English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Branch&Rank: Non-linear Object Detection

Lehmann, A., Gehler, P., & Van Gool, L. (2011). Branch&Rank: Non-linear Object Detection. In J. Hoey, S. McKenna, & E. Trucco (Eds.), Proceedings of the British Machine Vision Conference 2011 (pp. 8.1-8.11). Malvern, UK: BMVA Press. doi:10.5244/C.25.8.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0010-12CE-C Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-12B2-C
Genre: Conference Paper
Latex : {Branch\&Rank}: Non-linear Object Detection

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Lehmann, Alain1, Author
Gehler, Peter2, Author           
Van Gool, Luc1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: -
 Abstract: Branch&rank is an object detection scheme that overcomes the inherent limitation of branch&bound: this method works with arbitrary (classifier) functions whereas tight bounds exist only for simple functions. Objects are usually detected with less than 100 classifier evaluation, which paves the way for using strong (and thus costly) classifiers: We utilize non-linear SVMs with RBF- 2 kernels without a cascade-like approximation. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for too simple function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single, structured SVM formulation. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We demonstrate the algorithmic properties using the VOC'07 dataset.

Details

show
hide
Language(s): eng - English
 Dates: 20112011
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 618788
BibTex Citekey: 526
DOI: 10.5244/C.25.8
URI: http://dx.doi.org/10.5244/C.25.8
Other: Local-ID: C12576EE0048963A-C578EB50E10A203DC12579640041092D-Gehler2010
 Degree: -

Event

show
hide
Title: 2011 British Machine Vision Conference
Place of Event: Dundee, Scotland
Start-/End Date: 2011-08-29 - 2011-09-02

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the British Machine Vision Conference 2011
  Abbreviation : BMVC 2011
Source Genre: Proceedings
 Creator(s):
Hoey, Jesse1, Editor
McKenna, Stephen1, Editor
Trucco, Emanuele1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Malvern, UK : BMVA Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 8.1 - 8.11 Identifier: ISBN: 1-901725-43-X