Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model

doi:10.1006/cviu.1998.0735

Computer Vision and Image Understanding

Volume 73, Issue 3, 1 March 1999, Pages 357-373

https://doi.org/10.1006/cviu.1998.0735 Get rights and content

Abstract

The use of hypothesis verification is recurrent in the model-based recognition literature. Verification consists in measuring how many model features transformed by a pose coincide with some image features. When data involved in the computation of the pose are noisy, the pose is inaccurate and difficult to verify, especially when the objects are partially occluded. To address this problem, the noise in image features is modeled by a Gaussian distribution. A probabilistic framework allows the evaluation of the probability of a matching, knowing that the pose belongs to a rectangular volume of the pose space. It involves quadratic programming, if the transformation is affine. This matching probability is used in an algorithm computing the best pose. It consists in a recursive multiresolution exploration of the pose space, discarding outliers in the match data while the search is progressing. Numerous experimental results are described. They consist of 2D and 3D recognition experiments using the proposed algorithm.

References (29)

B.M. ter Haar Romeny et al.
Higher order differential structure of images
Image Vision Comput
(1994)
J.R. Beveridge et al.
Optimal geometric model matching under full 3d perspective
Comput. Vision Image Understanding
(1995)
D.M. Gavrila et al.
3d object recognition from 2d images using geometric hashing
Pattern Recog. Lett
(1992)
R. Kumar et al.
Robust methods for estimating pose and a sensitivity analysis
Comput. Vision Graphics Image Process.
(1994)
H. Murase et al.
Visual learning and recognition od 3d object from appearance
Int. J. Comput. Vision
(1995)
A. P. Pentland, B. Moghadam, T. Starner, View-based and modular eigenspaces for face recognition, Proc. IEEE Conference...
S. Sclaroff et al.
Modal matching for correspondence and recognition
IEEE Trans. Pattern Anal. Mach. Intell.
(1995)
R. Brunelli et al.
Person identification using multiple cues
IEEE Trans. Pattern Anal. Mach. Intell.
(1995)
W.E.L. Grimson
The combinatorics of heuristic search term for object recognition in cluttered environment
IEEE Trans. Pattern Anal. Mach. Intell.
(1991)
D.W. Jacobs
Robust and efficient detection of salient convex groups
IEEE Trans. Pattern Anal. Mach. Intell.
(1996)

A.C. Califano et al.

Mulidimensional indexing for recognizing visual shapes

IEEE Trans. Pattern Anal. Mach. Intell.

(1994)

C. F. Olson, Time and space efficient pose clustering, Proc. IEEE Conference on Computer Vision and Pattern...

D.P. Huttenlocher et al.

Comparing images using the hausdorff distance

IEEE Trans. Pattern Anal. Mach. Intell.

(1993)

T. L. Gandhi, O. I. Camps, Robust feature selection for object recognition using uncertain 2d image data, Proc. IEEE...

Cited by (47)

An application independent review of multimodal 3D registration methods
2020, Computers and Graphics (Pergamon)
Citation Excerpt :
At the end, the remaining transformation space is tightly bounded and includes the globally optimal solution. An early algorithm, similar to BnB, was proposed by Jurie [182] for 2D/3D alignment with a linear approximation of perspective projection. First, an initial volume of pose space is guessed and all of the correspondences compatible with this volume are considered.
Registration is a ubiquitous operation in Visual Computing, with applications in 3D object retrieval among others. Registration is the process of overlaying two or more datasets taken from different viewpoints, at different times or by different sensors into a common reference frame. Multimodal registration is a special case where the data to be matched do not belong to the same modality and is challenging due to the diverse nature of the modalities involved which makes the creation of a distance function harder. Due to the large number of possible modality combinations and application fields, a considerable number of multimodal registration techniques have been proposed in diverse fields, including medicine and archaeology. This survey aims to unify 3D multimodal registration techniques (i.e. where at least one of the modalities is in 3D) across application domains, with the hope of providing an application-independent view and the potential for cross-fertilization. The problem of 3D multimodal registration is explicitly defined and the various methods are systematically categorized and described in terms of a number of important properties. Methods with publicly available source code have been compared on common datasets. A discussion on trends, observations and challenges for further research concludes the review.
A family of globally optimal branch-and-bound algorithms for 2D–3D correspondence-free registration
2019, Pattern Recognition
Citation Excerpt :
LP relaxation techniques have been developed for complex and highly non-linear problems e.g. [35], where it is used for inlier set maximisation where correspondences are unknown. With respect to the 2D–3D registration problem, Jurie [36] approximates perspective pose by orthographic pose (a linear transformation) to create a problem that may be solved by similar techniques without the need for convex or concave envelopes. However, its use of the Gaussian error model results in an approach that is not robust to outliers.
We present a family of methods for 2D–3D registration spanning both deterministic and non-deterministic branch-and-bound approaches. Critically, the methods exhibit invariance to the underlying scene primitives, enabling e.g. points and lines to be treated on an equivalent basis, potentially enabling a broader range of problems to be tackled while maximising available scene information, all scene primitives being simultaneously considered. Being a branch-and-bound based approach, the method furthermore enjoys intrinsic guarantees of global optimality; while branch-and-bound approaches have been employed in a number of computer vision contexts, the proposed method represents the first time that this strategy has been applied to the 2D–3D correspondence-free registration problem from points and lines. Within the proposed procedure, deterministic and probabilistic procedures serve to speed up the nested branch-and-bound search while maintaining optimality. Experimental evaluation with synthetic and real data indicates that the proposed approach significantly increases both accuracy and robustness compared to the state of the art.
A systematic approach for 2D-image to 3D-range registration in urban environments
2012, Computer Vision and Image Understanding
Citation Excerpt :
Our method on the other hand explores the whole space of possible solutions in an efficient manner and is not a probabilistic approach. Solutions in automated matching of 3D with 2D features in the context of object recognition and localization include the following [18–23]. Recently a number of new methods were developed for attacking the problem of automated alignment of images with dense point clouds derived from range scanners.
The photorealistic modeling of large-scale objects, such as urban scenes, requires the combination of range sensing technology and digital photography. In this paper, we attack the key problem of camera pose estimation, in an automatic and efficient way. First, the camera orientation is recovered by matching vanishing points (extracted from 2D images) with 3D directions (derived from a 3D range model). Then, a hypothesis-and-test algorithm computes the camera positions with respect to the 3D range model by matching corresponding 2D and 3D linear features. The camera positions are further optimized by minimizing a line-to-line distance. The advantage of our method over earlier work has to do with the fact that we do not need to rely on extracted planar facades, or other higher-order features; we are utilizing low-level linear features. That makes this method more general, robust, and efficient. We have also developed a user-interface for allowing users to accurately texture-map 2D images onto 3D range models at interactive rates. We have tested our system in a large variety of urban scenes.
Gravitational pose estimation
2010, Computers and Electrical Engineering
Problem of relative pose estimation between a camera and rigid object, given an object model with feature points and image(s) with respective image points (hence known correspondence) has been extensively studied in the literature. We propose a “correspondenceless” method called gravitational pose estimation (GPE), which is inspired by classical mechanics. GPE can handle occlusion and uses only one image (i.e., perspective projection of the object). GPE creates a simulated gravitational field from the image and lets the object model move and rotate in that force field, starting from an initial pose. Experiments were carried out with both real and synthetic images. Results show that GPE is robust, consistent, and fast (runs in less than a minute). On the average (including up to 30% occlusion cases) it finds the orientation within 6° and the position within 17% of the object’s diameter. SoftPOSIT was so far the best correspondenceless method in the literature that works with a single image and point-based object model like GPE. However, SoftPOSIT’s convergence to a result is sensitive to the choice of initial pose. Even “random start SoftPOSIT,” which performs multiple runs of SoftPOSIT with different initial poses, can often fail. However, SoftPOSIT finds the pose with great precision when it is able to converge. We have also integrated GPE and SoftPOSIT into a single method called GPEsoftPOSIT, which finds the orientation within 3° and the position within 10% of the object’s diameter even under occlusion. In GPEsoftPOSIT, GPE finds a pose that is very close to the true pose, and then SoftPOSIT is used to enhance accuracy of the result. Unlike SoftPOSIT, GPE also has the ability to work with three points as well as planar object models.
Object recognition using point uncertainty regions as pose uncertainty regions
2006, Image and Vision Computing
In this paper, a recognition algorithm based on point features is presented. In this algorithm sets of hypothesized matches between model and image points are generated. From them the pose of the object is estimated and stored in a lookup table. When two similar poses are found the pose is assumed to be correct and the hypothesis is verified. The main contribution of this paper is that poses and their uncertainties are represented by the uncertainty regions of the projections of several 3D points, which are circles in the image. These uncertainty regions are due to the measurement uncertainty of the image features, which result in uncertainty in the recovered pose. When two poses are consistent, the pairs of uncertainty regions of the same 3D point will have a non-empty intersection. The algorithm exploits the fact that these uncertainty regions can be computed easily and accurately. The algorithm has been implemented and tested on real images.
Efficient Globally-Optimal Correspondence-Less Visual Odometry for Planar Ground Vehicles
2022, arXiv

View all citing articles on Scopus

^f1: [email protected]

View full text

Regular ArticleSolution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model

Abstract

Image Vision Comput

Comput. Vision Image Understanding

Pattern Recog. Lett

Comput. Vision Graphics Image Process.

Visual learning and recognition od 3d object from appearance

Int. J. Comput. Vision

Modal matching for correspondence and recognition

IEEE Trans. Pattern Anal. Mach. Intell.

Person identification using multiple cues

IEEE Trans. Pattern Anal. Mach. Intell.

The combinatorics of heuristic search term for object recognition in cluttered environment

IEEE Trans. Pattern Anal. Mach. Intell.

Robust and efficient detection of salient convex groups

IEEE Trans. Pattern Anal. Mach. Intell.

Mulidimensional indexing for recognizing visual shapes

IEEE Trans. Pattern Anal. Mach. Intell.

Comparing images using the hausdorff distance

IEEE Trans. Pattern Anal. Mach. Intell.

Regular Article
Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model