Beyond sliding windows: Object localization by efficient subwindow search

Lampert C, Blaschko M, Hofmann T. 2008. Beyond sliding windows: Object localization by efficient subwindow search. CVPR: Computer Vision and Pattern Recognition, 1–8.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
Lampert , ChristophISTA ; Blaschko,Matthew B; Hofmann,Thomas
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 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 of the resulting systems on the UIUC Cars dataset, the PASCAL VOC 2006 dataset and in the PASCAL VOC 2007 competition.
Publishing Year
Date Published
2008-09-18
Publisher
IEEE
Page
1 - 8
Conference
CVPR: Computer Vision and Pattern Recognition
IST-REx-ID

Cite this

Lampert C, Blaschko M, Hofmann T. Beyond sliding windows: Object localization by efficient subwindow search. In: IEEE; 2008:1-8. doi:10.1109/CVPR.2008.4587586
Lampert, C., Blaschko, M., & Hofmann, T. (2008). Beyond sliding windows: Object localization by efficient subwindow search (pp. 1–8). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2008.4587586
Lampert, Christoph, Matthew Blaschko, and Thomas Hofmann. “Beyond Sliding Windows: Object Localization by Efficient Subwindow Search,” 1–8. IEEE, 2008. https://doi.org/10.1109/CVPR.2008.4587586.
C. Lampert, M. Blaschko, and T. Hofmann, “Beyond sliding windows: Object localization by efficient subwindow search,” presented at the CVPR: Computer Vision and Pattern Recognition, 2008, pp. 1–8.
Lampert C, Blaschko M, Hofmann T. 2008. Beyond sliding windows: Object localization by efficient subwindow search. CVPR: Computer Vision and Pattern Recognition, 1–8.
Lampert, Christoph, et al. Beyond Sliding Windows: Object Localization by Efficient Subwindow Search. IEEE, 2008, pp. 1–8, doi:10.1109/CVPR.2008.4587586.

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data ISTA Research Explorer

Search this title in

Google Scholar