V
Visvanathan Ramesh
Researcher at Goethe University Frankfurt
Publications - 138
Citations - 15020
Visvanathan Ramesh is an academic researcher from Goethe University Frankfurt. The author has contributed to research in topics: Mean-shift & Image segmentation. The author has an hindex of 41, co-authored 138 publications receiving 14594 citations. Previous affiliations of Visvanathan Ramesh include Princeton University & Frankfurt Institute for Advanced Studies.
Papers
More filters
Journal ArticleDOI
Kernel-based object tracking
TL;DR: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
Proceedings ArticleDOI
Real-time tracking of non-rigid objects using mean shift
TL;DR: The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution for real time tracking of non-rigid objects seen from a moving camera.
Proceedings ArticleDOI
Background modeling and subtraction of dynamic scenes
TL;DR: An on-line auto-regressive model to capture and predict the behavior of dynamic scenes where the assumption of a static background is not valid and a new metric that is based on a state-driven comparison between the prediction and the actual frame is introduced.
Proceedings ArticleDOI
A system for traffic sign detection, tracking, and recognition using color, shape, and motion information
TL;DR: This paper describes a computer vision based system for real-time robust traffic sign detection, tracking, and recognition that offers a generic, joint modeling of color and shape information without the need of tuning free parameters.
Proceedings ArticleDOI
The variable bandwidth mean shift and data-driven scale selection
TL;DR: In this article, a nonparametric and semiparametric scale selection method is proposed for the scale selection problem in computer vision, where the local scale of the underlying density is taken as the bandwidth which maximizes the magnitude of the normalized mean shift vector.