The Variable Bandwidth Mean Shift and Data-Driven Scale Selection

Dorin Comaniciu, Visvanathan Ramesh and Peter Meer(*)

Imaging and Visualization Department
Siemens Corporate Research
Princeton, NJ 08540

(*)Department of Electrical and Computer Engineering
Rutgers University, Piscataway, NJ 08855, USA

We present two solutions for the scale selection problem in computer vision. The first one is completely nonparametric and is based on the the adaptive estimation of the normalized density gradient. Employing the sample point estimator, we define the Variable Bandwidth Mean Shift, prove its convergence, and show its superiority over the fixed bandwidth procedure. The second technique has a semiparametric nature and imposes a local structure on the data to extract reliable scale information. The local scale of the underlying density is taken as the bandwidth which maximizes the magnitude of the normalized mean shift vector. Both estimators provide practical tools for autonomous image and quasi real-time video analysis and several examples are shown to illustrate their effectiveness.

8th International Conference on Computer Vision , Vancouver, BC, Canada, July 2001, vol. I, 438-445.
Return to Research: Robust analysis of visual data       Return to List of Publications
Download the paper