Academic Degrees

Ph.D. Computer Science, Université Joseph Fourier, Grenoble, 1993, Summa Cum Laude (“avec les félicitations du jury”).

M.S. Naval Architecture and Offshore Engineering, U.C. Berkeley, 1980.

M.S. (Diplome d'Etudes Approfondies) Applied Mathematics, Université Claude Bernard, Lyon, France,1973.

M.S. ME / Fluid Dynamics, Ecole Centrale de Lyon, France, 1972.

Background

I am currently a Senior Research Scientist at Johns Hopkins University's Applied Physics Laboratory. My research is on object recognition and scene understanding.

From July 2005 and I will have this function until July 2008 I was Program Director for Computer Vision Research at the National Science Foundation (NSF), on leave from a position as associate research professor at the Laboratory for Language and Media Processing (LAMP), a division of the University of Maryland Institute for Advanced Computer Studies (UMIACS) . My research focused on object recognition, video surveillance, video retrieval, and document image analysis.

In 2003, I edited a book with Azriel Rosenfeld and David Doermann, called VIDEO MINING, which is still a good snapshot for navigation and search in large video databases.

I have taught a graduate level computer vision class which is available online, CMSC 828D: Fundamentals of Computer Vision , with Ramani Duraiswami, Larry Davis and Cornelia Fermuller.

Prior to my involvement with LAMP, I was with CVL (Computer Vision Laboratory) at the Center for Automation Research (CfAR) at University of Maryland, College Park , where I developed optical 3D pointers and techniques for pose calculation, such as POSIT and SoftPOSIT. I was also active in visual road following and motion detection research for the DARPA-funded UGV and ALV autonomous land navigation projects.

Recent Publications

Jian Liang, Daniel DeMenthon and David Doermann, "Geometric Rectification of Camera-captured Document Images", PAMI, vol. 30, no. 4, pp. 591-605, April 2008.

Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion", Asian Conference on Computer Vision (ACCV 2007), Tokyo, Japan, Nov. 18--22, 2007.

Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans", ICCV Workshop on Interactive Computer Vision (ICV 2007), Rio de Janeiro, Brazil, October 2007.

Zhe Lin, Larry S. Davis, David Doermann, Daniel DeMenthon, "Hierarchical Part-Template Matching for Human Detection and Segmentation", International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, October 2007.

Daniel DeMenthon and David Doermann, "Video Retrieval of Near-Duplicates using k-Nearest Neighbor Retrieval of Spatio-Temporal Descriptors". Multimedia Tools and Applications (MTAP), pp. 229-253, vol. 30, no. 3, Sept. 2006.

Jian Liang, Daniel DeMenthon and David Doermann, "Camera-Based Document Image Mosaicing", ICPR 2006, vol. 2, pp. 476-479, 2006.

Jian Liang, Daniel DeMenthon and David Doermann, " Mosaicing of Camera-captured Document Images", submitted to CVIU, July 2006.

Ming Luo, Daniel DeMenthon, Xiaodong Yu and and David Doermann, "SOFTCBIR: Object Searching in Videos Combining Keypoint Matching and Graduated Assignment", University of Maryland Technical Report, LAMP-TR-132, CAR-TR-1013, CS-TR-4804, UMIACS-TR-2006-25, May 2006.

Patents

"Computer Vision System for Accurate Monitoring of Object Pose'', U.S. Patent 5,388,059, D. DeMenthon, 1995.

"Three Dimensional Pointing Device Monitored by Computer Vision'', U.S. Patent 5,297,061, D. DeMenthon and Y. Fujii, 1994.

"Computer Vision System for Position Monitoring in Three Dimensions using Non-Coplanar Light Sources Attached to a Monitored Object", U.S. Patent 5,227,985, D. DeMenthon, 1993.

"Computer-Controlled Peripheral Shaping System", U.S. Patent 4,675,825, D. DeMenthon, 1987.

"Wave Energy Converter", U.S. Patent 4,412,417, D. DeMenthon, 1983.