New methods for matching 3-D objects with single perspective views
IEEE Transactions on Pattern Analysis and Machine Intelligence
Linear programming and convex hulls made easy
SCG '90 Proceedings of the sixth annual symposium on Computational geometry
Invariant Descriptors for 3D Object Recognition and Pose
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Geometric invariants and object recognition
International Journal of Computer Vision
Geometric computation for machine vision
Geometric computation for machine vision
Recognition Using Region Correspondences
International Journal of Computer Vision
3-D to 2-D Pose Determination with Regions
International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
A Stratified Approach to Metric Self-Calibration
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Projective Alignment with Regions
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape-Based Recognition of Wiry Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
View matching with blob features
Image and Vision Computing
Robust homography estimation from planar contours based on convexity
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Hi-index | 0.15 |
We have recently proposed an approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. Regions introduce an attractive alternative to existing global and local approaches, since, unlike global features, they can handle occlusion and segmentation errors, and unlike local features they are not as sensitive to sensor errors, and they are easier to match. The region-based approach also uses image information directly, without the construction of intermediate representations, such as algebraic descriptions, which may be difficult to reliably compute. In this paper, we further analyze properties of the method for planar objects undergoing projective transformations. In particular, we prove that three visible regions are sufficient to determine the transformation uniquely and that for a large class of objects, two regions are insufficient for this purpose. However, we show that when several regions are available, the pose of the object can generally be recovered even when some or all regions are significantly occluded. Our analysis is based on investigating the flow patterns of points under projective transformations in the presence of fixed points.