Efficient determination of shape from multiple images containing partial information

@article{Basri1996EfficientDO,
  title={Efficient determination of shape from multiple images containing partial information},
  author={Ronen Basri and Adam J. Grove and David W. Jacobs},
  journal={Proceedings of 13th International Conference on Pattern Recognition},
  year={1996},
  volume={1},
  pages={268-274 vol.1}
}
  • R. Basri, Adam J. Grove, D. Jacobs
  • Published 25 August 1996
  • Mathematics, Computer Science
  • Proceedings of 13th International Conference on Pattern Recognition
We consider the problem of reconstructing the shape of an object from multiple images related by translations, when only small portions of the object can be observed in each image. Lindenbaum and Bruckstein (1988) have considered this problem in the specific case where the translating object is seen by small sensors, for application to the understanding of insect vision. Their solution is limited by the fact that its run time is exponential in the number of images and sensors. We show that the… 

Figures from this paper

Structure from motion without correspondence

TLDR
A method is presented to recover 3D scene structure and camera motion from multiple images without the need for correspondence information by means of an algorithm which iteratively refines a probability distribution over the set of all correspondence assignments.

Monte carlo em for data-association and its applications in computer vision

TLDR
The resulting Monte Carlo EM approach represents the first truly multiview algorithm for geometric estimation with unknown correspondence and allows for a seamless and principled way of integrating prior knowledge, appearance models, and statistical models for occlusion and clutter.

EM, MCMC, and Chain Flipping for Structure from Motion with Unknown Correspondence

TLDR
An EM-based algorithm is developed, which solves the model learning and the data association problem in parallel, and it is conjecture that this approach can be applied to a broad range of model learning problems from sensordata, such as the robot mapping problem.

Image Analysis and Computer Vision: 1996

TLDR
A bibliography of nearly 2150 references related to computer vision and image analysis, arranged by subject matter, is presented, covering topics including computational techniques; feature detection and segmentation; image and scene analysis; and motion.

Image Analysis and Computer Vision: 1998

TLDR
A bibliography of over 2250 references related to computer vision and image analysis, arranged by subject matter is presented, covering topics including computational techniques; feature detection and segmentation; image and scene analysis; and motion.

References

SHOWING 1-10 OF 16 REFERENCES

Determining object shape from local velocity measurements

3-D to 2-D recognition with regions

  • D. JacobsR. Basri
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
This paper focuses on the problem of determining the pose of a 3-D object from a single 2-D image when convex parts of the object have been matched to corresponding regions in the image, and considers three types of occlusion: self-occlusion, occlusions whose locus is identified in theimage, and completely arbitrary occludes.

Recognition Using Region Correspondences

  • R. BasriD. Jacobs
  • Computer Science
    Proceedings of IEEE International Conference on Computer Vision
  • 1995
TLDR
The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls, and makes use of region information that reflects the true shape of the object.

Model-Based Image Matching Using Location

TLDR
This work deals with the computer vision problem of recognizing and locating rigid shapes in the plane which have been subjected to unknown rotation, scaling, and noise and develops a pruned tree-search algorithm which makes effective use of the Soviet ellipsoid algorithm for feasibility of linear constraints.

Tracking non-rigid objects in complex scenes

TLDR
A model-based method for tracking nonrigid objects moving in a complex scene by extracting two-dimensional models of an object from a sequence of images to decompose the image of a solid object moving in space into two components.

Motion and structure from feature correspondences: a review

TLDR
Some of the mathematical techniques borrowed from algebraic geometry, projective geometry, and homotopy theory that are required to solve three-dimensional (3D) motion and structure of rigid objects when their corresponding features are known at different times or are viewed by different cameras are mentioned.

Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty

TLDR
This work presents a general formulation of the problem of object recognition via local geometric feature matching and a polynomial-time algorithm which guarantees finding all geometrically feasible interpretations of the data, modulo uncertainty, in terms of the model.

On the Area of Overlap of Translated Polygons

TLDR
A number of mathematical results regarding the area-of-overlap function of PandQ, which has a number of applications in areas such as motion planning and object recognition, are presented.

Bounded boxes, Hausdorff distance, and a new proof of an interesting Helly-type theorem

TLDR
Two geometric optimization problems to convex programming are reduced: finding the largest axis-aligned box in the intersection of a family of convex sets and finding the translation and scaling that minimizes the Hausdorff distance between two polytopes.

The complexity of theorem-proving procedures

  • S. Cook
  • Mathematics, Computer Science
    STOC
  • 1971
It is shown that any recognition problem solved by a polynomial time-bounded nondeterministic Turing machine can be “reduced” to the problem of determining whether a given propositional formula is a