Martin A. Fischler

Timeline

1. 1969

   Machine perception at Lockheed

   At the Lockheed Palo Alto Research Laboratory, he writes "Machine Perception and Description of Pictorial Data" for IJCAI in 1969. The paper proposes a structural, linguistic approach to machine perception.

2. 1971–1973

   Pictorial data and AI forecasting

   At IJCAI in 1971, he publishes "Aspects of the Detection of Scene Congruence" and, with Oscar Firschein, "A Study in Descriptive Representation of Pictorial Data". In 1973, he and Firschein join L. Stephen Coles and Jay M. Tenenbaum on "Forecasting and Assessing the Impact of Artificial Intelligence on Society" for IJCAI.

3. 1981

   The RANSAC paper

   At SRI International, he and Robert C. Bolles publish "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography" in 1981. The paper introduces RANSAC, an iterative method that estimates the parameters of a mathematical model from data containing outliers. They apply it to the location determination problem, which asks for the points in space that project onto an image as a set of landmarks with known locations.

4. 1983–1985

   Linear structure and one-eyed stereo

   At IJCAI in 1983, he publishes "Machine Perception of Linear Structure" with Helen C. Wolf and "Perceptual Organization and the Curve Partitioning Problem" with Robert C. Bolles. In 1985, he and Thomas M. Strat publish "One-Eyed Stereo: A General Approach to Modeling 3-D Scene Geometry" at IJCAI.

5. 1987

   Two books on vision and intelligence

   In 1987, he and Oscar Firschein edit Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, which collects sixty papers, most published since 1980. Both editors are leaders of the AI Center Perception Group at SRI International. They also write Intelligence: The Eye, the Brain and the Computer, published by Addison-Wesley.

6. 1992

   Line drawings as 3-D wire frames

   In 1992, he and Y. G. Leclerc publish "An Optimization-Based Approach to the Interpretation of Single Line Drawings as 3-D Wire Frames" in the International Journal of Computer Vision. Their paper "Recovering 3-D wire frames from line drawings" appears in the proceedings of the DARPA Image Understanding Workshop in San Diego.

7. By 2006

   Ground robots at SRI

   As a Principal Scientist at SRI International, he works on LAGR, DARPA's Learning Applied to Ground Robots project for autonomous offroad navigation with realtime vision and learning. In 2006, he coauthors "Outdoor Mapping and Navigation using Stereo Vision" with Kurt Konolige, Motilal Agrawal, Robert C. Bolles, Cregg Cowan and Brian P. Gerkey for the International Symposium on Experimental Robotics in Rio de Janeiro.