## Algebraic Functions For Recognition (1994)

### Cached

### Download Links

- [www.cs.huji.ac.il]
- [publications.ai.mit.edu]
- DBLP

### Other Repositories/Bibliography

Venue: | IEEE Transactions on Pattern Analysis and Machine Intelligence |

Citations: | 149 - 29 self |

### BibTeX

@ARTICLE{Shashua94algebraicfunctions,

author = {Amnon Shashua},

title = {Algebraic Functions For Recognition},

journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

year = {1994},

volume = {17},

pages = {779--789}

}

### Years of Citing Articles

### OpenURL

### Abstract

In the general case, a trilinear relationship between three perspective views is shown to exist. The trilinearity result is shown to be of much practical use in visual recognition by alignment --- yielding a direct reprojection method that cuts through the computations of camera transformation, scene structure and epipolar geometry. Moreover, the direct method is linear and sets a new lower theoretical bound on the minimal number of points that are required for a linear solution for the task of reprojection. The proof of the central result may be of further interest as it demonstrates certain regularities across homographies of the plane and introduces new view invariants. Experiments on simulated and real image data were conducted, including a comparative analysis with epipolar intersection and the linear combination methods, with results indicating a greater degree of robustness in practice and a higher level of performance in re-projection tasks. Keywords--- Visual Recognition, Al...

### Citations

630 |
A computer algorithm for reconstructing a scene from two projections
- Longuet-Higgins
- 1981
(Show Context)
Citation Context ...n can in principal be dealt with via 3D reconstruction of shape and camera motion. This includes classical structure from motion methods for recovering rigid camera motion parameters and metric shape =-=[36, 18, 35, 14, 15]-=-, and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated [17, 25, 3... |

504 |
What can be seen in three dimensions with an uncalibrated stereo rig
- Faugeras
- 1992
(Show Context)
Citation Context ...5, 14, 15], and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated =-=[17, 25, 39, 10, 13, 30]-=-. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration [3, 9, 12], and therefore, are unlikel... |

467 |
The interpretation of visual motion
- Ullman
- 1979
(Show Context)
Citation Context ...n can in principal be dealt with via 3D reconstruction of shape and camera motion. This includes classical structure from motion methods for recovering rigid camera motion parameters and metric shape =-=[36, 18, 35, 14, 15]-=-, and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated [17, 25, 3... |

410 |
Recognition by linear combinations of models
- Ullman, Basri
- 1991
(Show Context)
Citation Context ... of a scene satisfy a pair of trilinear functions of image coordinates. In the limiting case, when all three views are orthographic, these functions become linear and reduce to the form discovered by =-=[38]-=-. Using the trilinear result one can manipulate views of an object (such as generate novel views from two model views) without recovering scene structure (metric or non-metric), camera transformation,... |

313 |
Uniqueness and estimation of three-dimensional motion parameters of rigid objects with curved surfaces
- Tsai, Huang
- 1984
(Show Context)
Citation Context ...n can in principal be dealt with via 3D reconstruction of shape and camera motion. This includes classical structure from motion methods for recovering rigid camera motion parameters and metric shape =-=[36, 18, 35, 14, 15]-=-, and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated [17, 25, 3... |

292 |
Affine structure from motion
- Koenderink, Doorn
- 1991
(Show Context)
Citation Context ...5, 14, 15], and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated =-=[17, 25, 39, 10, 13, 30]-=-. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration [3, 9, 12], and therefore, are unlikel... |

250 |
S.: Recognizing solid objects by alignment with an image
- Huttenlocher, Ullman
- 1990
(Show Context)
Citation Context ...y have several applications (discussed in Section VI), but the one emphasized throughout this paper is for the task of recognition of 3D objects via alignment. The alignment approach for recognition (=-=[37, 16]-=-, and references therein) is based on the result that the equivalence class of views of an object (ignoring self occlusions) undergoing 3D rigid, affine or projective transformations can be captured b... |

242 |
Stereo from uncalibrated cameras
- Hartley, Gupta, et al.
- 1992
(Show Context)
Citation Context ...5, 14, 15], and more recent methods for recovering non-metric structure, i.e., assuming the objects undergo 3D affine or projective transformations, or equivalently, that the cameras are uncalibrated =-=[17, 25, 39, 10, 13, 30]-=-. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration [3, 9, 12], and therefore, are unlikel... |

178 | Canonical representations for the geometries of multiple projective views
- Luong, Viéville
- 1996
(Show Context)
Citation Context ....58 pixels. In the latter case, we recovered first the homography B due to the ground plane and then the epipole v 00 using two additional points (those on the film cartridges). It is then known (see =-=[28, 21, 32]-=-) that F 13 = [v 00 ]B, where [v 00 ] is the anti-symmetric matrix of v 00 . A similar procedure was used to recover F 23 . Therefore, only six points were used for re-projection, Fig. 5. Results of r... |

162 |
Aligning pictorial descriptions: An approach to object recognition
- Ullman
- 1989
(Show Context)
Citation Context ...y have several applications (discussed in Section VI), but the one emphasized throughout this paper is for the task of recognition of 3D objects via alignment. The alignment approach for recognition (=-=[37, 16]-=-, and references therein) is based on the result that the equivalence class of views of an object (ignoring self occlusions) undergoing 3D rigid, affine or projective transformations can be captured b... |

154 | Layered representation for motion analysis
- Wang, Adelson
- 1993
(Show Context)
Citation Context ...y, and robustness (as shown above) due to the short-cut in the computations, is of great importance. Related to image coding, an approach of image decomposition into "layers" was recently pr=-=oposed by [1, 2]-=-. In this approach, a sequence of views is divided up into regions, whose motion of each is described approximately by a 2D affine transformation. The sender sends the first image followed only by the... |

130 | Relative orientation
- Horn
- 1990
(Show Context)
Citation Context |

123 |
Inherent ambiguities in recovering 3D motion and structure from a noisy ow eld
- Adiv
- 1989
(Show Context)
Citation Context ... uncalibrated [17, 25, 39, 10, 13, 30]. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration =-=[3, 9, 12]-=-, and therefore, are unlikely to be of practical use for purposes of re-projection. The non-metric approaches, as a general concept, have not been fully tested on real images, but the methods proposed... |

108 | What can two images tell us about a third one
- Faugeras, Robert
- 1994
(Show Context)
Citation Context ... a process that is also known to be unstable in the presence of noise. It is also known that the epipolar geometry alone is sufficient to achieve re-projection by means of intersecting epipolar lines =-=[24, 6, 8, 26, 23, 11]-=- using at least eight corresponding points across the three views. This, however, is possible only if the centers of the three cameras are noncollinear --- which can lead to numerical instability unle... |

104 |
Trilinearity in Visual Recognition by Alignment
- Shashua
- 1994
(Show Context)
Citation Context ...ints, but as we shall see in the experimental section to more accurate performance in the presence of errors in image measurements. Part of this work (Theorem 1 only) was presented in concise form in =-=[31]-=-. II. Notations We consider object space to be the three-dimensional projective space P 3 , and image space to be the twodimensional projective space P 2 . Let \Phi ae P 3 be a set of points standing ... |

91 | On determining the fundamental matrix: analysis of di€erent methods and experimental results
- Luong, Deriche, et al.
- 1993
(Show Context)
Citation Context ...he fundamental matrices in a linear or non-linear squares method. Since linear least squares methods are still sensitive to image noise, we used the implementation of a non-linear method described in =-=[20]-=- which was kindly provided by T. Luong and L. Quan (these were two implementations of the method proposed in [20] --- in each case, the implementation that provided the better results was adopted). Th... |

73 | Geometry and Photometry in 3D Visual Recognition
- Shashua
- 1992
(Show Context)
Citation Context ... a process that is also known to be unstable in the presence of noise. It is also known that the epipolar geometry alone is sufficient to achieve re-projection by means of intersecting epipolar lines =-=[24, 6, 8, 26, 23, 11]-=- using at least eight corresponding points across the three views. This, however, is possible only if the centers of the three cameras are noncollinear --- which can lead to numerical instability unle... |

62 | Projective structure from uncalibrated images: Structure from motion and recognition
- Shashua
- 1994
(Show Context)
Citation Context |

60 |
Hierarchical motion-based frame rate conversion,” David Sarnoff Res
- Begen, Hingorani
- 1990
(Show Context)
Citation Context ...espondences were automatically obtained along all other frames used in this experiment. The correspondence process is based on an implementation of a coarse-to-fine opticalflow algorithm described in =-=[7]-=-. To achieve accurate correspondences across distant views, intermediate in-between frames were taken and the displacements across consecutive frames were added. The overall displacement field was the... |

58 | Relative affine structure: Theory and application to 3D reconstruction from perspective views
- Shashua, Navab
- 1994
(Show Context)
Citation Context ... + kv 0 : The coefficient k is independent of / 2 , i.e., is invariant to the choice of the second view. The lemma, its proof and its theoretical and practical implications are discussed in detail in =-=[28, 32]-=-. Note that the particular case where the homography A is affine, and the epipole v 0 is on the line at infinity, corresponds to the construction of affine structure from two orthographic views [17]. ... |

44 |
Factoring image sequences into shape and motion
- Tomasi, Kanade
- 1992
(Show Context)
Citation Context ...er this process by selecting points in the first frame for which the Hessian matrix of spatial derivatives is well conditioned --- similar to the confidence values suggested in the implementations of =-=[4, 7, 34]-=- --- however, the intention here was not so much as to build a complete system but to test the performance of the trilinear re-projection method and compare it to the performance of epipolar intersect... |

41 |
Projective depth: A geometric invariant for 3D reconstruction from two perspective/orthographic views and for visual recognition
- Shashua
- 1993
(Show Context)
Citation Context ...fi; fl. Proof: Let q 2 / 1 be any point in the first view. There exists a scalar s q that satisfies v 0 �� = Aq \Gamma s q A 0 q. Let H = A \Gamma s q A 0 , and we have Hq �� = v 0 . But, as s=-=hown in [29], Av �-=-� = v 0 for any homography / 1 7! / 2 due to any plane. Therefore, Hv �� = v 0 as well. The mapping of two distinct points q; v onto the same point v 0 could happen only if H is the homography d... |

34 | Relative orientation revisited
- Horn
- 1991
(Show Context)
Citation Context |

31 | Affine and Projective Structure from Motion
- Demey, Zisserman, et al.
- 1992
(Show Context)
Citation Context ... a process that is also known to be unstable in the presence of noise. It is also known that the epipolar geometry alone is sufficient to achieve re-projection by means of intersecting epipolar lines =-=[24, 6, 8, 26, 23, 11]-=- using at least eight corresponding points across the three views. This, however, is possible only if the centers of the three cameras are noncollinear --- which can lead to numerical instability unle... |

30 |
The Reconstruction of a Scene from two Projections - Configurations that Defeat the 8-point Algorithm
- Longuet-Higgins
- 1984
(Show Context)
Citation Context ...ossibly yield a unique solution to the problem of recovering the coefficients. The matter of singular surfaces has been studied for the eight-point case necessary for recovering the epipolar geometry =-=[19, 14, 22]-=-. The same matter concerning the results presented in this paper is an open problem. Moving away from the need to recover the epipolar geometry carries distinct and significant advantages. To get a be... |

27 | Projective geometry for machine vision
- Mundy, Zisserman
- 1992
(Show Context)
Citation Context |

26 |
Invariant linear methods in photogrammetry and model-matching
- Barrett, Brill, et al.
- 1992
(Show Context)
Citation Context |

26 |
The Projective geometry of ambiguous surfaces
- Maybank
- 1989
(Show Context)
Citation Context ...ossibly yield a unique solution to the problem of recovering the coefficients. The matter of singular surfaces has been studied for the eight-point case necessary for recovering the epipolar geometry =-=[19, 14, 22]-=-. The same matter concerning the results presented in this paper is an open problem. Moving away from the need to recover the epipolar geometry carries distinct and significant advantages. To get a be... |

23 | Illumination and view position in 3d visual recognition
- Shashua
- 1992
(Show Context)
Citation Context ...oring a 3D model of the object, or simply by storing at least two arbitrary "model" views of the object --- assuming that the correspondence problem between the model views can somehow be so=-=lved (cf. [27, 5, 33]). During -=-recognition a small number of corresponding points between the novel input view and the model views of a particular candidate object are sufficient to "re-project" the model onto the novel v... |

23 | On Geometric and Algebraic Aspects of 3D Affine and Projective Structures from Perspective 2D Views
- Shashua
- 1994
(Show Context)
Citation Context ... + kv 0 : The coefficient k is independent of / 2 , i.e., is invariant to the choice of the second view. The lemma, its proof and its theoretical and practical implications are discussed in detail in =-=[28, 32]-=-. Note that the particular case where the homography A is affine, and the epipole v 0 is on the line at infinity, corresponds to the construction of affine structure from two orthographic views [17]. ... |

20 | Layered representation for image coding
- Adelson
- 1991
(Show Context)
Citation Context ...y, and robustness (as shown above) due to the short-cut in the computations, is of great importance. Related to image coding, an approach of image decomposition into "layers" was recently pr=-=oposed by [1, 2]-=-. In this approach, a sequence of views is divided up into regions, whose motion of each is described approximately by a 2D affine transformation. The sender sends the first image followed only by the... |

19 | Correspondence and Affine Shape from two Orthographic Views: Motion and Recognition
- Shashua
- 1991
(Show Context)
Citation Context |

16 |
A unified perspective on computational techniques for the measurement of visual motion
- Anandan
- 1987
(Show Context)
Citation Context ...er this process by selecting points in the first frame for which the Hessian matrix of spatial derivatives is well conditioned --- similar to the confidence values suggested in the implementations of =-=[4, 7, 34]-=- --- however, the intention here was not so much as to build a complete system but to test the performance of the trilinear re-projection method and compare it to the performance of epipolar intersect... |

13 | Contour Matching Using Local Affine Transformations
- Bachelder, Ullman
- 1992
(Show Context)
Citation Context ...oring a 3D model of the object, or simply by storing at least two arbitrary "model" views of the object --- assuming that the correspondence problem between the model views can somehow be so=-=lved (cf. [27, 5, 33]). During -=-recognition a small number of corresponding points between the novel input view and the model views of a particular candidate object are sufficient to "re-project" the model onto the novel v... |

12 |
The quadric reference surface: Applications in registering views of complex 3d objects
- Shashua, Toelg
- 1994
(Show Context)
Citation Context ...oring a 3D model of the object, or simply by storing at least two arbitrary "model" views of the object --- assuming that the correspondence problem between the model views can somehow be so=-=lved (cf. [27, 5, 33]). During -=-recognition a small number of corresponding points between the novel input view and the model views of a particular candidate object are sufficient to "re-project" the model onto the novel v... |

7 |
3-D model alignment without computing pose
- Mundy, Welty, et al.
- 1992
(Show Context)
Citation Context |

6 | Model based invariants for 3-D vision - Weinshall - 1993 |

5 |
Robustness of correspondence based structure from motion
- Dutta, Synder
- 1990
(Show Context)
Citation Context ... uncalibrated [17, 25, 39, 10, 13, 30]. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration =-=[3, 9, 12]-=-, and therefore, are unlikely to be of practical use for purposes of re-projection. The non-metric approaches, as a general concept, have not been fully tested on real images, but the methods proposed... |

4 |
stereo vision is not always about 3D reconstruction
- Why
- 1993
(Show Context)
Citation Context ... uncalibrated [17, 25, 39, 10, 13, 30]. The classic approaches for perspective views are known to be unstable under errors in image measurements, narrow field of view, and internal camera calibration =-=[3, 9, 12]-=-, and therefore, are unlikely to be of practical use for purposes of re-projection. The non-metric approaches, as a general concept, have not been fully tested on real images, but the methods proposed... |