RPV-II: A Stream-Based Real-Time Parallel Vision System and Its Application to Real-Time Volume Reconstruction
In this paper, we present RPV-II, a stream-based real-time parallel image processing environment on distributed parallel computers, or PC-cluster, and its performance evaluation using a realistic application. The system is based on our previous PC-cluster system for real-time image processing and computer vision, and is designed to overcome the problems of our previous system, one of which is long latency when we use pipelined structures. This becomes a serious problem when we apply the system to interactive applications. To make the latency shorter, we have introduced stream data transfer, or fine grained data transfer, to RPV-II. One frame data is divided into small elements such as pixels, lines and voxels, and we have developed efficient real-time data transfer mechanism of those. Using RPV-II we have developed a real-time volume reconstruction system by visual volume intersection method, and we have measured the system performance. Experimental results show better performance than that of our previous system, RPV.
KeywordsVisual Cone Frame Period Pipeline Structure Voxel Space Data Processing Module
Unable to display preview. Download preview PDF.
- 1.T. Kanade, R. T. Collins, A. J. Lipton, P. Burt, and L. Wixson, “Cooperative multi-sensor video surveillance,” in Proc. of Image Understanding Workshop, pp.3–10, 1997.Google Scholar
- 2.T. Matsuyama, “Cooperative Distributed Vision–Integration of Visual Perception, Action, and Communication-,” in Proc. of Image Understanding Workshop, pp.1–39, 1998.Google Scholar
- 3.D. Arita, Y. Hamada, and R. Taniguchi, “A Real-time Distributed Video Image Processing System on PC-cluster,” in Proc. of Int. Conf. of the Austrian Center for Parallel Computation(ACPC), pp.296–305, 1999.Google Scholar
- 4.D. Arita, S. Yonemoto, and R. Taniguchi, “Real-time Computer Vision on PC-cluster and Its Application to Real-time Motion Capture,” in Proc. of IEEE Workshop on Computer Architectures for Machine Perception, pp.205–214, 2000.Google Scholar
- 5.T. Kanade, H. Saito, and S. Vedula, “The 3D room: Digitizing time-varying 3D events by synchronized multiple video streams,” in Technical Report, CMU-RI-TR-98-34, Carnegie Mellon University, Dec. 1998.Google Scholar
- 6.T. Wada, X. Wu, S. Tokai, and T. Matsuyama, “Homography Based Parallel Volume Intersection: Toward Real-time Volume Reconstruction Using Active Cameras,” in Proc. of IEEE Workshop on Computer Architectures for Machine Perception, pp.331–339, 2000.Google Scholar
- 7.E. Borovikov, and L. Davis, “A Distributed System for Real-time Volume Reconstruction,” in Proc. of IEEE Workshop on Computer Architectures for Machine Perception, pp.183–189, 2000.Google Scholar
- 8.W. N. Martin and J. K. Aggarwal, “Volumetric Description of Objects from Multiple Views,” in IEEE Trans. PAMI, Vol.5,No.2, pp.150–158, 1987.Google Scholar
- 9.1394 Trade Association, in 1394-based Digital Camera Specification Version 1.20.Google Scholar
- 10.H. Tezuka, A. Hori, Y. Ishikawa, and M. Sato, “PM: an operating system coordinated high performance communication library,” High-Performance Computing and Networking, P. Sloot and B. Hertzberger, in Springer-Verlag, pp.708–717, 1997.Google Scholar
- 11.H. Yoshimoto, D. Arita and R. Taniguchi, “Real-Time Image Processing on IEEE1394-based PC Cluster,” in CD-ROM Proc. of International Parallel & Distributed Processing Symposium, 2001.Google Scholar