Three-dimensional object recognition from single two-dimensional images
Artificial Intelligence
Using vanishing points for camera calibration
International Journal of Computer Vision
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Introductory Techniques for 3-D Computer Vision
Introductory Techniques for 3-D Computer Vision
Flexible Filter Neighbourhood Designation
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
| Hi-index | 0.00 |
In this paper, we propose an iterative method of 3Dlocation of 2D parallelogram or 3D parallelepipedshapes by monocular vision from a single image. Themethod we propose assumes that the camera is calibratedand that the size of the polygonal object is known. The 3Dlocation is obtained in the following way. First we try tofind the orientation of a geometric model of the objectimaged such that they share the same vanishing points.This property known as "involution" in the 17th centuryinsures that the model and the object have the sameorientation. Moreover this property in invariant totranslation. This greatly simplifies the location problemby allowing to decouple rotation and translationassessments. The method is illustrated and tested withreal scene images.