Graphics, Visualization, and Computer Vision. Pilsen, Czech Republic (2012)
Williams, S.A.: Programming Models For Parallel Systems. Wiley, New York (1990)
Mackay, M., Benhabib, B.: A multi-camera active-vision system for dynamic form recognition. In: Innovations and Advanced Techniques in Systems, Computing Sciences and Software Engineering, pp. 26–31. Springer Science and Business Media B.V. (2008)
Himmelblau, M.D.: Applied Non-Linear Programming. McGraw Hill (1972)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: From Proceedings of Imaging Understanding Workshop, pp. 121–130 (1981)
Author information
Authors and Affiliations
Corresponding author
Electronic Supplementary Material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Mackay, M., Fenton, R.G. & Benhabib, B. Pipeline-Architecture Based Real-Time Active-Vision for Human-Action Recognition. J Intell Robot Syst 72, 385–407 (2013). https://doi.org/10.1007/s10846-012-9810-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-012-9810-6