| 1. |
- Olsson, Carl, et al.
(författare)
-
In Defense of 3D-Label Stereo
- 2013
-
Ingår i: Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. - 1063-6919 .- 2163-6648. ; , s. 1730-1737
-
Konferensbidrag (refereegranskat)abstract
- It is commonly believed that higher order smoothness should be modeled using higher order interactions. For example, 2nd order derivatives for deformable (active) contours are represented by triple cliques. Similarly, the 2nd order regularization methods in stereo predominantly use MRF models with scalar (1D) disparity labels and triple clique interactions. In this paper we advocate a largely overlooked alternative approach to stereo where 2nd order surface smoothness is represented by pairwise interactions with 3D-labels, e.g. tangent planes. This general paradigm has been criticized due to perceived computational complexity of optimization in higher-dimensional label space. Contrary to popular beliefs, we demonstrate that representing 2nd order surface smoothness with 3D labels leads to simpler optimization problems with (nearly) submodular pairwise interactions. Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo.
|
|
| 2. |
- Olsson, Carl, et al.
(författare)
-
Local Refinement for Stereo Regularization
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 4056-4061
-
Konferensbidrag (refereegranskat)abstract
- Stereo matching is an inherently difficult problem due to ambiguous and noisy texture. The non-convexity and non- differentiability makes local linear (or quadratic) approximations poor, thereby preventing the use of standard local descent methods. Therefore recent methods are predominantly based on discretization and/or random sampling of some class of approximating surfaces (e.g. planes). While these methods are very efficient in generating a rough surface estimate, via either fusion of proposals or label propagation, the end result is usually not as smooth as desired. In this paper we show that, if the objective function is decomposed correctly, local refinement of candidate solutions can be performed using an ADMM approach. This allows searching over more general function classes, thereby resulting in visually more appealing smooth surface estimations.
|
|
| 3. |
- Olsson, Carl, et al.
(författare)
-
Partial Enumeration and Curvature Regularization
- 2013
-
Ingår i: Computer Vision (ICCV), 2013 IEEE International Conference on. - 1550-5499. ; , s. 2936-2943
-
Konferensbidrag (refereegranskat)abstract
- Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is generally NP-hard. A naive approach that works for small problem instances is exhaustive search, that is, enumera- tion of all possible labelings of the underlying graph. We propose a general minimization approach for large graphs based on enumeration of labelings of certain small patches. This partial enumeration technique reduces complex high- order energy formulations to pairwise Constraint Satisfac- tion Problems with unary costs (uCSP), which can be ef- ficiently solved using standard methods like TRW-S. Our approach outperforms a number of existing state-of-the-art algorithms on well known difficult problems (e.g. curvature regularization, stereo, deconvolution); it gives near global minimum and better speed. Our main application of interest is curvature regular- ization. In the context of segmentation, our partial enu- meration technique allows to evaluate curvature directly on small patches using a novel integral geometry approach.
|
|
| 4. |
- Simayijiang, Zhayida, et al.
(författare)
-
Exploratory study of EEG burst characteristics in preterm infants
- 2013
-
Ingår i: Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE. - 1557-170X. ; , s. 4295-4298
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we study machine learning techniques and features of electroencephalography activity bursts for predicting outcome in extremely preterm infants. It was previously shown that the distribution of interburst interval durations predicts clinical outcome, but in previous work the information within the bursts has been neglected. In this paper, we perform exploratory analysis of feature extraction of burst characteristics and use machine learning techniques to show that such features could be used for outcome prediction. The results are promising, but further verification of the results in larger datasets is needed to obtain conclusive results.
|
|
| 5. |
- Strandmark, Petter, et al.
(författare)
-
HEp-2 Staining Pattern Classification
- 2012
-
Ingår i: Pattern Recognition (ICPR), 2012 21st International Conference on. - 9781467322164
-
Konferensbidrag (refereegranskat)abstract
- Classifying images of HEp-2 cells from indirect immunofluorescence has important clinical applications. We have developed an automatic method based on random forests that classifies an HEp-2 cell image into one of six classes. The method is applied to the data set of the ICPR 2012 contest. The previously obtained best accuracy is 79.3% for this data set, whereas we obtain an accuracy of 97.4%. The key to our result is due to carefully designed feature descriptors for multiple level sets of the image intensity. These features characterize both the appearance and the shape of the cell image in a robust manner.
|
|
| 6. |
- Strandmark, Petter, et al.
(författare)
-
Shortest Paths with Curvature and Torsion
- 2013
-
Ingår i: Computer Vision (ICCV), 2013 IEEE International Conference on. - 1550-5499. - 9781479928392 ; , s. 2024-2031
-
Konferensbidrag (refereegranskat)abstract
- This paper describes a method of finding thin, elongated structures in images and volumes. We use shortest paths to minimize very general functionals of higher-order curve properties, such as curvature and torsion. Our globally optimal method uses line graphs and its runtime is polynomial in the size of the discretization, often in the order of seconds on a single computer. To our knowledge, we are the first to perform experiments in three dimensions with curvature and torsion regularization. The largest graphs we process have almost one hundred billion arcs. Experiments on medical images and in multi-view reconstruction show the significance and practical usefulness of regularization based on curvature while torsion is still only tractable for small-scale problems
|
|
| 7. |
- Ulén, Johannes, et al.
(författare)
-
An Efficient Optimization Framework for Multi-Region Segmentation based on Lagrangian Duality
- 2013
-
Ingår i: IEEE Transactions on Medical Imaging. - 1558-254X. ; 32:2, s. 178-188
-
Tidskriftsartikel (refereegranskat)abstract
- We introduce a multi-region model for simultaneous segmentation of medical images. In contrast to many other models, geometric constraints such as inclusion and exclusion between the regions are enforced, which makes it possible to correctly segment different regions even if the intensity distributions are identical. We efficiently optimize the model using a combination of graph cuts and Lagrangian duality which is faster and more memory efficient than current state of the art. As the method is based on global optimization techniques, the resulting segmentations are independent of initialization. We apply our framework to the segmentation of the left and right ventricles, myocardium and the left ventricular papillary muscles in MRI and to lung segmentation in full-body X-ray CT. We evaluate our approach on a publicly available benchmark with competitive results.
|
|
| 8. |
- Ulén, Johannes
(författare)
-
Higher-Order Regularization in Computer Vision
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- At the core of many computer vision models lies the minimization of an objective function consisting of a sum of functions with few arguments. The order of the objective function is defined as the highest number of arguments of any summand. To reduce ambiguity and noise in the solution, regularization terms are included into the objective function, enforcing different properties of the solution. The most commonly used regularization is penalization of boundary length, which requires a second-order objective function. Most of this thesis is devoted to introducing higher-order regularization terms and presenting efficient minimization schemes. One of the topics of the thesis covers a reformulation of a large class of discrete functions into an equivalent form. The reformulation is shown, both in theory and practical experiments, to be advantageous for higher-order regularization models based on curvature and second-order derivatives. Another topic is the parametric max-flow problem. An analysis is given, showing its inherent limitations for large-scale problems which are common in computer vision. The thesis also introduces a segmentation approach for finding thin and elongated structures in 3D volumes. Using a line-graph formulation, it is shown how to efficiently regularize with respect to higher-order differential geometric properties such as curvature and torsion. Furthermore, an efficient optimization approach for a multi-region model is presented which, in addition to standard regularization, is able to enforce geometric constraints such as inclusion or exclusion of different regions. The final part of the thesis deals with dense stereo estimation. A new regularization model is introduced, penalizing the second-order derivatives of a depth or disparity map. Compared to previous second-order approaches to dense stereo estimation, the new regularization model is shown to be more easily optimized.
|
|
| 9. |
- Ulén, Johannes, et al.
(författare)
-
Optimization for Multi-Region Segmentation of Cardiac MRI
- 2011
-
Ingår i: Lecture Notes in Computer Science (Statistical Atlases and Computational Models of the Heart. Imaging and Modelling Challenges Second International Workshop, STACOM 2011, Held in Conjunction with MICCAI 2011, Toronto, ON, Canada, September 22, 2011, Revised Selected Papers). - Berlin, Heidelberg : Springer Berlin Heidelberg. - 1611-3349 .- 0302-9743. - 9783642283260 - 9783642283253 ; 7085, s. 129-138
-
Konferensbidrag (refereegranskat)abstract
- We introduce a new multi-region model for simultaneous segmentation of the left and right ventricles, myocardium and the left ventricular papillary muscles in MRI. The model enforces geometric constraints such as inclusion and exclusion between the regions, which makes it possible to correctly segment different regions even though the intensity distributions are identical. We efficiently optimize the model using Lagrangian duality which is faster and more memory efficient than current state of the art. As the optimization is based on global techniques, the resulting segmentations are independent of initialization. We evaluate our approach on two benchmarks with competitive results.
|
|
| 10. |
- Ulén, Johannes, et al.
(författare)
-
Simultaneous Fusion Moves for 3D-label Stereo
- 2013
-
Ingår i: Lecture Notes in Computer Science Vol. 8081 (Energy Minimization Methods in Computer Vision and Pattern Recognition). - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743 .- 1611-3349. - 9783642403941 - 9783642403958 ; 8081, s. 80-93
-
Konferensbidrag (refereegranskat)abstract
- Second derivative regularization methods for dense stereo matching is a topic of intense research. Some of the most successful recent methods employ so called binary fusion moves where the combination of two proposal solutions is computed. In many cases the fusion move can be solved optimally, but the approach is limited to fusing pairs of proposals in each move. For multiple proposals iterative binary fusion may potentially lead to local minima. In this paper we demonstrate how to simultaneously fuse more than two proposals at the same time for a 2nd order stereo regularizer. The optimization is made possible by effectively computing a generalized distance transform. This allows for computation of messages in linear time in the number of proposals. In addition the approach provides a lower bound on the globally optimal solution of the multi-fusion problem. We verify experimentally that the lower bound is very close to the computed solution, thus providing a near optimal solution.
|
|
