Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Efficient rotation invariant object detection using boosted random Ferns

AuthorsVillamizar, Michael CSIC; Moreno-Noguer, Francesc CSIC ORCID ; Andrade-Cetto, Juan CSIC ORCID ; Sanfeliu, Alberto CSIC ORCID
KeywordsObject recognition
Pattern recognition
Pattern recognition systems
Image processing
Issue Date2010
CitationIEEE Conference on Computer Vision and Pattern Recognition: 1038-1045 (2010)
AbstractWe present a new approach for building an efficient and robust classifier for the two class problem, that localizes objects that may appear in the image under different orientations. In contrast to other works that address this problem using multiple classifiers, each one specialized for a specific orientation, we propose a simple two-step approach with an estimation stage and a classification stage. The estimator yields an initial set of potential object poses that are then validated by the classifier. This methodology allows reducing the time complexity of the algorithm while classification results remain high. The classifier we use in both stages is based on a boosted combination of Random Ferns over local histograms of oriented gradients (HOGs), which we compute during a preprocessing step. Both the use of supervised learning and working on the gradient space makes our approach robust while being efficient at run-time. We show these properties by thorough testing on standard databases and on a new database made of motorbikes under planar rotations, and with challenging conditions such as cluttered backgrounds, changing illumination conditions and partial occlusions.
DescriptionTrabajo presentado al CVPR 2010 celebrado en San Francisco (EE.UU.) del 13 al 18 de junio.
Publisher version (URL)
Appears in Collections:(IRII) Libros y partes de libros

Files in This Item:
File Description SizeFormat
Efficient rotation invariant.pdf7,62 MBAdobe PDFThumbnail
Show full item record
Review this work

Page view(s)

checked on May 25, 2022


checked on May 25, 2022

Google ScholarTM




WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.