On-line inverse multiple instance boosting for classifier grids release_nizsnhcjizagfpzqnhuaemmr7q

by Sabine Sternig, Peter M. Roth, Horst Bischof

Published in Pattern Recognition Letters by Elsevier BV.

Volume 33, Issue 7 p890-897 (2012)


Classifier grids have shown to be a considerable choice for object detection from static cameras. By applying a single classifier per image location the classifier's complexity can be reduced and more specific and thus more accurate classifiers can be estimated. In addition, by using an on-line learner a highly adaptive but stable detection system can be obtained. Even though long-term stability has been demonstrated such systems still suffer from short-term drifting if an object is not moving over a long period of time. The goal of this work is to overcome this problem and thus to increase the recall while preserving the accuracy. In particular, we adapt ideas from multiple instance learning (MIL) for on-line boosting. In contrast to standard MIL approaches, which assume an ambiguity on the positive samples, we apply this concept to the negative samples: inverse multiple instance learning. By introducing temporal bags consisting of background images operating on different time scales, we can ensure that each bag contains at least one sample having a negative label, providing the theoretical requirements. The experimental results demonstrate superior classification results in presence of non-moving objects.
In text/plain format

Archived Files and Locations

application/pdf  5.2 MB
lrs.icg.tugraz.at (web)
web.archive.org (webarchive)
Read Archived PDF
Type  article-journal
Stage   published
Date   2012-05-01
Language   en ?
DOI  10.1016/j.patrec.2011.11.008
PubMed  22556453
PMC  PMC3320709
Wikidata  Q41829404
Container Metadata
Not in DOAJ
In Keepers Registery
ISSN-L:  0167-8655
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d8c8cd0b-da7c-4975-8a9b-199e33c7022b