Shared random Ferns for efficient detection of multiple categories
Document typeConference report
Rights accessOpen Access
We propose a new algorithm for detecting multiple object categories that exploits the fact that different categories may share common features but with different geometric distributions. This yields an efficient detector which, in contrast to existing approaches, considerably reduces the computation cost at runtime, where the feature computation step is traditionally the most expensive. More specifically, at the learning stage we compute common features by applying the same Random Ferns over the Histograms of Oriented Gradients on the training images. We then apply a boosting step to build discriminative weak classifiers, and learn the specific geometric distribution of the Random Ferns for each class. At runtime, only a few Random Ferns have to be densely computed over each input image, and their geometric distribution allows performing the detection. The proposed method has been validated in public datasets achieving competitive detection results, which are comparable with state-of-the-art methods that use specific features per class.
CitationVillamizar, M.A. [et al.]. Shared random Ferns for efficient detection of multiple categories. A: International Conference on Pattern Recognition. "20th International Conference on Pattern Recognition". Estambul: 2010, p. 388-391.
- VIS - Visió Artificial i Sistemes Intel.ligents - Ponències/Comunicacions de congressos 
- Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos 
- Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial - Ponències/Comunicacions de congressos