Branch-and-bound hypothesis selection for two-view multiple structure and motion segmentation

Thakoor, Ninad; Gao, Jean

doi:10.1109/cvpr.2008.4587469

Cited by 15 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given two trajectory matrices T 1 ∈ R 2F1×n1 and T 2 ∈ R 2F2×n2 we combine them to create a new trajectory matrix T 3 as follows: (19) where F 3 = min(F 1 , F 2 ) and n 3 = n 1 + n 2 . If F j = F 3 then T j = T j , else T j is taken as rows 1 to 2F 3 of T j .…”

Section: Resultsmentioning

confidence: 99%

“…The idea is to strike a balance between the goodness of fit of a model and the model complexity (which in the multi-structure case is proportional to the number of structures). Previous work on model selection in motion segmentation can roughly be categorised into three groups: Rank detection methods [13], combinatorial methods [15,19] and cluster detection methods [11,4,3].…”

Section: Introductionmentioning

confidence: 99%

“…The second group of methods [15,19] advocate a hypothesise-then-select approach. A set of candidate motions are first generated from the data by random sampling in the manner of RANSAC [9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-structure model selection via kernel optimisation

Chin

Suter

Wang

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine structures present. In contrast to conventional model selection approaches, our method is driven by kernel-based learning. The input data is first clustered based on their potential to have emerged from the same structure. However the number of clusters is deliberately overestimated to obtain a set of initial model fits onto the data. We then resolve the oversegmentation via a series of kernel optimisation conducted through multiple kernel learning, and the concept of kernel-target alignment is used as a model selection criterion. Experiments on synthetic and real data show that our method outperforms previous model selection schemes. We also focus on the application of multibody motion segmentation. In particular we demonstrate success on estimating the number of motions on sequences with more than 3 unique motions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-structure model selection via kernel optimisation

Chin

Suter

Wang

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…In most previous works, the noises are set to be constant all over the sequence [8,11,12,16]. However, it is more reasonable to think of the noises to be changeable among the candidate motion models, for the following reasons: (1) those who assume the noises are constant only consider the feature detector localization error.…”

Section: Discussionmentioning

confidence: 99%

Multiframe Motion Segmentation via Penalized MAP Estimation and Linear Programming

Han

Deng³

et al. 2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

Motion segmentation is an important topic in computer vision. In this paper, we study the problem of multi-body motion segmentation under the affine camera model. We use a mixture of subspace model to describe the multi-body motions. Then the motion segmentation problem is formulated as an MAP estimation problem with model complexity penalty. With several candidate motion models, the problem can be naturally converted into a linear programming problem, which guarantees a global optimality. The main advantages of our algorithm include: It needs no priori on the number of motions and it has comparable high segmentation accuracy with the best of motion-number-known algorithms. Experiments on benchmark data sets illustrate these points.

show abstract

“…Thakoor and Gao [44] and Li [45] proposed an interesting approach to globally optimize a multimodel function with an information criterion regularizer. However, they assume they have a list of model candidates and that the optimal results belong to that list.…”

Section: Existing Methodsmentioning

confidence: 99%

A Branch-and-Bound Approach to Correspondence and Grouping Problems

Bazin

Kweon

et al. 2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our work. It is a key ingredient for a wide range of vision tasks, including three-dimensional reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity or global geometric consistency or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially in the presence of repetitive image textures or mismatches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features extracted from two images as input, and outputs the feature correspondences with the largest number of inliers, which verify both the appearance similarity and geometric constraints. Specifically, we formulate the problem as a mixed integer program and solve it efficiently by a series of linear programs via a branch-and-bound procedure. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.

show abstract

Branch-and-bound hypothesis selection for two-view multiple structure and motion segmentation

Cited by 15 publications

References 18 publications

Multi-structure model selection via kernel optimisation

Multi-structure model selection via kernel optimisation

Multiframe Motion Segmentation via Penalized MAP Estimation and Linear Programming

A Branch-and-Bound Approach to Correspondence and Grouping Problems

Contact Info

Product

Resources

About