Dr. Webb's research interests lie at the intersection of parallel computing and computer vision, and he has published extensively in these areas. He contributed to the design of the Carnegie Mellon Warp machine and the Carnegie Mellon-Intel Corporation iWarp Computer, and developed applications in computer vision and image processing for those machines. In particular, he guided the use of the Warp machine on the Navlab autonomous land vehicle.
His current interests lie in the use of high performance computers in computer vision systems. To this end, he has developed the fastest stereo vision system ever constructed: it is an implementation of Kanade-Okutomi multi-baseline stereo on a 64-cell iWarp computer, which fuses 240x256 images from three cameras to recover 16 depth levels at 15 Hertz.
I am also associated with the Maui High Performance Computing Center.
Structure from motion of rigid and jointed objects, with J. K. Aggarwal, Artificial Intelligence, 19, 1982. 107-130. Also presented at the Seventh International Joint Conference on Artificial Intelligence, Vancouver, Canada, 1981.
Shape and correspondence, with J. K. Aggarwal, Computer Vision, Graphics, and Image Processing, 21, 1983. 145-160. Also presented at the IEEE Workshop on Computer Vision: Representation and Control, Rindge, NH. 1982.
Mapping Image Processing Operations onto a Linear Systolic Machine, with H. T. Kung, Distributed Computing, 1, 4, October, 1986.
The Warp Computer: Architecture, Implementation and Performance, Annaratone, M., Arnould, E., Gross, T., Kung, H. T., Lam, M., Menzilcioglu, O. and Webb, J. A., IEEE Transactions on Computers, C-36, (12), December, 1987.
An Architecture Independent Programming Language for Low-Level Vision, 4, 1989, Computer Vision, Graphics, and Image Processing, 246-264.
Architecture Independent Image Processing: Performance of Apply on Diverse Architectures, Richard Wallace and I-Chen Wu, 4, 1989, Computer Vision, Graphics, and Image Processing, 265-276. Also presented at The Third International Conference on Supercomputing, Boston, MA, May, 1988.
Implementation of Apply on a transputer array, with H. Wang and P. Dew, Concurrency: Practice and Experience, 3 (1), 43-54, February, 1991.
The Warp Machine on Navlab, with J. Crisman, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13 (5), 451-465, May, 1991.
Implementation of Apply on a Transputer Array, with H. Wang and P. M. Dew, Concurrency: Practice and Experience, 3, (1), 43-54, 1991.
Steps Towards Architecture-Independent Image Processing. IEEE Computer, 25, (2), 21-31, February, 1992.
Structure from motion of rigid and jointed objects, with J. K. Aggarwal, Presented at the Seventh International Joint Conference on Artificial Intelligence, Vancouver, Canada, 1981. Also appeared in Artificial Intelligence.
Quaternions for computer vision and robotics, with E. Pervin. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Washington, D.C., 1983. Also appeared as technical report.
The shape of subjective contours, with E. Pervin, in Proceedings of the National Conference on Artificial Intelligence, Austin, Texas, 1984.
Warp as a Machine for Low-level Vision, with T. Gross, H. T. Kung, and M. Lam, Proceeding of the 1985 IEEE International Conference on Robotics and Automation, St. Louis, Mo.
Progress in Robot Road-following, with R. Wallace, K. Matsuzaki, Y. Goto, J. Crisman, T. Kanade, Proceedings of the 1986 IEEE International Conference on Robotics and Automation, San Francisco, Ca.
Warp Architecture and Implementation, with M. Annaratone, E. Arnould, H. T. Kung, M. Lam, O. Menzilcioglu, and K. Sarocky, in Conference Proceedings of the 13th Annual International Symposium on Computer Architecture, 1986.
Architecture of Warp, with M. Annaratone, E. Arnould, R. Cohn, T. Gross, M. Lam, O. Menzilcioglu, K. Sarocky, and J. Senko, in COMPCON Spring 1987, San Francisco, California.
Applications and algorithm partitioning on Warp, with M. Annaratone, F. Bitz, E. Clune, H. T. Kung, P. Maulik, H. Ribas, P. Tseng, in COMPCON Spring 1987, San Francisco, California.
Applications experience on Warp, with M. Annaratone, F. Bitz, J. Deutch, L. Hamey, H. T. Kung, P. Maulik, H. Ribas, and P. Tseng, in Proceedings of the 1987 National Computer Conference.
Warp architecture: from prototype to production, with M. Annaratone, E. Arnould, R. Cohn, T. Gross, H. T. Kung, O. Menzilcioglu, K. Sarocky, and J. Senko, in Proceedings of the 1987 National Computer Conference.
Implementation and Performance of a Complex Vision System on a Systolic Array, Ed Clune, Jill D. Crisman, Gudrun J. Klinker, and Jon A. Webb, presented at the International Conference on the Frontiers in Computing, Amsterdam, The Netherlands, December, 1987. Also published as a technical report, and in Future Generations Computer Systems.
Performance of Warp on the DARPA Architecture Benchmarks, Jeff Deutch, P. C. Maulik, Ravi Mosur, Harry Printz, Hudson Ribas, John Senko, P. S. Tseng, Jon A. Webb, and I-Chen Wu, in the International Conference on Parallel Processing for Computer Vision and Display, Leeds, England, January, 1988. Also published as technical report.
iWarp: An Integrated Solution to high-speed parallel computing, with S. Borkar, R. Cohn, G. Cox, S. Gleason, T. Gross, H. T. Kung, M. Lam, B. Moore, C. Peterson, J. Pieper, L. Rankin, P. S. Tseng, J. Sutton, and J. Urbanski. Proceedings of the Supercomputing Conference, Orlando, FL, November, 1988.
Apply, a common language for low- to mid-level vision on diverse architectures, presented at the IJCAI-89 Workshop on Parallel Algorithms, Detroit, Michigan, August, 1989.
APPLY: Machine Independent Image Processing Language and its Implementation on a Meiko Computing Surface, with P. M. Dew and H. Wang, Proceedings of the Fifth Alvey Vision Conference, University of Reading, England. September, 1989.
Supporting Systolic and Memory Communication in iWarp, with S. Borkar, R. Cohn, G. Cox, T. Gross, H. T. Kung, M. Lam, M. Levine, B. Moore, W. Moore, C. Peterson, J. Susman, J. Sutton, and J. Urbanski, Proceedings of the 17th Annual International Symposium on Computer Architecture, Seattle, Washington, May 28-31, 1990.
Building Blocks for a New Generation of Application-Specific Computing Systems, with B. Baxter, G. Cox, T. Gross, H. T. Kung, D. O'Hallaron, C. Peterson, and P. Wiley, International Conference on Application Specific Array Processors, Princeton, NJ, September, 1990.
Connected Components with Split and Merge, with J. Kistler, International Parallel Processing Symposium, Anaheim, CA, April 30-May 2, 1991.
Accurate Parallel Digital Halftoning, Society for Information Display, Anaheim, CA, May 6-10, 1991.
Accurate halftoning using the Gibbs sampler, pp. 280-288, Image Processing Algorithms and Techniques III, Proceedings SPIE Volume 1657, Ed. James R. Sullivan, Majid Rabbani, and Benjamin M. Dawson, 10-13 Februay, 1992, San Jose, CA.
Unifying concepts in architecture-independent parallel image processing in Adapt, pp. 228-239, Image Processing and Interchange: Implementation and Systems, Proceedings SPIE Volume 1659, Ed. Ronald B. Arps and William K. Pratt, 12-14 February, 1992, San Jose, CA.
Real Time Supercomputing on iWarp, with Bruce Greer, pp. 12-23, Image Processing and Interchange: Implementation and Systems, Proceedings SPIE Volume 1659, Ed. Ronald B. Arps and William K. Pratt, 12-14 February, 1992, San Jose, CA.
Latency and bandwidth considerations in parallel robotics image processing, Supercomputing `93, November, 1993. Portland, OR.
Implementation and performance of fast parallel multi-baseline stereo vision, Computer Architectures for Machine Perception, December, 1993. New Orleans, LA. Also appeared in ARPA Image Understanding Workshop, Washington, D.C.
Low-level vision on Warp and the Apply programming model, with L Hamey and I-C Wu. In Parallel Computation and Computers for Artificial Intelligence, ed. J. Kowalik. Kluwer, 1987. A later version of this paper appears in Computer Vision, Graphics, and Image Processing.
Machine independent parallel image processing. To appear in Parallel Architectures and Algorithms for Image Understanding, ed. V. P. Kumar, Academic Press, 1990.
The Warp machine on NAVLAB, with J. Crisman. In Vision and Navigation: The Carnegie Mellon Navlab, ed. C. Thorpe, Kluwer, 1990.
Parallel Affine Image Warping, with G. Gusciora. To appear in Parallel Processing for Artificial Intelligence, ed. L. N. Kanal, North-Holland, 1993.
Representation and processing of perceptible knowledge, with J. Perlmutter, in American Association for the study of mental imagery, Minneapolis, Minnesota.
Observing jointed objects, with J. K. Aggarwal, Solicited paper at the Fifth International Conference on Pattern Recognition, Miami, FL, 1980. 1246-1250.
Global Operations on a Systolic Array Machine, with H. T. Kung, Proceedings of the 1985 Computers and Aerospace V Conference, American Institute of Aeronautics and Astronautics, October, 1985.
Implementation and Performance of a Complex Vision System on a Systolic Array, Ed Clune, Jill D. Crisman, Gudrun J. Klinker, and Jon A. Webb, in Future Generations Computer Systems, 4, 15-29, 1988. Also published as Technical report CMU-RI-TR-87-16, Robotics Institute, Carnegie-Mellon University, Pittsburgh, PA, 1987.
Object recognition on a systolic array, with Claire Bono, solicited paper at The Third International Conference on Supercomputing, Boston, MA, May, 1988. Also published as Technical report CMU-RI-TR-87-21, Robotics Institute, Carnegie-Mellon University, Pittsburgh, PA, 1987.
Performance of Warp on the DARPA Architecture Benchmarks, Jeff Deutch, P. C. Maulik, Ravi Mosur, Harry Printz, Hudson Ribas, John Senko, P. S. Tseng, Jon A. Webb, and I-Chen Wu, Technical report CMU-CS-87-148, Computer Science Department, Carnegie-Mellon University, Pittsburgh, PA, 1987. Also appeared in International Conference on Parallel Processing for Computer Vision and Display.
End of Year Report for Parallel Vision Algorithm Design and Implementation, T. Kanade and J. A. Webb, Technical report CMU-RI-TR-87-15, Robotics Institute, Carnegie-Mellon University, Pittsburgh, PA, 1987.
Parallel algorithms and architectures: report of a workshop, with D. A. Buell, D. A. Carlson, Y.-C. Chow, K. Culik, N. Deo, R. Finkel, E. N. Houstis, E. M. Jacobson, Z. M. Kedem, J. S. Kowalik, P. J. Kuekes, J. L. Martin, G. A. Michael, N. S. Ostlund, J. Potter, D. K. Pardhan, M. J. Quinn, G. S. Stewart, Q. F. Stout, and L. Watson, in The Journal of Supercomputing, 1, 301-325, 1988.
The Second DARPA Image Understanding Benchmark on Warp and Extending Apply to Include Global Operations, with Mike MacPherson, Proceedings: Image Understanding Workshop, DARPA, Palo Alto, CA. May, 1989.
Book Review: Parallel Architectures and Computer Vision, in Photogrammetric Engineering and Remote Sensing, 55, October, 1989.
Global Image Processing Operations on Parallel Architectures, solicited paper in SPIE Technical Symposium on Optical Engineering and Photonics in Aerospace, Orlando, FL, April 1990.
Architecture-independent Global Image Processing, solicited paper in International Conference on Pattern Recognition, Atlantic City, NJ, June 1990.
Adapt: Global Image Processing and the Split and Merge Model, Technical Report CMU-CS-91-129, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, April, 1991.
Overcoming the Barriers to Architecture-Independent Image Processing. Proceedings: Image Understanding Workshop. Sponsored by Defense Advanced Research Projects Agency, January, 1992. San Diego, California.
Implementation and Performance of Fast Parallel Multi-Baseline Stereo Vision. Proceedings: Image Understanding Workshop. Sponsored by Defense Advanced Research Projects Agency, April 1993. Washington, D.C.