| 1. |
- Ardö, Håkan, et al.
(författare)
-
Bayesian Formulation of Gradient Orientation Matching
- 2015
-
Ingår i: Lecture Notes in Computer Science. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. ; 9163, s. 91-103
-
Konferensbidrag (refereegranskat)abstract
- Gradient orientations are a common feature used in many computer vision algorithms. It is a good feature when the gradient magnitudes are high, but can be very noisy when the magnitudes are low. This means that some gradient orientations are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those with higher uncertainty. To enable this, we derive the probability distribution of gradient orientations based on a signal to noise ratio defined as the gradient magnitude divided by the standard deviation of the Gaussian noise. The noise level is reasonably invariant over time, while the magnitude, has to be measured for every frame. Using this probability distribution we formulate the matching of gradient orientations as a Bayesian classification problem. A common application where this is useful is feature point matching. Another application is background/foreground segmentation. This paper will use the latter application as an example, but is focused on the general formulation. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm that is capable of handling complex lighting variations.
|
|
| 2. |
- Ask, Erik, et al.
(författare)
-
Tractable and Reliable Registration of 2D Point Sets
- 2014
-
Ingår i: Lecture Notes in Computer Science (Computer Vision - ECCV 2014, 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I). - Cham : Springer International Publishing. - 0302-9743 .- 1611-3349. - 9783319105895 - 9783319105901 ; 8689, s. 393-406
-
Konferensbidrag (refereegranskat)abstract
- This paper introduces two new methods of registering 2D point sets over rigid transformations when the registration error is based on a robust loss function. In contrast to previous work, our methods are guaranteed to compute the optimal transformation, and at the same time, the worst-case running times are bounded by a low-degree polynomial in the number of correspondences. In practical terms, this means that there is no need to resort to ad-hoc procedures such as random sampling or local descent methods that cannot guarantee the quality of their solutions. We have tested the methods in several different settings, in particular, a thorough evaluation on two benchmarks of microscopic images used for histologic analysis of prostate cancer has been performed. Compared to the state-of-the-art, our results show that the methods are both tractable and reliable despite the presence of a significant amount of outliers.
|
|
| 3. |
- Haner, Sebastian, et al.
(författare)
-
Joint Under and Over Water Calibration of a Swimmer Tracking System
- 2015
-
Ingår i: Proceedings of the 4th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2015). - : SCITEPRESS - Science and and Technology Publications. ; , s. 142-149
-
Konferensbidrag (refereegranskat)abstract
- This paper describes a multi-camera system designed for capture and tracking of swimmers both above and below the surface of a pool. To be able to measure the swimmer's position, the cameras need to be accurately calibrated. Images captured below the surface provide a number of challenges, mainly due to refraction and reflection effects at optical media boundaries. We present practical methods for intrinsic and extrinsic calibration of two sets of cameras, optically separated by the water surface, and for stitching panoramas allowing synthetic panning shots of the swimmer.
|
|
| 4. |
- Lindgren Belal, Sarah, et al.
(författare)
-
Association of PET index quantifying skeletal uptake in NaF PET/CT images with overall survival in prostate cancer patients
- 2017
-
Ingår i: Journal of Clinical Oncology. - 0732-183X. ; 35:6 Suppl, s. 178-178
-
Konferensbidrag (refereegranskat)abstract
- Background: Bone Scan Index (BSI) derived from 2D whole-body bone scans is considered an imaging biomarker of bone metastases burden carrying prognostic information. Sodium fluoride (NaF) PET/CT is more sensitive than bone scan in detecting bone changes due to metastases. We aimed to develop a semi-quantitative PET index similar to the BSI for NaF PET/CT imaging and to study its relationship to BSI and overall survival in patients with prostate cancer.Methods: NaF PET/CT and bone scans were analyzed in 48 patients (aged 53-92 years) with prostate cancer. Thoracic and lumbar spines, sacrum, pelvis, ribs, scapulae, clavicles, and sternum were automatically segmented from the CT images, representing approximately 1/3 of the total skeletal volume. Hotspots in the PET images, within the segmented parts in the CT images, were visually classified and hotspots interpreted as metastases were included in the analysis. The PET index was defined as the quotient obtained as the hotspot volume from the PET images divided by the segmented bone tissue volume from the CT images. BSI was automatically calculated using EXINIboneBSI.Results: The correlation between the PET index and BSI was r2= 0.54. The median BSI was 0.39 (IQR 0.08-2.05). The patients with a BSI ≥ 0.39 had a significantly shorter median survival time than patients with a BSI < 0.39 (2.3 years vs. not reached after 5 years). BSI was significantly associated with overall survival (HR 1.13, 95% CI 1.13 to 1.41; p < 0.001), and the C-index was 0.68. The median PET index was 0.53 (IQR 0.02-2.62). The patients with a PET index ≥ 0.53 had a significantly shorter median survival time than patients with a PET index < 0.53 (2.5 years vs. not reached after 5 years). The PET index was significantly associated with overall survival (HR 1.18, 95% CI 1.01 to 1.30; p < 0.001) and C-index was 0.68.Conclusions: PET index based on NaF PET/CT images was correlated to BSI and significantly associated with overall survival in patients with prostate cancer. Further studies are needed to evaluate the clinical value of this novel 3D PET index as a possible future imaging biomarker.
|
|
| 5. |
- Svärm, Linus, et al.
(författare)
-
Accurate Localization and Pose Estimation for Large 3D Models
- 2014
-
Ingår i: Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. - 1063-6919. - 9781479951178 ; , s. 532-539
-
Konferensbidrag (refereegranskat)abstract
- We consider the problem of localizing a novel image in a large 3D model. In principle, this is just an instance of camera pose estimation, but the scale introduces some challenging problems. For one, it makes the correspondence problem very difficult and it is likely that there will be a significant rate of outliers to handle. In this paper we use recent theoretical as well as technical advances to tackle these problems. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite more than 99% of outlier correspondences.
|
|
| 6. |
- Svärm, Linus, et al.
(författare)
-
City-Scale Localization for Cameras with Known Vertical Direction
- 2017
-
Ingår i: IEEE Transactions on Pattern Analysis and Machine Intelligence. - 0162-8828 .- 1939-3539. ; 39:7, s. 1455-1461
-
Tidskriftsartikel (refereegranskat)abstract
- We consider the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known. In principle, this is just an instance of camera pose estimation, but the scale of the problem introduces some interesting challenges. Most importantly, it makes the correspondence problem very difficult so there will often be a significant number of outliers to handle. To tackle this problem, we use recent theoretical as well as technical advances. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite cases with more than 99% outlier correspondences in city-scale models with several millions of 3D points.
|
|
| 7. |
- Svärm, Linus
(författare)
-
Efficient Optimization Techniques for Localization and Registration of Images
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis focuses on two problems in the field of computer vision and image analysis. The first part of the thesis deals with image localization. The goal is simply to answer the question: Where was this picture taken? To answer this two things are needed: A model of the world, or at least the relevant parts of the world, and a method for relating a new image to the model. The thesis presents new methods for both steps, based on modern optimization methods. By taking advantage of additional sensors, such as GPS or gravity sensors, higher precision and reliability is achieved compared to previous methods. The second part of the thesis is concerned with the problem of image registration, with focus on medical applications. The goal of image registration is to find the correct transformation between two images depicting the same, or similar, objects. The new methods presented in this thesis aim at increasing robustness in the sense of easy accommodation to new applications without manual adjustment. Several of the methods also aim to increase reliability, i.e. to be able to find good solutions, even if the data contains high levels of noise and outlier structures.
|
|
| 8. |
- Svärm, Linus, et al.
(författare)
-
Improving Robustness for Inter-Subject Medical Image Registration Using a Feature-Based Approach
- 2015
-
Ingår i: Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on. ; , s. 824-828
-
Konferensbidrag (refereegranskat)abstract
- We propose new feature-based methods for rigid and affine image registration. These are compared to state-of-the-art intensity-based techniques as well as existing feature-based methods. On challenging datasets of brain MR and whole-body CT images, a significant improvement in terms of speed, robustness to outlier structures and dependence on initialization is shown.
|
|
| 9. |
- Svärm, Linus, et al.
(författare)
-
Point Track Creation in Unordered Image Collections Using Gomory-Hu Trees
- 2012
-
Ingår i: Pattern Recognition (ICPR) 2012 21st International Conference on. - 9781467322164 ; , s. 2116-2119
-
Konferensbidrag (refereegranskat)abstract
- Geometric reconstruction from image collections is a classical computer vision problem. The problem essentially consists of two steps; First, the identification of matches and assembling of point tracks, and second, multiple view geometry computations. In this paper we address the problem of constructing point tracks using graph theoretical algorithms. From standard descriptor matches between all pairs of images we construct a graph representing all image points and all possible matches. Using Gomory-Hu trees we make cuts in the graph to construct the individual point tracks. We present both theoretical and experimental results (on real datasets) that clearly demonstrates the benefits of using our approach.
|
|
| 10. |
- Svärm, Linus, et al.
(författare)
-
Shift-map Image Registration
- 2010
-
Konferensbidrag (refereegranskat)abstract
- Shift-map image processing is a new framework based on energy minimization over a large space of labels. The optimization utilizes -expansion moves and iterative refinement over a Gaussian pyramid. In this paper we extend the range of applications to image registration. To do this, new data and smoothness terms have to be constructed. We note a great improvement when we measure pixel similarities with the dense DAISY descriptor. The main contributions of this paper are: • The extension of the shift-map framework to include image registration. We register images for which SIFT only provides 3 correct matches. • A publicly available implementation of shift-map image processing (e.g. inpainting, registration). We conclude by comparing shift-map registration to a recent method for optical flow with favorable results.
|
|
