W
William Bruce Jatko
Researcher at Oak Ridge National Laboratory
Publications - 7
Citations - 71
William Bruce Jatko is an academic researcher from Oak Ridge National Laboratory. The author has contributed to research in topics: Image processing & Digital image processing. The author has an hindex of 4, co-authored 7 publications receiving 68 citations.
Papers
More filters
Proceedings ArticleDOI
Subpixel measurement of image features based on paraboloid surface fit
TL;DR: In this paper, a least squares fit of a paraboloid function to the surface generated by correlating a reference image feature against a test image search area is used to locate unique image features to subpixel accuracies.
Robust pose determination for autonomous docking
TL;DR: This paper describes current work at the Oak Ridge National Laboratory to develop a robotic vision system capable of recognizing designated objects by their intrinsic geometry, which combines point features and a model-based technique using geometric feature matching for the pose calculation.
Proceedings ArticleDOI
Nonlinear filter derived from topological image features
TL;DR: A novel algorithm has been developed to filter edge noise from the difference images that has reduced edge noise by 98% over the unfiltered image and can be implemented using off-the-shelf hardware.
Proceedings ArticleDOI
Application of the smart portal in transportation
Stephen W. Kercel,Vivian M. Baylor,William B. Dress,Tim W. Hickerson,William Bruce Jatko,Leo E. Labaj,Jeffrey D. Muhs,Richard M. Pack +7 more
TL;DR: Although not originally developed for commercial transportation, the smart portal has the potential to solve several transportation problems, it could relieve congestion at international highway border crossings by reducing the time required to inspect each vehicle while increasing the level of security.
Proceedings ArticleDOI
An asynchronous modulation/demodulation technique for robust identification of a target for 3-D pose determination
TL;DR: A method of uniquely identifying and segmenting the receiving port from its background in a sequence of video images is described, which has been robust and reliable in a laboratory demonstration of autodocking.