2024-03-29T02:21:48Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/301552019-06-11T11:31:46Zcom_10261_106com_10261_4col_10261_1241
http://hdl.handle.net/10261/30155
10.1109/CVPR.2010.5540104
30766
Efficient rotation invariant object detection using boosted random Ferns
2010
comunicaciĆ³n de congreso
Villamizar, Michael
Moreno-Noguer, Francesc
rp12429
Andrade-Cetto, Juan
rp12201
Sanfeliu, Alberto
rp12226
Object recognition
Boosting
Pattern recognition
Pattern recognition systems
Image processing
2010
Trabajo presentado al CVPR 2010 celebrado en San Francisco (EE.UU.) del 13 al 18 de junio.
We 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.
IEEE Conference on Computer Vision and Pattern Recognition
2010
1038
1045