| 51. |
- Ardö, Håkan, et al.
(författare)
-
Bayesian Formulation of Image Patch Matching Using Cross-correlation
- 2012
-
Ingår i: Journal of Mathematical Imaging and Vision. - : Springer Science and Business Media LLC. - 0924-9907 .- 1573-7683. ; 43:1, s. 72-87
-
Tidskriftsartikel (refereegranskat)abstract
- A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those that are more uncertain. To enable this two distribution functions for two different cases are used: (i) the correlation between two patches showing the same object but with different lighting conditions and different noise realisations and (ii) the correlation between two unrelated patches.Using these two distributions the patch matching problem is, in this paper, formulated as a binary classification problem. The probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or its spatial variance, has to be measured for every frame.A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. This paper will concentrate on the latter application. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm by transforming the calculations to the DCT-domain and processing a motion-JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150 MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.
|
|
| 52. |
- Ardö, Håkan, et al.
(författare)
-
Bayesian Formulation of Image Patch Matching Using Cross-correlation
- 2009
-
Ingår i: 2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC). - 9781424446209 ; , s. 92-99
-
Konferensbidrag (refereegranskat)abstract
- A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty more weight can be put on the confident matches than those that are more uncertain. In this paper we present a system that can learn the distribution of the correlation coefficient from a video sequence of an empty scene. No manual annotation of the video is needed. Two distributions functions are learned for two different cases: i) the correlation between an estimated background image and the current frame showing that background and ii) the correlation between an estimated background image and an unrelated patch. Using these two distributions the patch matching problem is formulated as a binary classification problem and the probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or it's spatial variance, has to be measured for every frame. A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. In this paper it is shown how the theory can be used to implement a very fast background/foreground segmentation by transforming the calculations to the DCT-domain and processing a motion JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.
|
|
| 53. |
- Ardö, Håkan, et al.
(författare)
-
Foreground Estimation and Hidden Markov Models for Tracking
- 2005
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- We will give a short introduction to foreground/background estimation and Hidden Markov fortracking. More information about the topics can be found in the papers listed at the end.
|
|
| 54. |
|
|
| 55. |
|
|
| 56. |
- Ardö, Håkan, et al.
(författare)
-
Real time viterbi optimization of hidden Markov Models for multi target tracking
- 2007
-
Ingår i: 2007 IEEE Workshop on Motion and Video Computing (WMVC'07). - 0769527930
-
Konferensbidrag (refereegranskat)abstract
- In this paper the problem of tracking multiple objects in image sequences is studied. A Hidden Markov Model describing the movements of multiple objects is presented. Previously similar models have been used, but in real time system the standard dynamic programming Viterbi algorithm is typically not used to find the global optimum state sequence, as it requires that all past and future observations are available. In this paper we present an extension to the Viterbi algorithm that allows it to operate on infinite time sequences and produce the optimum with only a finite delay. This makes it possible to use the Viterbi algorithm in real time applications. Also, to handle the large state spaces of these models another extension is proposed. The global optimum is found by iteratively running an approximative algorithm with higher and higher precision. The algorithm can determine when the global optimum is found by maintaining an upper bound on all state sequences not evaluated. For real time performance some approximations are needed and two such approximations are suggested. The theory has been tested on three real data experiments, all with promising results.
|
|
| 57. |
- Arvidsson, Ida, et al.
(författare)
-
Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer’s disease in patients with mild cognitive symptoms
- 2024
-
Ingår i: Alzheimer's Research and Therapy. - 1758-9193. ; 16:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Predicting future Alzheimer’s disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods: A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. Results: In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R2 = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R2 = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R2 = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R2 = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated. Conclusions: The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
|
|
| 58. |
- Ask, Erik, et al.
(författare)
-
A Unifying Approach to Minimal Problems in Collinear and Planar TDOA Sensor Network Self-Calibration
- 2014
-
Ingår i: European Signal Processing Conference. - 2219-5491.
-
Konferensbidrag (refereegranskat)abstract
- This work presents a study of sensor network calibration from time-difference-of-arrival (TDOA) measurements for cases when the dimensions spanned by the receivers and the transmitters differ. This could for example be if receivers are restricted to a line or plane or if the transmitting objects are moving linearly in space. Such calibration arises in several applications such as calibration of (acoustic or ultrasound) microphone arrays, and radio antenna networks. We propose a non-iterative algorithm based on recent stratified approaches: (i) rank constraints on modified measurement matrix, (ii) factorization techniques that determine transmitters and receivers up to unknown affine transformation and (iii) determining the affine stratification using remaining non-linear constraints. This results in a unified approach to solve almost all minimal problems. Such algorithms are important components for systems for self-localization. Experiments are shown both for simulated and real data with promising results.
|
|
| 59. |
- Ask, Erik, et al.
(författare)
-
Exploiting p-Fold Symmetries for Faster Polynomial Equation Solving
- 2012
-
Ingår i: 21st International Conference on Pattern Recognition (ICPR 2012), Proceedings of. - 9784990644116 ; , s. 3232-3235
-
Konferensbidrag (refereegranskat)abstract
- Numerous geometric problems in computer vision in- volve the solution of systems of polynomial equations. This is true for problems with minimal information, but also for finding stationary points for overdetermined problems. The state-of-the-art is based on the use of numerical linear algebra on the large but sparse co- efficient matrix that represents the expanded original equation set. In this paper we present two simplifica- tions that can be used (i) if the zero vector is one of the solutions or (ii) if the equations display certain p- fold symmetries. We evaluate the simplifications on a few example problems and demonstrate that significant speed increases are possible without loosing accuracy.
|
|
| 60. |
- Ask, Erik, et al.
(författare)
-
Minimal Structure and Motion Problems for TOA and TDOA Measurements with Collinearity Constraints
- 2013
-
Ingår i: 2nd International Conference on Pattern Recognition Applications and Methods, Proceedings of. - 9789898565419 ; , s. 425-429
-
Konferensbidrag (refereegranskat)abstract
- Structure from sound can be phrased as the problem of determining the position of a number of microphones and a number of sound sources given only the recorded sounds. In this paper we study minimal structure from sound problems in both TOA (time of arrival) and TDOA (time difference of arrival) settings with collinear constraints on e.g. the microphone positions. Three such minimal cases are analyzed and solved with efficient and numerically stable techniques. An experimental validation of the solvers are performed on both simulated and real data. In the paper we also show how such solvers can be utilized in a RANSAC framework to perform robust matching of sound features and then used as initial estimates in a robust non-linear leastsquares optimization.
|
|
