Mutual information for multi-modal, discontinuity-preserving image registration

Size: px
Start display at page:

Download "Mutual information for multi-modal, discontinuity-preserving image registration"

Transcription

1 Mutual information for multi-modal, discontinuity-preserving image registration Giorgio Panin German Aerospace Center (DLR) Institute for Robotics and Mechatronics Münchner Straße 20, Weßling Abstract. Multi-sensory data fusion and medical image analysis often pose the challenging task of aligning dense, non-rigid and multi-modal images. However, optical sequences may also present illumination variations and noise. The above problems can be addressed by an invariant similarity measure, such as mutual information. However, in a variational setting convex formulations are generally recommended for efficiency reasons, especially when discontinuities at the motion boundaries have to be preserved. In this paper we propose the TV-MI approach, addressing for the first time all of the above issues, through a primal-dual estimation framework, and a novel approximation of the pixel-wise Hessian matrix, decoupling pixel dependencies while being asymptotically correct. At the same time, we keep a high computational efficiency by means of prequantized kernel density estimation and differentiation. Our approach is demonstrated on ground-truth data from the Middlebury database, as well as medical and visible-infrared image pairs. 1 Introduction An important problem in computer vision is to find visual correspondences between two views of a scene, possibly acquired by multi-modal sensors, or under different illumination conditions. The former is a preliminary step for multisensory data fusion, as well as medical image analysis and visualization. However, robustness to illumination and image noise is also a vital requirement for motion estimation in optical sequences. In the optical flow literature, we can first distinguish between global and local methods, dating back to [1] and [2] respectively, or combinations of both [3]. The former minimize a global energy, that combines a pixel-wise data term, assessing the quality of matching, with a regularization prior, coping with the ill-posedness of the problem. The others extend data terms to local windows of a given aperture, increasing robustness to noise and avoiding further regularization, but usually limited to a sparse set of features in textured areas, roughly undergoing planar homographies. Global energies are efficiently minimized through locally convex approximations of the nonlinear cost function, typically obtained by linearizing residuals,

2 2 Giorgio Panin under an L p -norm or a convex M-estimator. For differentiable cost functions, discretized Euler-Lagrange equations are employed: for example, in [1] a linearized L 2 -norm data term is regularized by the L 2 -norm of the motion field f, and the resulting quadratic problem is solved by Jacobi iterations. These algorithms are also suitable for graphics hardware implementation, because of their highly parallel structure. For preserving motion discontinuities at the surface boundaries, the total variation (TV) regularizer employs instead the L 1 -norm, that allows non differentiable solutions, however adding non-trivial issues to the optimization procedure. Earlier works in this direction [4] use the approximate L 1 regularizer f 2 + ɛ 2, where ɛ is a small positive constant, thus keeping the Euler- Lagrange framework. However, this procedure introduces ill-conditioning, especially for small ɛ. More recently, careful studies have shown how to directly and efficiently address convex TV-L 1 problems [5], including optical flow [6], by means of primaldual formulations, that introduce a dual variable and solve a saddle-point problem in two alternate steps (min-max), coupled by a quadratic penalty. Considering the data term, the simplest and most common assumption is the brightness constancy, that may be violated in presence of photometric changes. This happens in case of a variable camera exposure, as well as environment light variations, and especially for multi-modal data (such as medical, or multispectral images), that bear nonlinear and many-to-one relationships. Since the L p -norm is not robust to such variations, several alternatives have been proposed. To cope with smooth, additive illumination fields, in [6] both images are pre-processed by a structure-texture decomposition [7], which amounts to a L 1 denoising (the ROF model [8]), producing a structure image, that is afterwards removed so that only texture components are used for matching. Other works introduce additional terms such as image gradients [4], which are robust to additive changes, but also more noisy and requiring a proper relative weighting; while others estimate smooth, additive illumination fields [5], or complex parametrized models [9]. A different class of approaches looks instead for more robust and invariant matching indices. For example, normalized cross-correlation (NCC) is invariant to brightness mean and variance, thus allowing linear photometric relationships; it has been recently included into the convex variational framework [10], through local correlation windows, and a second-order Taylor expansion with numerical differentiation. Another index is the correlation ratio (CR) [11], which is invariant to a class of nonlinear, one-to-one relationships. So far, the most general index is mutual information (MI), defined in information theory to express the statistical dependency between two random variables, in this case the corresponding grey pairs: in this way, any photometric relationship is enforced, also nonlinear and many-to-one. Due to this property, as well as a higher robustness to outliers and noise, MI has been initially proposed for medical image registration [12, 13]. Later on,

3 TV-MI image registration 3 it has been applied to stereo, in [14] and in the semi-global matching (SGM) algorithm [15], for object tracking [16] and visual navigation [17]. Notably, [11] considered a unified variational formulation of global NCC, CR and MI, as well as their local counterparts, for multi-modal and non-rigid registration. This approach only relies on gradient descent, through the nonlinear Euler-Lagrange equations. Although MI has been used also for variational registration, in this case we are not aware of any locally convex formulation, which, as we have seen, is the key for an efficient optimization using discontinuity-preserving priors. Our main contribution is, therefore, the integration of global MI into the primal-dual TV framework through locally convex, second-order Taylor expansion. Furthermore, we adopt a particular approximation of the Hessian matrix, motivated by the following insights. In fact, it is well-known that MI is a cascade of two mappings: one at the level of grey-value statistics (Sec. 3.1) and one at pixel-level (Sec. 3.2), where both Hessian contributions contain first- and second-order terms. We choose to retain at the upper level only second-order terms, while keeping only first-order ones at the lower level. This leads to a block-diagonal, negative-semidefinite approximation, resulting in directional searches along image gradients, while being asymptotically correct. By contrast, the traditional approximation first proposed in [18], intuitively following the Gauss-Newton approach, neglects second-order terms everywhere. However, this has been put recently under discussion [17],while already confirmed by a seldom usage even in a few dimensions (e.g. Levenberg-Marquardt strategies [19] show less efficiency than the LSE counterpart). At pixel level, instead, (2 2) rank-1 structure tensors are consistent with the aperture problem of global approaches. By comparison, the second-order approximation of local NCC [10] neglects off-diagonal terms, further decoupling the horizontal and vertical flow components, by assuming in most places to have diagonally-dominant, full-rank blocks, due to the extended sampling windows. In our case, this assumption would be clearly incorrect. The remainder of the paper is organized as follows: in Sec. 2 we review the primal-dual variational approach. Sec. 3 describes our formulation for the MI data term and optimization strategy, finally resuming the TV-MI algorithm. Sec. 4 shows experimental results on the Middlebury training dataset and multimodal images, and Sec. 5 proposes future developments. 2 TV-regularized motion estimation Given two images I 0, I 1, a motion field f = (u(x, y), v(x, y)) is sought in order to match corresponding points I 0 (x, y), I 1 (x + u, y + v) with possibly sub-pixel accuracy, such that some similarity index is maximized, at the same time keeping a smooth field, while preserving discontinuities at the motion boundaries. The first requirement can be expressed, omitting the x, y coordinates for brevity, by a global data term E data (I 0, I 1 (u, v)). The other constraints are usu-

4 4 Giorgio Panin ally incorporated into a smoothness (or soft penalty) term E smooth (u, v), which is a function of the local behaviour of the field, typically through the spatial gradients arg min E smooth ( u, v) + λe data (I 0, I 1 (u, v)) (1) (u,v) with a proper weighting factor λ. Following [5], let F = E smooth, G = λe data, we have the general problem arg min F (Df) + G (f) (2) f X where f : Ω R 2 belongs to an Euclidean space X of functions with open domain, D : X Y is a linear operator such as the component-wise gradient, mapping onto another space Y, F : Y R + and G : X R + are the prior and data terms, for example given by an integral over Ω of the respective L p -norm. Both spaces are endowed with the scalar product, and induced norm f, g = f i g i dx dy; f = f, f (3) i Ω summed over the vector field components i = {1, 2}. If both F, G are convex and lower semi-continuous [5], then (2) can be cast into a saddle-point problem min max Df, p + G (f) F (p) (4) f X p Y where p Y is the dual variable, and F is the Legendre-Fenchel conjugate F (p ) sup p, p F (p) (5) p Y In order to solve (4), first-order algorithms alternate descent and ascent steps in the respective variables f, p, by defining the resolvent, or proximal operators ( ) f = (I + τ G) 1 f ; p = (I + σ F ) 1 ( p) (6) where τ, σ are two parameters, I is the identity mapping, and F is the subgradient of F, which extends the (variational) gradient to non-differentiable but convex functions, being well-defined over the whole domain Y. This operator is given by ( ) (I + τ G) 1 1 f = arg min f f 2τ f 2 + G (f) (7) and similarly for F. Then, an efficient algorithm (Alg. 1 in [5], with θ = 1) iterates the following steps Initialization: choose τ, σ > 0 s.t. τσ D 2 1, set initial values f 0, p 0, and the auxiliary variable f 0 = f 0

5 TV-MI image registration 5 Iterate: for n = 1, 2,... p n = (I + σ F ) 1 ( p n 1 + σd f n 1) f n = (I + τ G) 1 ( f n 1 τd p n) f n = 2f n f n 1 (8) where D is the dual operator: Df, p Y = f, D p X. In particular, the total variation regularizer F T V = Df dxdy (9) Ω is the isotropic L 1 -norm of the distributional derivative, that is defined also for discontinuous fields, and reduces to the gradient D = when f is sufficiently smooth, so that Df = fx 2 + fy 2. The corresponding dual operator is the divergence, p = divp. Thus, proximal operators in (8) are applied to p n p n 1 + σ f n 1 ; f n f n 1 + τdivp n (10) In the following, we will consider the problem in a discrete setting, where f, p are defined on pixel grids, and the discretized operators are given in [5]. Then, it can be shown that D 2 8, and a common choice is τ = σ = 1/ 8. Furthermore, (I + τ F T V ) 1 is the point-wise Euclidean projection p = (I + τ F T V ) 1 ( p) p x,y = p x,y max (1, p x,y ) (11) that is, the temporal variation between I 0 and the warped image I 1 (f) is assumed to be a zero-mean white noise process. 3 Mutual information data term Formally, MI is the Kullback-Leibler divergence between P (i 0, i 1 ) and the product of marginals P (i 0 )P (i 1 ) MI(I 0, I 1 f) = H(I 0 ) + H(I 1 f) H(I 0, I 1 f) (12) = P (i 0, i 1 f) log P (i 0, i 1 f) P (i 0 )P (i 1 f) di 0di 1 where H are the marginal and joint entropies, and we emphasize the dependency of the I 1 sample on f. This quantity must be maximized with respect to f, so we can write E data = MI(I 0, I 1 f). In order to introduce our Hessian approximation, we will first consider the statistical dependency of MI on grey values, and then the lowerlevel dependency upon flow vectors.

6 6 Giorgio Panin 3.1 Approximating the Hessian: grey-value statistics For a given a density estimate P (i 0, i 1 ), obtained from a sample of grey pairs I 0,h, I 1,h ; h = 1,..., N, let us consider the dependency of MI on the I 1 sample 1 (suppressing the 1 index) MI I h = 2 MI I h I k = P (i 0, i 1 ) log P (i 0, i 1 ) i 0,i 1 I h P (i 1 ) 2 P (i 0, i 1 ) log P (i 0, i 1 ) i 0,i 1 I h I k P (i 1 ) ( P (i 0, i 1 ) I h P (i 0, i 1 ) I k + 1 P (i 0, i 1 ) 1 P (i 1 ) ) (13) This Hessian is generally not diagonal since, although sampling schemes for P (i 0, i 1 ) ensure that mixed partials are zero, the last term is generally non zero for h k, leading to a problem of untractable complexity. In order to reduce MI to a sum of independent terms, [14] and [15] linearize P log P around the previous density estimate P = P (I 0, I 1 f), leading to P log P P log P. Although these methods are derivative-free, this corresponds to neglecting first-order terms in the Hessian, that cause the undesired coupling. We can see that the resulting accuracy is mainly related to the finite sample size N, and to the kernel bandwidth: in fact, because of the products, first order terms decay as 1/N 2, while second order terms as 1/N. Moreover, we observed that the approximation is always best at the optimum, i.e. when the joint density is maximally clustered. Finally, the eigenvalues of our approximation have always a larger magnitude than those of the true Hessian, that can be seen from the fact that first-order terms on the diagonal are always non-negative. Among the many existing non-parametric procedures for entropy estimation, we decided to follow the efficient strategy used in [15, 14], extended to our derivative-based framework. Briefly resumed, it consists of a Parzen-based estimation, with pre-quantized kernels assigned to the cells of a ( ) joint histogram P. The density is estimated, after warping I 1 (f), by collecting the histogram of I 0,h, I 1,h, and subsequently convolving it with an isotropic Gaussian K w of bandwidth w. Afterwards, a further convolution of log P with the same kernel, evaluated at the same sample points 2, produces the desired data terms, whose sum is the entropy. H(I 0, I 1 ) = 1 [K w log (K w P )] (I 0,h, I 1,h ) (14) N h and similarly for the marginal entropy H(I 1 ), this time with mono-dimensional convolutions, and a possibly different bandwidth w 1. 1 Notice that we write log instead of (1 + log) as it is often found, because derivatives of a twice-differentiable density integrate to 0. 2 In order to keep a sub-pixel/sub-grey precision, we perform bilinear interpolation at non-integer histogram positions.

7 TV-MI image registration 7 From (14) we obtain derivatives in a straightforward way, again by convolution of the log P table H I 1,h = 1 N [K w log (K w P )] (I 0,h, I 1,h ) (15) 2 H I1,h 2 1 N [K w log (K w P )] (I 0,h, I 1,h ) where K, K are first- and second-derivatives along I 1, and the last equation comes from the previously explained approximation to (13). All of these operations are efficiently carried out by the FFT. The bandwitdths w, w 1 for (14) are estimated in a maximum-likelihood way, according to cross-validation rules [11], that can be shown to require a convolution by K/ w. In practice, performing the above convolutions is still an expensive operation; therefore, we update those tables only once per pyramid level, while interpolating them at new values of I 1 (f) for computing the Hessian and gradient. The latter operations are performed in an intermediate warp loop (Fig. 1), while the innermost loop alternates primal-dual steps (8) until convergence. 3.2 Approximating the Hessian: directional derivatives At the pixel level, the aperture problem results in rank-deficient (2 2) diagonal blocks of the overall Hessian. In fact, after decoupling pixel-wise dependencies, we can compute derivatives of MI w.r.t. the flow MI f h 2 MI fh 2 = MI I 1,h I 1,h (16) = 2 MI I1,h 2 I 1,h I1,h T + MI 2 I 1,h I 1,h fh 2 where, hereafter dropping the h index [ I I I T 2 = x I x I y I x I y I 2 y ] ; 2 [ ] I f 2 = Ixx I xy I xy I yy (17) are the (rank-1) structure tensor, and the Hessian of I 1, respectively. At the optimum, in absence of noise, (MI)/ I 1 vanishes from (16), so we approximately keep the rank-1 term, scaled by the second derivatives of MI. The image Hessian is seldom used in the literature, because it may be indefinite, and consists of possibly noisy values. However, we have to further check the factor 2 MI/ I 2 1 in order to ensure a negative-semidefinite matrix. In fact, during the initial stages the density is spreaded out, and some places may have a positive (or almost zero) curvature. Therefore, we threshold each factor to a maximum value D 2 max < 0. In order to cope with the rank deficiency, the primal step thus relies on the regularizing prior, whose strict convexity ensures a unique minimum. Since the

8 8 Giorgio Panin Initialization: Let I 0, I 1 be two images, set f 0 and an initial guess for w, w 1. Compute the two pyramids at L levels, including sub-octaves and related subsampling. Outer loop: let f l 1 be the result at the previous level 1. Upsample f l 1 f l (and the dual field p l 1 p l ) 2. Warp I 1 and I 1 at f l, and collect the joint histogram 3. Adapt w, w 1 with maximum-likelhood ascent 4. Compute the entropy tables for MI (14)(15) 5. Warp loop: initialize f 0 = f l, and repeat (a) Warp I 1 at f 0 and compute MI gradient and Hessian, by interpolating the tables at (I 0, I 1) (b) Inner loop: iterate n = 1, 2,... i. Perform the dual step (10)(11) to obtain f n ii. Solve (20) and update the primal variable f n (c) Apply median filtering to f n, and update the expansion point f 0 = f n Fig. 1. The TV-MI algorithm. prior f f 2 is isotropic in (x, y), the problem reduces to a mono-dimensional search, along n = I 1 / I 1. For this purpose, first- and second-order directional derivatives are given by MI n 2 MI n 2 = MI I 1 I 1 (18) = 2 MI I 2 1 I MI 2 I 1 I 1 n 2 where, once again, the last term of the second derivative is neglected. Thus, we look for ρ n (f T f ), the projected motion field along n, and conversely f = f + ρn. Several primal-dual steps (Fig. 1) are needed for the TV-regularized optimization, so that prior values f n will be different from the initial expansion point f 0. ( Therefore, by defining ρ n = n T f 0 f ), n dropping the n index, the primal step becomes { [ ρ 2 MI arg min ρ 2τ λ I 1 (ρ ρ) ]} MI I 1 2 I1 2 I 1 2 (ρ ρ) 2 (19) where derivatives are computed at f 0, that is solved by ρ = MI I 1 2 MI I 1 I1 2 I 1 2 ρ (20) 1 λτ 2 MI I1 2 I 1 2

9 TV-MI image registration 9 Fig. 2. Photometric variations of different types (see text), added to the second image of the RubberWhale sequence. First row: image; Second row: result of TV-L 1 with illumination field estimation [5] (β = 0.05); Third row: result of TV-MI. Dataset Dimetrodon Grove2 Grove3 Hydrangea RubberWhale Urban2 Urban3 Venus Average angular error (AE) Original 3.39, , , , , , , , 4.59 Noise 26.09, , , , , , , , Linear 6.08, , , , , , , , 4.67 Square 5.80, , , , , , , , 4.38 Neg. square 80.79, , , , , , , , 4.45 Two-to-one 88.56, , , , , , , , Average end-point error (EE) Original 0.18, , , , , , , , 0.30 Noise 1.14, , , , , , , , 1.16 Add. field 0.22, , , , , , , , 0.63 Linear 0.30, , , , , , , , 0.30 Square 0.28, , , , , , , , 0.31 Neg. square 31.04, , , , , , , , 0.31 Two-to-one 22.65, , , , , , , , 0.71 Table 1. Ground-truth comparison on the Middlebury dataset. On each entry, results for TV-L 1 (left) and TV-MI (right) are shown. Optimization failures are marked. 4 Experimental results In order to assess the quality of the TV-MI algorithm, we tested it first on optical sequences with ground-truth, using the Middlebury datasets 3, and compared with the illumination-robust TV-L 1 algorithm [5], that estimates additive fields q(x, y) I t I n 1 (u u n, v v n ) + I n t + βq (21) with an additional coefficient β, so that f is augmented to f = (u, v, q). This over-parametrization leads to a compromise between robustness and precision: a high β tends to estimate strong brightness variations and suppress motion, while a low β cannot deal with the actual illumination changes, increasing the risk of divergence. For this comparison, we run the TV-L 1 Matlab implementation available at the TU-Graz computer vision website 4. Our algorithm is currently in Matlab

10 10 Giorgio Panin code, showing roughly the same timing: for example, the RubberWhale sequence takes about 45 sec. for TV-MI and 51 sec. for TV-L 1. Throughout all sequences, parameters were set as follows: data term weight λ = 1 for TV-MI (λ = 50 for TV-L 1 ), initial guess for kernel size w = 5, pyramid levels 30 (with reduction factor 0.9), primal-dual coefficients τ = σ = 1/ 8, 1 warp iteration and 50 inner-loop iterations TV L1 (beta=0) TV L1 (beta=0.05) TV MI Rubberwhale average angular error 6 5 Rubberwhale average end point error TV L1 (beta=0) TV L1 (beta=0.05) TV MI Gaussian noise std Gaussian noise std. Fig. 3. Average estimation errors at different levels of additive noise. In the first set of experiments, we also set β = 0, obtaining the result marked Original in Table 1. As we can see, for a constant illumination, our algorithm shows similar performances or slight improvements. Subsequently, we create more challenging conditions, by making photometric changes to the second image I 1 of each sequence (Fig. 2 shows the RubberWhale example) in the following order: additive Gaussian noise (σ = 0.1), linear map 0.7I , nonlinear one-to-one map I 2 1, with color inversion 1 I 2 1, and twoto-one map 2 I In order to cope with these changes, we set β = 0.05 for TV-L 1. We can see how MI can cope with linear and nonlinear maps, outperforming L 1 most of the times, and showing an improved robustness to random noise (see also Fig. 3). Examples of MRI/CT and near infrared (NIR)/optical pairs, bearing more complex photometric relationships, are shown in Fig Conclusions In this paper, we presented the TV-MI approach for multi-modal and discontinuitypreserving variational image registration. Future developments may follow several directions. For example, the TV regularizer can be replaced by a more robust, anisotropic Huber term [10]. Moreover, as for any global data term, MI performances degrade in presence of a slowly

11 TV-MI image registration 11 Fig. 4. Multi-modal registration of medical and infrared-optical images. From left to right: original images; superimposed images, before and after warping. Optical/NIR pictures re-printed with permission ( c James McCreary, varying illumination field, that creates a one-to-many relationship by spreading out the joint histogram. For this purpose, here one may resort either to a local formulation of statistics [11], or to an additional parametric field. Finally, a GPU-based implementation can largely improve the speed of histogram sampling, FFT convolution, gradient and Hessian interpolation, and solution to the primal problem. References 1. Horn, B.K.P., Schunk, B.G.: Determining optical flow. Artificial Intelligence 17 (1981)

12 12 Giorgio Panin 2. Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision (darpa). In: Proceedings of the 1981 DARPA Image Understanding Workshop. (1981) Bruhn, A., Weickert, J., Schnörr, C.: Lucas-kanade meets horn-schunck: combining local and global optic flow methods. International Journal of Computer Vision 61 (2005) Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Computer Vision - ECCV 2004, 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, Proceedings, Part IV. (2004) Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. Journal of Mathematical Imaging and Vision 40 (2011) Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D. In: An Improved Algorithm for TV-L1 Optical Flow. Springer-Verlag, Berlin, Heidelberg (2009) Aujol, J.F., Gilboa, G., Chan, T.F., Osher, S.: Structure-texture image decomposition - modeling, algorithms, and parameter selection. International Journal of Computer Vision 67 (2006) Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D 60 (1992) Haussecker, H.W., Fleet, D.J.: Computing optical flow with physical models of brightness variation. IEEE Trans. Pattern Anal. Mach. Intell. 23 (2001) Werlberger, M., Pock, T., Bischof, H.: Motion estimation with non-local total variation regularization. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA (2010) 11. Hermosillo, G., Chefd Hotel, C., Faugeras, O.D.: Variational methods for multimodal image matching. International Journal of Computer Vision 50 (2002) Gaens, T., Maes, F., Vandermeulen, D., Suetens, P. In: Non-rigid multimodal image registration using mutual information. Volume Springer (1998) Wells, W., Viola, P., Atsumi, H., Nakajima, S., Kikinis, R.: Multi-modal volume registration by maximization of mutual information. Medical Image Analysis 1 (1996) Kim, J., Kolmogorov, V., Zabih, R.: Visual correspondence using energy minimization and mutual information. In: 9th IEEE International Conference on Computer Vision (ICCV 2003), October 2003, Nice, France. (2003) Hirschmüller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30 (2008) Panin, G., Knoll, A.: Mutual information-based 3d object tracking. International Journal of Computer Vision 78 (2008) Dame, A., Marchand, E.: Accurate real-time tracking using mutual information. In: IEEE Int. Symp. on Mixed and Augmented Reality, ISMAR 10, Seoul, Korea (2010) Thevenaz, P., Unser, M.: Optimization of mutual information for multiresolution image registration. IEEE Transactions on Image Processing 9 (2000) Pluim, J.P.W., Maintz, J.B.A., Viergever, M.A.: Mutual-information-based registration of medical images: a survey. Medical Imaging, IEEE Transactions on 22 (2003)

Motion Estimation (I) Ce Liu Microsoft Research New England

Motion Estimation (I) Ce Liu Microsoft Research New England Motion Estimation (I) Ce Liu celiu@microsoft.com Microsoft Research New England We live in a moving world Perceiving, understanding and predicting motion is an important part of our daily lives Motion

More information

Motion Estimation (I)

Motion Estimation (I) Motion Estimation (I) Ce Liu celiu@microsoft.com Microsoft Research New England We live in a moving world Perceiving, understanding and predicting motion is an important part of our daily lives Motion

More information

Pose estimation from point and line correspondences

Pose estimation from point and line correspondences Pose estimation from point and line correspondences Giorgio Panin October 17, 008 1 Problem formulation Estimate (in a LSE sense) the pose of an object from N correspondences between known object points

More information

Efficient Nonlocal Regularization for Optical Flow

Efficient Nonlocal Regularization for Optical Flow Efficient Nonlocal Regularization for Optical Flow Philipp Krähenbühl and Vladlen Koltun Stanford University {philkr,vladlen}@cs.stanford.edu Abstract. Dense optical flow estimation in images is a challenging

More information

Dense Optical Flow Estimation from the Monogenic Curvature Tensor

Dense Optical Flow Estimation from the Monogenic Curvature Tensor Dense Optical Flow Estimation from the Monogenic Curvature Tensor Di Zang 1, Lennart Wietzke 1, Christian Schmaltz 2, and Gerald Sommer 1 1 Department of Computer Science, Christian-Albrechts-University

More information

A Tutorial on Primal-Dual Algorithm

A Tutorial on Primal-Dual Algorithm A Tutorial on Primal-Dual Algorithm Shenlong Wang University of Toronto March 31, 2016 1 / 34 Energy minimization MAP Inference for MRFs Typical energies consist of a regularization term and a data term.

More information

Introduction to motion correspondence

Introduction to motion correspondence Introduction to motion correspondence 1 IPAM - UCLA July 24, 2013 Iasonas Kokkinos Center for Visual Computing Ecole Centrale Paris / INRIA Saclay Why estimate visual motion? 2 Tracking Segmentation Structure

More information

EE 367 / CS 448I Computational Imaging and Display Notes: Image Deconvolution (lecture 6)

EE 367 / CS 448I Computational Imaging and Display Notes: Image Deconvolution (lecture 6) EE 367 / CS 448I Computational Imaging and Display Notes: Image Deconvolution (lecture 6) Gordon Wetzstein gordon.wetzstein@stanford.edu This document serves as a supplement to the material discussed in

More information

Nonlinear Diffusion. Journal Club Presentation. Xiaowei Zhou

Nonlinear Diffusion. Journal Club Presentation. Xiaowei Zhou 1 / 41 Journal Club Presentation Xiaowei Zhou Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology 2009-12-11 2 / 41 Outline 1 Motivation Diffusion process

More information

Copula based Divergence Measures and their use in Image Registration

Copula based Divergence Measures and their use in Image Registration 7th European Signal Processing Conference (EUSIPCO 009) Glasgow, Scotland, August 4-8, 009 Copula based Divergence Measures and their use in Image Registration T S Durrani and Xuexing Zeng Centre of Excellence

More information

Edges and Scale. Image Features. Detecting edges. Origin of Edges. Solution: smooth first. Effects of noise

Edges and Scale. Image Features. Detecting edges. Origin of Edges. Solution: smooth first. Effects of noise Edges and Scale Image Features From Sandlot Science Slides revised from S. Seitz, R. Szeliski, S. Lazebnik, etc. Origin of Edges surface normal discontinuity depth discontinuity surface color discontinuity

More information

Dual methods for the minimization of the total variation

Dual methods for the minimization of the total variation 1 / 30 Dual methods for the minimization of the total variation Rémy Abergel supervisor Lionel Moisan MAP5 - CNRS UMR 8145 Different Learning Seminar, LTCI Thursday 21st April 2016 2 / 30 Plan 1 Introduction

More information

Convex Hodge Decomposition of Image Flows

Convex Hodge Decomposition of Image Flows Convex Hodge Decomposition of Image Flows Jing Yuan 1, Gabriele Steidl 2, Christoph Schnörr 1 1 Image and Pattern Analysis Group, Heidelberg Collaboratory for Image Processing, University of Heidelberg,

More information

A First Order Primal-Dual Algorithm for Nonconvex T V q Regularization

A First Order Primal-Dual Algorithm for Nonconvex T V q Regularization A First Order Primal-Dual Algorithm for Nonconvex T V q Regularization Thomas Möllenhoff, Evgeny Strekalovskiy, and Daniel Cremers TU Munich, Germany Abstract. We propose an efficient first order primal-dual

More information

Generalized Newton-Type Method for Energy Formulations in Image Processing

Generalized Newton-Type Method for Energy Formulations in Image Processing Generalized Newton-Type Method for Energy Formulations in Image Processing Leah Bar and Guillermo Sapiro Department of Electrical and Computer Engineering University of Minnesota Outline Optimization in

More information

An Adaptive Confidence Measure for Optical Flows Based on Linear Subspace Projections

An Adaptive Confidence Measure for Optical Flows Based on Linear Subspace Projections An Adaptive Confidence Measure for Optical Flows Based on Linear Subspace Projections Claudia Kondermann, Daniel Kondermann, Bernd Jähne, Christoph Garbe Interdisciplinary Center for Scientific Computing

More information

A Generative Model Based Approach to Motion Segmentation

A Generative Model Based Approach to Motion Segmentation A Generative Model Based Approach to Motion Segmentation Daniel Cremers 1 and Alan Yuille 2 1 Department of Computer Science University of California at Los Angeles 2 Department of Statistics and Psychology

More information

Erkut Erdem. Hacettepe University February 24 th, Linear Diffusion 1. 2 Appendix - The Calculus of Variations 5.

Erkut Erdem. Hacettepe University February 24 th, Linear Diffusion 1. 2 Appendix - The Calculus of Variations 5. LINEAR DIFFUSION Erkut Erdem Hacettepe University February 24 th, 2012 CONTENTS 1 Linear Diffusion 1 2 Appendix - The Calculus of Variations 5 References 6 1 LINEAR DIFFUSION The linear diffusion (heat)

More information

Global parametric image alignment via high-order approximation

Global parametric image alignment via high-order approximation Global parametric image alignment via high-order approximation Y. Keller, A. Averbuch 2 Electrical & Computer Engineering Department, Ben-Gurion University of the Negev. 2 School of Computer Science, Tel

More information

Revisiting Horn and Schunck: Interpretation as Gauß-Newton Optimisation

Revisiting Horn and Schunck: Interpretation as Gauß-Newton Optimisation ZIKIC, KAMEN, AND NAVAB: REVISITING HORN AND SCHUNCK 1 Revisiting Horn and Schunck: Interpretation as Gauß-Newton Optimisation Darko Zikic 1 zikic@in.tum.de Ali Kamen ali.kamen@siemens.com Nassir Navab

More information

Pose Tracking II! Gordon Wetzstein! Stanford University! EE 267 Virtual Reality! Lecture 12! stanford.edu/class/ee267/!

Pose Tracking II! Gordon Wetzstein! Stanford University! EE 267 Virtual Reality! Lecture 12! stanford.edu/class/ee267/! Pose Tracking II! Gordon Wetzstein! Stanford University! EE 267 Virtual Reality! Lecture 12! stanford.edu/class/ee267/!! WARNING! this class will be dense! will learn how to use nonlinear optimization

More information

Optic Flow Computation with High Accuracy

Optic Flow Computation with High Accuracy Cognitive Computer Vision Colloquium Prague, January 12 13, 2004 Optic Flow Computation with High ccuracy Joachim Weickert Saarland University Saarbrücken, Germany joint work with Thomas Brox ndrés Bruhn

More information

A Riemannian Framework for Denoising Diffusion Tensor Images

A Riemannian Framework for Denoising Diffusion Tensor Images A Riemannian Framework for Denoising Diffusion Tensor Images Manasi Datar No Institute Given Abstract. Diffusion Tensor Imaging (DTI) is a relatively new imaging modality that has been extensively used

More information

Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems

Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems 1 Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems V. Estivill-Castro 2 Perception Concepts Vision Chapter 4 (textbook) Sections 4.3 to 4.5 What is the course

More information

Adaptive Primal Dual Optimization for Image Processing and Learning

Adaptive Primal Dual Optimization for Image Processing and Learning Adaptive Primal Dual Optimization for Image Processing and Learning Tom Goldstein Rice University tag7@rice.edu Ernie Esser University of British Columbia eesser@eos.ubc.ca Richard Baraniuk Rice University

More information

NONLINEAR DIFFUSION PDES

NONLINEAR DIFFUSION PDES NONLINEAR DIFFUSION PDES Erkut Erdem Hacettepe University March 5 th, 0 CONTENTS Perona-Malik Type Nonlinear Diffusion Edge Enhancing Diffusion 5 References 7 PERONA-MALIK TYPE NONLINEAR DIFFUSION The

More information

ENERGY METHODS IN IMAGE PROCESSING WITH EDGE ENHANCEMENT

ENERGY METHODS IN IMAGE PROCESSING WITH EDGE ENHANCEMENT ENERGY METHODS IN IMAGE PROCESSING WITH EDGE ENHANCEMENT PRASHANT ATHAVALE Abstract. Digital images are can be realized as L 2 (R 2 objects. Noise is introduced in a digital image due to various reasons.

More information

ITK Filters. Thresholding Edge Detection Gradients Second Order Derivatives Neighborhood Filters Smoothing Filters Distance Map Image Transforms

ITK Filters. Thresholding Edge Detection Gradients Second Order Derivatives Neighborhood Filters Smoothing Filters Distance Map Image Transforms ITK Filters Thresholding Edge Detection Gradients Second Order Derivatives Neighborhood Filters Smoothing Filters Distance Map Image Transforms ITCS 6010:Biomedical Imaging and Visualization 1 ITK Filters:

More information

Corners, Blobs & Descriptors. With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros

Corners, Blobs & Descriptors. With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros Corners, Blobs & Descriptors With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros Motivation: Build a Panorama M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003 How do we build panorama?

More information

Lecture 8: Interest Point Detection. Saad J Bedros

Lecture 8: Interest Point Detection. Saad J Bedros #1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Review of Edge Detectors #2 Today s Lecture Interest Points Detection What do we mean with Interest Point Detection in an Image Goal:

More information

Linear Diffusion and Image Processing. Outline

Linear Diffusion and Image Processing. Outline Outline Linear Diffusion and Image Processing Fourier Transform Convolution Image Restoration: Linear Filtering Diffusion Processes for Noise Filtering linear scale space theory Gauss-Laplace pyramid for

More information

Variational Methods in Signal and Image Processing

Variational Methods in Signal and Image Processing Variational Methods in Signal and Image Processing XU WANG Texas A&M University Dept. of Electrical & Computer Eng. College Station, Texas United States xu.wang@tamu.edu ERCHIN SERPEDIN Texas A&M University

More information

Total Variation Theory and Its Applications

Total Variation Theory and Its Applications Total Variation Theory and Its Applications 2nd UCC Annual Research Conference, Kingston, Jamaica Peter Ndajah University of the Commonwealth Caribbean, Kingston, Jamaica September 27, 2018 Peter Ndajah

More information

Mixture Models and EM

Mixture Models and EM Mixture Models and EM Goal: Introduction to probabilistic mixture models and the expectationmaximization (EM) algorithm. Motivation: simultaneous fitting of multiple model instances unsupervised clustering

More information

ECS289: Scalable Machine Learning

ECS289: Scalable Machine Learning ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Sept 29, 2016 Outline Convex vs Nonconvex Functions Coordinate Descent Gradient Descent Newton s method Stochastic Gradient Descent Numerical Optimization

More information

Multigrid Acceleration of the Horn-Schunck Algorithm for the Optical Flow Problem

Multigrid Acceleration of the Horn-Schunck Algorithm for the Optical Flow Problem Multigrid Acceleration of the Horn-Schunck Algorithm for the Optical Flow Problem El Mostafa Kalmoun kalmoun@cs.fau.de Ulrich Ruede ruede@cs.fau.de Institute of Computer Science 10 Friedrich Alexander

More information

Image Alignment and Mosaicing

Image Alignment and Mosaicing Image Alignment and Mosaicing Image Alignment Applications Local alignment: Tracking Stereo Global alignment: Camera jitter elimination Image enhancement Panoramic mosaicing Image Enhancement Original

More information

Feature Vector Similarity Based on Local Structure

Feature Vector Similarity Based on Local Structure Feature Vector Similarity Based on Local Structure Evgeniya Balmachnova, Luc Florack, and Bart ter Haar Romeny Eindhoven University of Technology, P.O. Box 53, 5600 MB Eindhoven, The Netherlands {E.Balmachnova,L.M.J.Florack,B.M.terHaarRomeny}@tue.nl

More information

Introduction to Nonlinear Image Processing

Introduction to Nonlinear Image Processing Introduction to Nonlinear Image Processing 1 IPAM Summer School on Computer Vision July 22, 2013 Iasonas Kokkinos Center for Visual Computing Ecole Centrale Paris / INRIA Saclay Mean and median 2 Observations

More information

Kernel Correlation for Robust Distance Minimization

Kernel Correlation for Robust Distance Minimization Chapter 2 Kernel Correlation for Robust Distance Minimization We introduce kernel correlation between points, between a point and a set of points, and among a set of points. We show that kernel correlation

More information

INTEREST POINTS AT DIFFERENT SCALES

INTEREST POINTS AT DIFFERENT SCALES INTEREST POINTS AT DIFFERENT SCALES Thank you for the slides. They come mostly from the following sources. Dan Huttenlocher Cornell U David Lowe U. of British Columbia Martial Hebert CMU Intuitively, junctions

More information

Learning features by contrasting natural images with noise

Learning features by contrasting natural images with noise Learning features by contrasting natural images with noise Michael Gutmann 1 and Aapo Hyvärinen 12 1 Dept. of Computer Science and HIIT, University of Helsinki, P.O. Box 68, FIN-00014 University of Helsinki,

More information

Parameter Identification in Partial Differential Equations

Parameter Identification in Partial Differential Equations Parameter Identification in Partial Differential Equations Differentiation of data Not strictly a parameter identification problem, but good motivation. Appears often as a subproblem. Given noisy observation

More information

Filtering and Edge Detection

Filtering and Edge Detection Filtering and Edge Detection Local Neighborhoods Hard to tell anything from a single pixel Example: you see a reddish pixel. Is this the object s color? Illumination? Noise? The next step in order of complexity

More information

Inverse problems Total Variation Regularization Mark van Kraaij Casa seminar 23 May 2007 Technische Universiteit Eindh ove n University of Technology

Inverse problems Total Variation Regularization Mark van Kraaij Casa seminar 23 May 2007 Technische Universiteit Eindh ove n University of Technology Inverse problems Total Variation Regularization Mark van Kraaij Casa seminar 23 May 27 Introduction Fredholm first kind integral equation of convolution type in one space dimension: g(x) = 1 k(x x )f(x

More information

Energy-Based Image Simplification with Nonlocal Data and Smoothness Terms

Energy-Based Image Simplification with Nonlocal Data and Smoothness Terms Energy-Based Image Simplification with Nonlocal Data and Smoothness Terms Stephan Didas 1, Pavel Mrázek 2, and Joachim Weickert 1 1 Mathematical Image Analysis Group Faculty of Mathematics and Computer

More information

Supplementary Material: Minimum Delay Moving Object Detection

Supplementary Material: Minimum Delay Moving Object Detection Supplementary Material: Minimum Delay Moving Object Detection Dong Lao and Ganesh Sundaramoorthi King Abdullah University of Science & Technology KAUST, Saudi Arabia {dong.lao, ganesh.sundaramoorthi}@kaust.edu.sa.

More information

Human Pose Tracking I: Basics. David Fleet University of Toronto

Human Pose Tracking I: Basics. David Fleet University of Toronto Human Pose Tracking I: Basics David Fleet University of Toronto CIFAR Summer School, 2009 Looking at People Challenges: Complex pose / motion People have many degrees of freedom, comprising an articulated

More information

Deformation and Viewpoint Invariant Color Histograms

Deformation and Viewpoint Invariant Color Histograms 1 Deformation and Viewpoint Invariant Histograms Justin Domke and Yiannis Aloimonos Computer Vision Laboratory, Department of Computer Science University of Maryland College Park, MD 274, USA domke@cs.umd.edu,

More information

Variational Methods in Image Denoising

Variational Methods in Image Denoising Variational Methods in Image Denoising Jamylle Carter Postdoctoral Fellow Mathematical Sciences Research Institute (MSRI) MSRI Workshop for Women in Mathematics: Introduction to Image Analysis 22 January

More information

Feature extraction: Corners and blobs

Feature extraction: Corners and blobs Feature extraction: Corners and blobs Review: Linear filtering and edge detection Name two different kinds of image noise Name a non-linear smoothing filter What advantages does median filtering have over

More information

Lecture 8: Interest Point Detection. Saad J Bedros

Lecture 8: Interest Point Detection. Saad J Bedros #1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Last Lecture : Edge Detection Preprocessing of image is desired to eliminate or at least minimize noise effects There is always tradeoff

More information

Generalized Laplacian as Focus Measure

Generalized Laplacian as Focus Measure Generalized Laplacian as Focus Measure Muhammad Riaz 1, Seungjin Park, Muhammad Bilal Ahmad 1, Waqas Rasheed 1, and Jongan Park 1 1 School of Information & Communications Engineering, Chosun University,

More information

Numerisches Rechnen. (für Informatiker) M. Grepl P. Esser & G. Welper & L. Zhang. Institut für Geometrie und Praktische Mathematik RWTH Aachen

Numerisches Rechnen. (für Informatiker) M. Grepl P. Esser & G. Welper & L. Zhang. Institut für Geometrie und Praktische Mathematik RWTH Aachen Numerisches Rechnen (für Informatiker) M. Grepl P. Esser & G. Welper & L. Zhang Institut für Geometrie und Praktische Mathematik RWTH Aachen Wintersemester 2011/12 IGPM, RWTH Aachen Numerisches Rechnen

More information

PDEs in Image Processing, Tutorials

PDEs in Image Processing, Tutorials PDEs in Image Processing, Tutorials Markus Grasmair Vienna, Winter Term 2010 2011 Direct Methods Let X be a topological space and R: X R {+ } some functional. following definitions: The mapping R is lower

More information

Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction

Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction Qifa Ke and Takeo Kanade Department of Computer Science, Carnegie Mellon University Email: ke@cmu.edu, tk@cs.cmu.edu Abstract

More information

Multiscale Image Transforms

Multiscale Image Transforms Multiscale Image Transforms Goal: Develop filter-based representations to decompose images into component parts, to extract features/structures of interest, and to attenuate noise. Motivation: extract

More information

ECE521 week 3: 23/26 January 2017

ECE521 week 3: 23/26 January 2017 ECE521 week 3: 23/26 January 2017 Outline Probabilistic interpretation of linear regression - Maximum likelihood estimation (MLE) - Maximum a posteriori (MAP) estimation Bias-variance trade-off Linear

More information

CS 231A Section 1: Linear Algebra & Probability Review. Kevin Tang

CS 231A Section 1: Linear Algebra & Probability Review. Kevin Tang CS 231A Section 1: Linear Algebra & Probability Review Kevin Tang Kevin Tang Section 1-1 9/30/2011 Topics Support Vector Machines Boosting Viola Jones face detector Linear Algebra Review Notation Operations

More information

CS 231A Section 1: Linear Algebra & Probability Review

CS 231A Section 1: Linear Algebra & Probability Review CS 231A Section 1: Linear Algebra & Probability Review 1 Topics Support Vector Machines Boosting Viola-Jones face detector Linear Algebra Review Notation Operations & Properties Matrix Calculus Probability

More information

Stable Adaptive Momentum for Rapid Online Learning in Nonlinear Systems

Stable Adaptive Momentum for Rapid Online Learning in Nonlinear Systems Stable Adaptive Momentum for Rapid Online Learning in Nonlinear Systems Thore Graepel and Nicol N. Schraudolph Institute of Computational Science ETH Zürich, Switzerland {graepel,schraudo}@inf.ethz.ch

More information

Lecture Notes 5: Multiresolution Analysis

Lecture Notes 5: Multiresolution Analysis Optimization-based data analysis Fall 2017 Lecture Notes 5: Multiresolution Analysis 1 Frames A frame is a generalization of an orthonormal basis. The inner products between the vectors in a frame and

More information

Notes on Regularization and Robust Estimation Psych 267/CS 348D/EE 365 Prof. David J. Heeger September 15, 1998

Notes on Regularization and Robust Estimation Psych 267/CS 348D/EE 365 Prof. David J. Heeger September 15, 1998 Notes on Regularization and Robust Estimation Psych 67/CS 348D/EE 365 Prof. David J. Heeger September 5, 998 Regularization. Regularization is a class of techniques that have been widely used to solve

More information

Single-Image-Based Rain and Snow Removal Using Multi-guided Filter

Single-Image-Based Rain and Snow Removal Using Multi-guided Filter Single-Image-Based Rain and Snow Removal Using Multi-guided Filter Xianhui Zheng 1, Yinghao Liao 1,,WeiGuo 2, Xueyang Fu 2, and Xinghao Ding 2 1 Department of Electronic Engineering, Xiamen University,

More information

Image enhancement. Why image enhancement? Why image enhancement? Why image enhancement? Example of artifacts caused by image encoding

Image enhancement. Why image enhancement? Why image enhancement? Why image enhancement? Example of artifacts caused by image encoding 13 Why image enhancement? Image enhancement Example of artifacts caused by image encoding Computer Vision, Lecture 14 Michael Felsberg Computer Vision Laboratory Department of Electrical Engineering 12

More information

Analysis of Numerical Methods for Level Set Based Image Segmentation

Analysis of Numerical Methods for Level Set Based Image Segmentation Analysis of Numerical Methods for Level Set Based Image Segmentation Björn Scheuermann and Bodo Rosenhahn Institut für Informationsverarbeitung Leibnitz Universität Hannover {scheuerm,rosenhahn}@tnt.uni-hannover.de

More information

Scale-Invariance of Support Vector Machines based on the Triangular Kernel. Abstract

Scale-Invariance of Support Vector Machines based on the Triangular Kernel. Abstract Scale-Invariance of Support Vector Machines based on the Triangular Kernel François Fleuret Hichem Sahbi IMEDIA Research Group INRIA Domaine de Voluceau 78150 Le Chesnay, France Abstract This paper focuses

More information

Motion estimation. Digital Visual Effects Yung-Yu Chuang. with slides by Michael Black and P. Anandan

Motion estimation. Digital Visual Effects Yung-Yu Chuang. with slides by Michael Black and P. Anandan Motion estimation Digital Visual Effects Yung-Yu Chuang with slides b Michael Black and P. Anandan Motion estimation Parametric motion image alignment Tracking Optical flow Parametric motion direct method

More information

Convexity and Non-Convexity in Partitioning and Interpolation Problems

Convexity and Non-Convexity in Partitioning and Interpolation Problems Convexity and Non-Convexity in Partitioning and Interpolation Problems Jan Lellmann CIA/DAMTP, University of Cambridge Joint work with: C. Schnörr, F. Lenzen (IPA/HCI, University of Heidelberg), F. Widmann,

More information

STA141C: Big Data & High Performance Statistical Computing

STA141C: Big Data & High Performance Statistical Computing STA141C: Big Data & High Performance Statistical Computing Lecture 8: Optimization Cho-Jui Hsieh UC Davis May 9, 2017 Optimization Numerical Optimization Numerical Optimization: min X f (X ) Can be applied

More information

NON-LINEAR DIFFUSION FILTERING

NON-LINEAR DIFFUSION FILTERING NON-LINEAR DIFFUSION FILTERING Chalmers University of Technology Page 1 Summary Introduction Linear vs Nonlinear Diffusion Non-Linear Diffusion Theory Applications Implementation References Page 2 Introduction

More information

On the interior of the simplex, we have the Hessian of d(x), Hd(x) is diagonal with ith. µd(w) + w T c. minimize. subject to w T 1 = 1,

On the interior of the simplex, we have the Hessian of d(x), Hd(x) is diagonal with ith. µd(w) + w T c. minimize. subject to w T 1 = 1, Math 30 Winter 05 Solution to Homework 3. Recognizing the convexity of g(x) := x log x, from Jensen s inequality we get d(x) n x + + x n n log x + + x n n where the equality is attained only at x = (/n,...,

More information

DESIGN OF MULTI-DIMENSIONAL DERIVATIVE FILTERS. Eero P. Simoncelli

DESIGN OF MULTI-DIMENSIONAL DERIVATIVE FILTERS. Eero P. Simoncelli Published in: First IEEE Int l Conf on Image Processing, Austin Texas, vol I, pages 790--793, November 1994. DESIGN OF MULTI-DIMENSIONAL DERIVATIVE FILTERS Eero P. Simoncelli GRASP Laboratory, Room 335C

More information

Multi-modal Image Registration Using Dirichlet-Encoded Prior Information

Multi-modal Image Registration Using Dirichlet-Encoded Prior Information Multi-modal Image Registration Using Dirichlet-Encoded Prior Information Lilla Zöllei and William Wells MIT, CSAIL; 32 Vassar St (Bld 32), Cambridge, MA 0239, USA {lzollei, sw}@csail.mit.edu Abstract.

More information

Proximal Newton Method. Zico Kolter (notes by Ryan Tibshirani) Convex Optimization

Proximal Newton Method. Zico Kolter (notes by Ryan Tibshirani) Convex Optimization Proximal Newton Method Zico Kolter (notes by Ryan Tibshirani) Convex Optimization 10-725 Consider the problem Last time: quasi-newton methods min x f(x) with f convex, twice differentiable, dom(f) = R

More information

Simultaneous Multi-frame MAP Super-Resolution Video Enhancement using Spatio-temporal Priors

Simultaneous Multi-frame MAP Super-Resolution Video Enhancement using Spatio-temporal Priors Simultaneous Multi-frame MAP Super-Resolution Video Enhancement using Spatio-temporal Priors Sean Borman and Robert L. Stevenson Department of Electrical Engineering, University of Notre Dame Notre Dame,

More information

T H E S I S. Computer Engineering May Smoothing of Matrix-Valued Data. Thomas Brox

T H E S I S. Computer Engineering May Smoothing of Matrix-Valued Data. Thomas Brox D I P L O M A Computer Engineering May 2002 T H E S I S Smoothing of Matrix-Valued Data Thomas Brox Computer Vision, Graphics, and Pattern Recognition Group Department of Mathematics and Computer Science

More information

Image Alignment and Mosaicing Feature Tracking and the Kalman Filter

Image Alignment and Mosaicing Feature Tracking and the Kalman Filter Image Alignment and Mosaicing Feature Tracking and the Kalman Filter Image Alignment Applications Local alignment: Tracking Stereo Global alignment: Camera jitter elimination Image enhancement Panoramic

More information

Wavelet-based Salient Points with Scale Information for Classification

Wavelet-based Salient Points with Scale Information for Classification Wavelet-based Salient Points with Scale Information for Classification Alexandra Teynor and Hans Burkhardt Department of Computer Science, Albert-Ludwigs-Universität Freiburg, Germany {teynor, Hans.Burkhardt}@informatik.uni-freiburg.de

More information

Optical Flow, Motion Segmentation, Feature Tracking

Optical Flow, Motion Segmentation, Feature Tracking BIL 719 - Computer Vision May 21, 2014 Optical Flow, Motion Segmentation, Feature Tracking Aykut Erdem Dept. of Computer Engineering Hacettepe University Motion Optical Flow Motion Segmentation Feature

More information

Convex Hodge Decomposition and Regularization of Image Flows

Convex Hodge Decomposition and Regularization of Image Flows Convex Hodge Decomposition and Regularization of Image Flows Jing Yuan, Christoph Schnörr, Gabriele Steidl April 14, 2008 Abstract The total variation (TV) measure is a key concept in the field of variational

More information

Accelerated Dual Gradient-Based Methods for Total Variation Image Denoising/Deblurring Problems (and other Inverse Problems)

Accelerated Dual Gradient-Based Methods for Total Variation Image Denoising/Deblurring Problems (and other Inverse Problems) Accelerated Dual Gradient-Based Methods for Total Variation Image Denoising/Deblurring Problems (and other Inverse Problems) Donghwan Kim and Jeffrey A. Fessler EECS Department, University of Michigan

More information

A Tensor Variational Formulation of Gradient Energy Total Variation

A Tensor Variational Formulation of Gradient Energy Total Variation A Tensor Variational Formulation of Gradient Energy Total Variation Freddie Åström, George Baravdish and Michael Felsberg Linköping University Post Print N.B.: When citing this work, cite the original

More information

Recent developments on sparse representation

Recent developments on sparse representation Recent developments on sparse representation Zeng Tieyong Department of Mathematics, Hong Kong Baptist University Email: zeng@hkbu.edu.hk Hong Kong Baptist University Dec. 8, 2008 First Previous Next Last

More information

TRACKING SOLUTIONS OF TIME VARYING LINEAR INVERSE PROBLEMS

TRACKING SOLUTIONS OF TIME VARYING LINEAR INVERSE PROBLEMS TRACKING SOLUTIONS OF TIME VARYING LINEAR INVERSE PROBLEMS Martin Kleinsteuber and Simon Hawe Department of Electrical Engineering and Information Technology, Technische Universität München, München, Arcistraße

More information

Lucas-Kanade Optical Flow. Computer Vision Carnegie Mellon University (Kris Kitani)

Lucas-Kanade Optical Flow. Computer Vision Carnegie Mellon University (Kris Kitani) Lucas-Kanade Optical Flow Computer Vision 16-385 Carnegie Mellon University (Kris Kitani) I x u + I y v + I t =0 I x = @I @x I y = @I u = dx v = dy I @y t = @I dt dt @t spatial derivative optical flow

More information

CS4495/6495 Introduction to Computer Vision. 6B-L1 Dense flow: Brightness constraint

CS4495/6495 Introduction to Computer Vision. 6B-L1 Dense flow: Brightness constraint CS4495/6495 Introduction to Computer Vision 6B-L1 Dense flow: Brightness constraint Motion estimation techniques Feature-based methods Direct, dense methods Motion estimation techniques Direct, dense methods

More information

Iterative Image Registration: Lucas & Kanade Revisited. Kentaro Toyama Vision Technology Group Microsoft Research

Iterative Image Registration: Lucas & Kanade Revisited. Kentaro Toyama Vision Technology Group Microsoft Research Iterative Image Registration: Lucas & Kanade Revisited Kentaro Toyama Vision Technology Group Microsoft Research Every writer creates his own precursors. His work modifies our conception of the past, as

More information

Video and Motion Analysis Computer Vision Carnegie Mellon University (Kris Kitani)

Video and Motion Analysis Computer Vision Carnegie Mellon University (Kris Kitani) Video and Motion Analysis 16-385 Computer Vision Carnegie Mellon University (Kris Kitani) Optical flow used for feature tracking on a drone Interpolated optical flow used for super slow-mo optical flow

More information

Methods in Computer Vision: Introduction to Optical Flow

Methods in Computer Vision: Introduction to Optical Flow Methods in Computer Vision: Introduction to Optical Flow Oren Freifeld Computer Science, Ben-Gurion University March 22 and March 26, 2017 Mar 22, 2017 1 / 81 A Preliminary Discussion Example and Flow

More information

Sparsity Regularization

Sparsity Regularization Sparsity Regularization Bangti Jin Course Inverse Problems & Imaging 1 / 41 Outline 1 Motivation: sparsity? 2 Mathematical preliminaries 3 l 1 solvers 2 / 41 problem setup finite-dimensional formulation

More information

Variational Image Restoration

Variational Image Restoration Variational Image Restoration Yuling Jiao yljiaostatistics@znufe.edu.cn School of and Statistics and Mathematics ZNUFE Dec 30, 2014 Outline 1 1 Classical Variational Restoration Models and Algorithms 1.1

More information

Landscapes & Algorithms for Quantum Control

Landscapes & Algorithms for Quantum Control Dept of Applied Maths & Theoretical Physics University of Cambridge, UK April 15, 211 Control Landscapes: What do we really know? Kinematic control landscapes generally universally nice 1 Pure-state transfer

More information

Scale Space Analysis by Stabilized Inverse Diffusion Equations

Scale Space Analysis by Stabilized Inverse Diffusion Equations Scale Space Analysis by Stabilized Inverse Diffusion Equations Ilya Pollak, Alan S. Willsky and Hamid Krim Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts

More information

Rotational Invariants for Wide-baseline Stereo

Rotational Invariants for Wide-baseline Stereo Rotational Invariants for Wide-baseline Stereo Jiří Matas, Petr Bílek, Ondřej Chum Centre for Machine Perception Czech Technical University, Department of Cybernetics Karlovo namesti 13, Prague, Czech

More information

EAD 115. Numerical Solution of Engineering and Scientific Problems. David M. Rocke Department of Applied Science

EAD 115. Numerical Solution of Engineering and Scientific Problems. David M. Rocke Department of Applied Science EAD 115 Numerical Solution of Engineering and Scientific Problems David M. Rocke Department of Applied Science Taylor s Theorem Can often approximate a function by a polynomial The error in the approximation

More information

Photometric Stereo: Three recent contributions. Dipartimento di Matematica, La Sapienza

Photometric Stereo: Three recent contributions. Dipartimento di Matematica, La Sapienza Photometric Stereo: Three recent contributions Dipartimento di Matematica, La Sapienza Jean-Denis DUROU IRIT, Toulouse Jean-Denis DUROU (IRIT, Toulouse) 17 December 2013 1 / 32 Outline 1 Shape-from-X techniques

More information

Orientation Map Based Palmprint Recognition

Orientation Map Based Palmprint Recognition Orientation Map Based Palmprint Recognition (BM) 45 Orientation Map Based Palmprint Recognition B. H. Shekar, N. Harivinod bhshekar@gmail.com, harivinodn@gmail.com India, Mangalore University, Department

More information

SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE

SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE Overview Motivation of Work Overview of Algorithm Scale Space and Difference of Gaussian Keypoint Localization Orientation Assignment Descriptor Building

More information

Nonparametric Bayesian Methods (Gaussian Processes)

Nonparametric Bayesian Methods (Gaussian Processes) [70240413 Statistical Machine Learning, Spring, 2015] Nonparametric Bayesian Methods (Gaussian Processes) Jun Zhu dcszj@mail.tsinghua.edu.cn http://bigml.cs.tsinghua.edu.cn/~jun State Key Lab of Intelligent

More information