Publication
Efficient 3D object detection using multiple pose-specific classifiers
Conference Article
Conference
British Machine Vision Conference (BMVC)
Edition
2011
Pages
20.1-20.10
Doc link
http://dx.doi.org/10.5244/C.25.20
File
Authors
-
Villamizar Vergel, Michael Alejandro
-
Grabner, Helmut
-
Andrade Cetto, Juan
-
Sanfeliu Cortés, Alberto
-
Van Gool, Luc
-
Moreno Noguer, Francesc
Projects associated
Abstract
We propose an efficient method for object localization and 3D pose estimation. A two-step approach is used. In the first step, a pose estimator is evaluated in the input images in order to estimate potential object locations and poses. These candidates are then validated, in the second step, by the corresponding pose-specific classifier. The result is a detection approach that avoids the inherent and expensive cost of testing the complete set of specific classifiers over the entire image. A further speedup is achieved by feature sharing. Features are computed only once and are then used for evaluating the pose estimator and all specific classifiers. The proposed method has been validated on two public datasets for the problem of detecting of cars under several views. The results show that the proposed approach yields high detection rates while keeping efficiency.
Categories
computer vision.
Scientific reference
M. Villamizar, H. Grabner, J. Andrade-Cetto, A. Sanfeliu, L. Van Gool and F. Moreno-Noguer. Efficient 3D object detection using multiple pose-specific classifiers, 2011 British Machine Vision Conference, 2011, Dundee, UK, pp. 20.1-20.10.
Follow us!