English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Branch&Rank: Non-linear Object Detection

MPS-Authors
/persons/resource/persons44483

Gehler,  Peter
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

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.


Cite as: https://hdl.handle.net/11858/00-001M-0000-0010-12CE-C
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.