Sciweavers

Share
CVPR
2008
IEEE

Beyond sliding windows: Object localization by efficient subwindow search

9 years 8 months ago
Beyond sliding windows: Object localization by efficient subwindow search
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branchand-bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages. It converges to a globally optimal solution typically in sublinear time. We show how our method is applicable to different object detection and retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest neighbor classifiers based on the 2 -distance. We demonstrate state-of-the-art performance...
Christoph H. Lampert, Matthew B. Blaschko, Thomas
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Christoph H. Lampert, Matthew B. Blaschko, Thomas Hofmann
Comments (0)
books