Invariant-based recognition of complex curved 3D objects from image contours

Authors:
B. Vijayakumar;D. J. Kriegman;J. Ponce
Affiliations:
-;-;-
Venue:
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Year:
1995

Citing 0
Cited 6

Visualization of plant growth

VIS '97 Proceedings of the 8th conference on Visualization '97
Motion Estimation in Image Sequences Using the Deformation of Apparent Contours

IEEE Transactions on Pattern Analysis and Machine Intelligence
Affine Reconstruction of Curved Surfaces from Uncalibrated Views of Apparent Contours

IEEE Transactions on Pattern Analysis and Machine Intelligence
Generalised Epipolar Constraints

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
Minimal Representations of 3D Models in Terms of Image Parameters under Calibrated and Uncalibrated Perspective

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

To recognize three-dimensional objects bounded by smooth curved surfaces from monocular image contours, viewpoint-dependent image features must be related to object geometry. Contour bitangents and inflections along with associated parallel tangents points are the projection of surface points that lie on the occluding contour for a five-parameter family of scaled orthographic projection viewpoints. An invariant representation can be computed from these image features and seen for modeling and recognizing objects. Modeling is achieved by moving an object in front of a camera to obtain a curve of possible invariants. The relative camera-object motion is not required, and 3D models are not utilized. At recognition time, invariants computed from a single image are used to index the model database. Using the matched features, independent qualitative and quantitative verification procedures eliminate potential false matches. Examples from an implementation are presented.