Sciweavers

Share
CVPR
2007
IEEE

Parameter Sensitive Detectors

10 years 7 months ago
Parameter Sensitive Detectors
Object detection can be challenging when the object class exhibits large variations. One commonly-used strategy is to first partition the space of possible object variations and then train separate classifiers for each portion. However, with continuous spaces the partitions tend to be arbitrary since there are no natural boundaries (for example, consider the continuous range of human body poses). In this paper, a new formulation is proposed, where the detectors themselves are associated with continuous parameters, and reside in a parameterized function space. There are two advantages of this strategy. First, a-priori partitioning of the parameter space is not needed; the detectors themselves are in a parameterized space. Second, the underlying parameters for object variations can be learned from training data in an unsupervised manner. In profile face detection experiments, at a fixed false alarm number of 90, our method attains a detection rate of 75% vs. 70% for the method of Viola-...
Quan Yuan, Ashwin Thangali, Vitaly Ablavsky, Stan
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2007
Where CVPR
Authors Quan Yuan, Ashwin Thangali, Vitaly Ablavsky, Stan Sclaroff
Comments (0)
books