D
David Harwood
Researcher at University of Maryland, College Park
Publications - 52
Citations - 15988
David Harwood is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Background subtraction & Hough transform. The author has an hindex of 28, co-authored 52 publications receiving 15080 citations.
Papers
More filters
Robot Acting on Moving Bodies (RAMBO): Interaction with tumbling objects
Larry S. Davis,Daniel DeMenthon,Thor Bestul,Sotirios G. Ziavras,H. V. Srinivasan,Madhu Siddalingaiah,David Harwood +6 more
TL;DR: Low level vision uses parallel algorithms for image enhancement by symmetric nearest neighbor filtering, edge detection by local gradient operators, and corner extraction by sector filtering and trajectories are created using dynamic interpolations between initial and goal trajectories.
Journal ArticleDOI
Automated Visual Inspection of Textured Surfaces
TL;DR: A new class of texture measures based on covariance analysis of center-symmetric pixel neighborhoods is introduced and the results indicate that the new measures are more powerful than the popular texture measures developed by Laws.
Robot acting on moving bodies (RAMBO): Preliminary results
Larry S. Davis,Daniel DeMenthon,Thor Bestul,Sotirios G. Ziavras,H. V. Srinivasan,Madju Siddalingaiah,David Harwood +6 more
TL;DR: Low level vision uses parallel algorithms for image enchancement by symmetric nearest neighbor filtering, edge detection by local gradient operators, and corner extraction by sector filtering, and object pose estimation is a Hough transform method accumulating position hypotheses obtained by matching triple of image features (corners) to triples of model features.
Proceedings Article
Appearance-based human gallery construction from video
TL;DR: In this paper, an approach for constructing a dynamic gallery of people observed in a video stream is described, which automatically computes an appearance model based on the clothing of people and employs this model in constructing and matching the gallery of participants.