An analytic solution for the perspective 4-point problem
Computer Vision, Graphics, and Image Processing
Recognizing solid objects by alignment with an image
International Journal of Computer Vision
Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Model-based invariants for 3-D vision
International Journal of Computer Vision
Model-Based Object Pose in 25 Lines of Code
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Distance Metric Between 3D Models and 2D Images for Recogntion and Classification
Distance Metric Between 3D Models and 2D Images for Recogntion and Classification
On View Likelihood and Stability
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vision guided bin picking and mounting in a flexible assembly cell
IEA/AIE '00 Proceedings of the 13th international conference on Industrial and engineering applications of artificial intelligence and expert systems: Intelligent problem solving: methodologies and approaches
An evolutionary optimization approach for 3D human head model classification
MIR '03 Proceedings of the 5th ACM SIGMM international workshop on Multimedia information retrieval
Hierarchical multi-classifier system design based on evolutionary computation technique
Multimedia Tools and Applications
| Hi-index | 0.14 |
Similarity measurements between 3D objects and 2D images are useful for the tasks of object recognition and classification. We distinguish between two types of similarity metrics: metrics computed in image-space (image metrics) and metrics computed in transformation-space (transformation metrics). Existing methods typically use image metrics; namely, metrics that measure the difference in the image between the observed image and the nearest view of the object. Example for such a measure is the Euclidean distance between feature points in the image and their corresponding points in the nearest view. (This measure can be computed by solving the exterior orientation calibration problem.) In this paper we introduce a different type of metrics: transformation metrics. These metrics penalize for the deformations applied to the object to produce the observed image.In particular, we define a transformation metric that optimally penalizes for "affine deformations" under weak-perspective. A closed-form solution, together with the nearest view according to this metric, are derived. The metric is shown to be equivalent to the Euclidean image metric, in the sense that they bound each other from both above and below. It therefore provides an easy-to-use closed-form approximation for the commonly-used least-squares distance between models and images. We demonstrate an image understanding application, where the true dimensions of a photographed battery charger are estimated by minimizing the transformation metric.