Correspondence and segmentation of multiple rigid motions via epipolar geometry

@article{Xu1996CorrespondenceAS,
  title={Correspondence and segmentation of multiple rigid motions via epipolar geometry},
  author={Gang Xu and Saburo Tsuji},
  journal={Proceedings of 13th International Conference on Pattern Recognition},
  year={1996},
  volume={1},
  pages={213-217 vol.1}
}
  • Gang Xu, S. Tsuji
  • Published 25 August 1996
  • Engineering
  • Proceedings of 13th International Conference on Pattern Recognition
This paper presents a new approach to matching and segmenting multiple rigid motions using epipolar constraint. Epipolar geometry underlying the motion images are first recovered, and the epipolar equations are used to reduce search for correspondence from 2-dimensional to 1-dimensional, thus resolving the "aperture problem". Segmentation of images into different motions is simultaneous. Experimental results show that this approach is effective and efficient. 

Figures from this paper

A unified approach to image matching and segmentation in stereo, motion and object recognition via recovery of epipolar geometry

  • G. Xu
  • Computer Science
  • 1997
TLDR
Videre: Journal of Computer Vision Research is a quarterly journal published electronically on the Internet by The MIT Press, Cambridge, Massachusetts, 02142 and prices subject to change without notice.

Object and motion recognition using the plane plus parallax displacement of conics

TLDR
Parallax displacement is used to determine a relative 3D conic projective structure which can be used to segment groups of conics which have consistent motion and determines conic correspondence between three simultaneous views.

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.

Classification and segmentation of vector flow fields using a neural network

TLDR
The projection onto the image plane of the 3D infinitesimal generators of the3D Euclidean group have proved to provide an effective description for the considered vector flow fields.

References

SHOWING 1-10 OF 28 REFERENCES

Unifying Stereo, Motion and Object Recognition via Epipolar Geometry

TLDR
By recovering epipolar geometry underlying the images, the correspondence search problems in motion and object recognition can also be changed to be 1-dimensional, thus providing a framework to treat all these 3 problems in a unified way.

Epipolar Geometry in Stereo, Motion and Object Recognition

TLDR
Redefining Stereo, Motion and Object Recognition via Ep bipolar Geometry via Epipolar Geometry, and Multiple Rigid Motions: Correspondence and Segmentation is redefined.

Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective

TLDR
An algorithm for identifying and tracking independently moving rigid objects from optical flow using the fact that each independently moving object has a unique epipolar constraint associated with its motion to distinguished motion discontinuities based on self-occlusion from those due to separate objects.

Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects

  • Gilad Adiv
  • Physics
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1985
TLDR
A new approach for the interpretation of optical flow fields is presented, where the flow field is partitioned into connected segments of flow vectors, where each segment is consistent with a rigid motion of a roughly planar surface.

Motion From Point Matches Using Affine Epipolar Geometry

TLDR
This work defines the affine epipolar geometry for two such cameras, giving the fundamental matrix in this case and discussing its noise resistant computation, and presents a new framework that caters for errors and noise, and allows all available features to be used, without the need to select a frame explicitly.

Motion and Structure from Image Sequences

Estimating motion and structure of the scene from image sequences is a very important and active research area in computer vision. The results of research have applications in vision-guided

Scene Segmentation from Visual Motion Using Global Optimization

  • D. W. MurrayB. Buxton
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1987
TLDR
To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used and the search for the globally optimal segmentation is performed using simulated annealing.

Three dimensional transparent structure segmentation and multiple 3D motion estimation from monocular perspective image sequences

  • Stefano SoattoP. Perona
  • Physics
    Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects
  • 1994
A three dimensional scene can be segmented using different cues, such as boundaries, texture, motion, discontinuities of the optical flow, stereo, models for structure, etc. We investigate

Factoring image sequences into shape and motion

TLDR
The authors show that a matrix of image measurements can be factored by singular value decomposition into the product of two matrices that represent shape and motion, respectively.