Skin and bones: multi-layer, locally affine, optical flow and regularization with transparency

Ju, Shanon X.; Black, Michael J.; Jepson, Allan D.

doi:10.1109/cvpr.1996.517090

Cited by 105 publications

(67 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We estimate the parametric motions in a regularization framework, similar to that used in [14,16]. Specifically, we define an affine model and denote by a s = (a s0 , a s1 , a s2 , a s3 , a s4 , a s5 ) T the vector of all affine parameters for segment s. The motion field w(a s , x) = (u(a s , x), v(a s , x)) T in segment s is given by…”

Section: Parametric Flow Estimating Incorporating Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Liu

Chen

Jia

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Segmentation has gained in popularity in stereo matching. However, it is not trivial to incorporate it in optical flow estimation due to the possible non-rigid motion problem. In this paper, we describe a new optical flow scheme containing three phases. First, we partition the input images and integrate the segmentation information into a variational model where each of the segments is constrained by an affine motion. Then the errors brought in by segmentation are measured and stored in a confidence map. The final flow estimation is achieved through a global optimization phase that minimizes an energy function incorporating the confidence map. Extensive experiments show that the proposed method not only produces quantitatively accurate optical flow estimates but also preserves sharp motion boundaries, which makes the optical flow result usable in a number of computer vision applications, such as image/video segmentation and editing.

show abstract

Section: Parametric Flow Estimating Incorporating Segmentationmentioning

confidence: 99%

“…Zitnick et al [4] generated consistent segments between frames and enforced a translational model within each segment. Piece-wise parametric motion model is also used in [5,7,14] within small patches. This assumption may result in poor estimation of the motion parameters because of the local aperture problem.…”

Section: Related Workmentioning

confidence: 99%

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Liu

Chen

Jia

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The column vectors of W correspond to the q first eigenvectors of (8), that have been previously ordered from the largest eigenvalues to the smallest one. The projected coordinates onto the appearance subspace are: b.…”

Section: The Algorithmmentioning

confidence: 99%

“…Moreover the analysis is instantaneous, which means that is not integrated over many frames. Many authors [15,1,12,2,8] focus on this registration problem in terms of 2D parametric alignment, where the estimation process is still between two frames. Thus, taking into account that the second step, reconstruction, requires that all the transformations must be put in correspondence with a certain frame of reference, the accumulation error can be present in these computations.…”

mentioning

confidence: 99%

An Appearance-Based Method for Parametric Video Registration

Orriols¹,

Barceló²,

Binefa³

2003

ELCVIA

View full text Add to dashboard Cite

In this paper, we address the problem of multi-frame video registration using an appearance-based framework, where linear subspace constraints are applied in terms of the appearance subspace constancy assumption [3]. We frame the multiple-image registration in a two step iterative algorithm. First, a feature space is built through and Singular Value Decomposition (SVD) of a second moment matrix provided by the images in the sequence to be analyzed, where the variabilities of each frame respect to a previously selected frame of reference are encoded. Secondly, a parametric model is introduced in order to estimate the transformation that has been produced across the sequence. This model is described in terms of a polynomial representation of the velocity field evolution, which corresponds to a parametric multi-frame optical flow estimation. The objective function to be minimized considers both issues at the same time, i.e., the appearance representation and the time evolution across the sequence. This function is the connection between the global coordinates in the subspace representation and the parametric optical flow estimates. Both minimization steps are reduced to two linear least squares sub-problems, whose solutions turn out to be in closed form for each iteration. The appearance constraints result to take into account all the images in a sequence in order to estimate the transformation parameters. Finally, results show the extraction of 3D affine structure from multiple views depending on the analysis of the surface polynomial's degree.

show abstract

“…Existing techniques of motion correction [4] remain largely insufficient in dealing with such complex motion. Related work has been reported in dealing with transparent motion [1,2,5,6]. In [7], a technique based on non-parametric motion estimation has been proposed, where a dense motion field is used for motion correction between a mask and a contrast image, and learning-based method is used to facilitate motion estimation.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Layer Separation for Coronary DSA and Enhancement in Fluoroscopic Sequences

Zhu

Prummer

Wang

et al. 2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

View full text Add to dashboard Cite

Abstract. This paper presents a new technique of coronary digital subtraction angiography which separates layers of moving background structures from dynamic fluoroscopic sequences of the heart and obtains moving layers of coronary arteries. A Bayeisan framework combines dense motion estimation, uncertainty propagation and statistical fusion to achieve reliable background layer estimation and motion compensation for coronary sequences. Encouraging results have been achieved on clinically acquired coronary sequences, where the proposed method considerably improves the visibility and perceptibility of coronary arteries undergoing breathing and cardiac movements. Perceptibility improvement is significant especially for very thin vessels. Clinical benefit is expected in the context of obese patients and deep angulation, as well as in the reduction of contrast dose in normal size patients.

show abstract

Skin and bones: multi-layer, locally affine, optical flow and regularization with transparency

Abstract: Abstract

Cited by 105 publications

References 14 publications

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

An Appearance-Based Method for Parametric Video Registration

Dynamic Layer Separation for Coronary DSA and Enhancement in Fluoroscopic Sequences

Contact Info

Product

Resources

About