1. Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach
- Author
-
Reyes Rios-Cabrera and Tinne Tuytelaars
- Subjects
Monocular ,business.industry ,Computer science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,PSI_VISICS ,Frame rate ,Object detection ,Support vector machine ,Object-class detection ,Discriminative model ,Computer vision ,Viola–Jones object detection framework ,Artificial intelligence ,business ,Representation (mathematics) - Abstract
In this paper we propose a new method for detecting multiple specific 3D objects in real time. We start from the template-based approach based on the LINE2D/LINEMOD representation introduced recently by Hinterstoisser et al., yet extend it in two ways. First, we propose to learn the templates in a discriminative fashion. We show that this can be done online during the collection of the example images, in just a few milliseconds, and has a big impact on the accuracy of the detector. Second, we propose a scheme based on cascades that speeds up detection. Since detection of an object is fast, new objects can be added with very low cost, making our approach scale well. In our experiments, we easily handle 10-30 3D objects at frame rates above 10fps using a single CPU core. We outperform the state-of-the-art both in terms of speed as well as in terms of accuracy, as validated on 3 different datasets. This holds both when using monocular color images (with LINE2D) and when using RGBD images (with LINEMOD). Moreover, we propose a challenging new dataset made of 12 objects, for future competing methods on monocular color images. © 2013 IEEE. Rios-Cabrera R., Tuytelaars T., ''Discriminatively trained templates for 3D object detection: A real time scalable approach'', Proceedings 14th international conference on computer vision - ICCV 2013, pp. 2048-2055, December 3-6, 2013, Sydney, Australia. ispartof: pages:2048-2055 ispartof: Proceedings ICCV 2013 pages:2048-2055 ispartof: International conference on computer vision - ICCV 2013 location:Sydney, Australia date:3 Dec - 6 Dec 2013 status: published
- Published
- 2013