PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Beyond Sliding Windows: Object Localization by Efficient Subwindow Search
Christoph Lampert, Matthew Blaschko and Thomas Hofmann
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 24-26 Jun 2008, Anchorage, USA.

Abstract

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 branch- and-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 localiza- tion 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 of the resulting systems on the UIUC Cars dataset, the PASCAL VOC 2006 dataset and in the PASCAL VOC 2007 competition.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:4802
Deposited By:Christoph Lampert
Deposited On:24 March 2009