Radim Šára - Academia.edu (original) (raw)
Papers by Radim Šára
We address the problem of automatically reconstructing m-manifolds of unknown topology from unorg... more We address the problem of automatically reconstructing m-manifolds of unknown topology from unorganized points in metric p-spaces obtained from a noisy measurement process. The point set is first approximated by a collection of oriented primitive fuzzy sets over a range of resolutions. Hierarchical multiresolution representation is then computed based on the relation of relative containment defined on the collection. Finally, manifold structure is recovered by establishing connectivity between these primitives based on proximity, compatibility of position and orientation, and local topological constraints. The method has been successfully applied to the problem of surface reconstruction from polynocular-stereo data with many outliers.
We pose robust matching with parametric and non-parametric constraints as the problem of finding ... more We pose robust matching with parametric and non-parametric constraints as the problem of finding a stable independent set (SIS) in an oriented graph whose vertices are all possible correspondences, whose edges capture the structure of the constraints and whose edge orientation represents pairwise comparison 'is better' based on correspondence quality, including the uncertainty of this comparison. We show SIS possess properties of both robustness and weak optimality. The main contribution of this paper is algorithmic speedup that results from exploiting the dependence between the standard uniqueness constraint and the parametric constraint. The general theory is demonstrated on the example of image stitching using homography model. The algorithm needs at most k N 2 calls of a procedure testing if two ellipse correspondences are consistent with a general homography. The previous known SIS algorithm needed O(N 4 ) tests. Experiments show the method gives good results and is fast in practice with k ≈ 0.3.
Proceedings of SPIE, Sep 16, 1999
ABSTRACT Among properties computer vision attempts to extract from images are: local shape, intri... more ABSTRACT Among properties computer vision attempts to extract from images are: local shape, intrinsic reflection parameters, and roughness because they are all crucial to the success of image interpretation in general and to realistic surface modeling in particular. We seek light reflection phenomena and reflectance models that could better capture the relation of reflected light parameters to the local properties of the observed surface. In addition to the relation intensity--shape studied in computer vision for a long time, we study the relation of other light characteristics to local shape. We started by focusing on light polarization state. We found that the generalization of the Lambert's reflectance model based on Fresnel coefficients, as proposed by Wolff, correctly predicts the polarization state of light reflected on smooth dielectrics. Both the light incidence and the viewer plane orientations may be measured to estimate the surface normal if light position relative to the observer is...
It is known that detecting straight streaks from fast moving celestial objects in optical images ... more It is known that detecting straight streaks from fast moving celestial objects in optical images is an easy problem as long as the streaks are sufficiently long and/or their signal-to-background (SBR) is sufficiently high. At low SBR the situation is different. Since the SBR can be arbitrarily small in practice, a good detection procedure has to provide a detection certificate which is a yes/no answer to the question "does the image contain a streak?" In this paper we pose detection with certificate as a Multi-Level Bayesian Inference (MLBI) problem which is based on Bayesian model selection. We describe the algorithm and show an experimental proof of good behavior on synthetic streaks over real image data. A systematic performance evaluation shows that MLBI confirms and partially exceeds results of state-of-the art methods. In particular, in the class of difficult problem instances with SBR of 0 dB to -5 dB and streak length 10 to 500 pixels, we achieved AUC ≈ 0.97, which means that the Bayesian detection certificate is wrong in just 3% of cases.
Pattern analysis and applications/Pattern analysis & applications, Apr 13, 2024
Cameras are the prevalent sensors used for perception in autonomous robotic systems, but their in... more Cameras are the prevalent sensors used for perception in autonomous robotic systems, but their initial calibration may degrade over time due to dynamic factors. This may lead to a failure of downstream tasks, such as simultaneous localization and mapping (SLAM) or object recognition. Hence, a computationally lightweight process that detects the decalibration is of interest. We describe a modification of StOCaMo, an online calibration monitoring procedure for a stereoscopic system. The method uses robust kernel correlation based on epipolar constraints; it validates extrinsic calibration parameters on a single frame with no temporal tracking. In this paper, we present a modified StOCaMo with an improved recall rate on small decalibrations through a confirmation technique based on resampled variance. With fixed parameters learned on a realistic synthetic dataset from CARLA, StOCaMo and its proposed modification were tested on multiple sequences from two realworld datasets: KITTI and EuRoC MAV. The modification improved the recall of StOCaMo by 25 % (to 91 % and 82 %, respectively), and the accuracy by 12 % (to 94.7 % and 87.5 %, respectively), while labeling at most one-third of the input data as uninformative. The upgraded method achieved the rank correlation between StOCaMo V-index and downstream SLAM error of 0.78 (Spearman).
Lecture Notes in Computer Science, 2023
: This work deals with verish-scale position in 3D space structure matrix{orientation, `radii&... more : This work deals with verish-scale position in 3D space structure matrix{orientation, `radii', and local surface uncertainty Principal plane Normal vector Center Two f-s with dierent surface uncertainty Elimination Good f-s Bad f-s Terrible f-s Acknowledgements: This research has been supported by Czech Ministry of Education in the project Center for Machine Perception, grant No. VS96049 and in part by the Grant Agency of the Czech Republic under grants 102/97/0855 and 102/97/0480. sh-scales position and orientation estimates are biased () the images will not be images of the same physical object and they will not be mutually congruent (, ) as can be seen on planar scene with synthetic texture. Several congruence measures were suggested and tested, e.g. { normalized least squares, { correlation, { rank correlation, { relative rank agreement. The next diÆculties should be overcome. First, the images Dependence on F-S size 0.2 0.4 0.6 0.8 1.2 1.4 1.6 1.8 0.6 0.65 0.7 0.75 0...
Lymphocytic thyroiditis (LT), one of the most frequent thyroid disorders, is a chronic autoimmune... more Lymphocytic thyroiditis (LT), one of the most frequent thyroid disorders, is a chronic autoimmune inflammation of the thyroid gland (WARTO�SKY and IN-GBAR 1991). It usually results in hypothyroidism, which causes serious health problems to the patient. The structure of thyroid tissue is impaired by immune process. Such destruction may be either focal or, most frequently, diffuse. The tissue changes can be mostly detected by a routine method used in the diagnos-
An efficient algorithm for computing correlation tables of binocularly and trinocularly rectified... more An efficient algorithm for computing correlation tables of binocularly and trinocularly rectified stereo images is described. It is shown the proposed algorithms have a low complexity linearly proportional to a size of the images, independent on the correlation window size.
2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), 2017
Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided F... more Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided Filter based method proposed by Hosni, the cost map is smoothed by Guided Filter using original image as a guiding image. However, the Guided Filter sometimes fails when there are regions whose textures are same but disparities are different. Thus, parameter tuning for filter size of Guided Filter is difficult to obtain the best accuracy. In this paper we propose an algorithm for automatic filter size selection for each pixel of Guided Filter based stereo matching based on the response of the Different of Gaussian (DoG). In our algorithm, we generate the Filter-Size map whose pixel value for each pixel is appropriate filter size. The value of the Filter-Size map is the largest size of the filtering area around the pixel in interest calculated such that more than two edges are not included in filtering area. In our experiments, we evaluated accuracy of Guided Filter based method with our algorithm for selecting filter size compared with the original Guided Filter based method without our algorithm. By using the Middle-bury datasets, the experimental results shows our algorithm's superiority in accuracy.
This work deals with verification of local planar 3D geometric model recovered from noisy data. V... more This work deals with verification of local planar 3D geometric model recovered from noisy data. Verification is understood as making decision about consistency of the model with a set of images. To evaluate the consistency, a statistical measure is chosen and a novel procedure for testing statistical dependence among a set of random variables is proposed. 1 Introduction In various computer vision tasks it is possible to encounter the problem of verification of a 3D model. The purpose of verification is to assess the consistency between the model and a set of images that are supposed to be views of the scene that is modeled. For example, Baillard et al. [2] describe the reconstruction of 3D urban site models from aerial images. The local candidate models for each building roof are recovered from edge-based stereo. The roof regions are then verified in the input images based on the mutual consistency of image values. A similar problem has been reported in [4], where local planar surfa...
One of the basic diagnostic and monitoring tools for the diseases of the thyroid gland is sonogra... more One of the basic diagnostic and monitoring tools for the diseases of the thyroid gland is sonography. Nonetheless, conventional sonography is still qualitative. To improve the diagnosis reliability, quantitative image analysis is highly desirable. In this paper, we report preliminary results on computer distinguishing between an ultrasound image of chronic inflammation – Hashimoto’s lymphocytic thyreoiditis and healthy tissue. The combination of texture entropy, correlation and uniformity of energy and combination of cluster tendency, texture homogeneity and uniformity of energy proved to be most efficient parameters for discriminative power and recognition stability. There is possibility to use this quantitative tissue characterisation in clinical diagnostic process. Other conditions will be studied in the future.
We address the problem of automatically reconstructing m-manifolds of unknown topology from unorg... more We address the problem of automatically reconstructing m-manifolds of unknown topology from unorganized points in metric p-spaces obtained from a noisy measurement process. The point set is first approximated by a collection of oriented primitive fuzzy sets over a range of resolutions. Hierarchical multiresolution representation is then computed based on the relation of relative containment defined on the collection. Finally, manifold structure is recovered by establishing connectivity between these primitives based on proximity, compatibility of position and orientation, and local topological constraints. The method has been successfully applied to the problem of surface reconstruction from polynocular-stereo data with many outliers.
We pose robust matching with parametric and non-parametric constraints as the problem of finding ... more We pose robust matching with parametric and non-parametric constraints as the problem of finding a stable independent set (SIS) in an oriented graph whose vertices are all possible correspondences, whose edges capture the structure of the constraints and whose edge orientation represents pairwise comparison 'is better' based on correspondence quality, including the uncertainty of this comparison. We show SIS possess properties of both robustness and weak optimality. The main contribution of this paper is algorithmic speedup that results from exploiting the dependence between the standard uniqueness constraint and the parametric constraint. The general theory is demonstrated on the example of image stitching using homography model. The algorithm needs at most k N 2 calls of a procedure testing if two ellipse correspondences are consistent with a general homography. The previous known SIS algorithm needed O(N 4 ) tests. Experiments show the method gives good results and is fast in practice with k ≈ 0.3.
Proceedings of SPIE, Sep 16, 1999
ABSTRACT Among properties computer vision attempts to extract from images are: local shape, intri... more ABSTRACT Among properties computer vision attempts to extract from images are: local shape, intrinsic reflection parameters, and roughness because they are all crucial to the success of image interpretation in general and to realistic surface modeling in particular. We seek light reflection phenomena and reflectance models that could better capture the relation of reflected light parameters to the local properties of the observed surface. In addition to the relation intensity--shape studied in computer vision for a long time, we study the relation of other light characteristics to local shape. We started by focusing on light polarization state. We found that the generalization of the Lambert's reflectance model based on Fresnel coefficients, as proposed by Wolff, correctly predicts the polarization state of light reflected on smooth dielectrics. Both the light incidence and the viewer plane orientations may be measured to estimate the surface normal if light position relative to the observer is...
It is known that detecting straight streaks from fast moving celestial objects in optical images ... more It is known that detecting straight streaks from fast moving celestial objects in optical images is an easy problem as long as the streaks are sufficiently long and/or their signal-to-background (SBR) is sufficiently high. At low SBR the situation is different. Since the SBR can be arbitrarily small in practice, a good detection procedure has to provide a detection certificate which is a yes/no answer to the question "does the image contain a streak?" In this paper we pose detection with certificate as a Multi-Level Bayesian Inference (MLBI) problem which is based on Bayesian model selection. We describe the algorithm and show an experimental proof of good behavior on synthetic streaks over real image data. A systematic performance evaluation shows that MLBI confirms and partially exceeds results of state-of-the art methods. In particular, in the class of difficult problem instances with SBR of 0 dB to -5 dB and streak length 10 to 500 pixels, we achieved AUC ≈ 0.97, which means that the Bayesian detection certificate is wrong in just 3% of cases.
Pattern analysis and applications/Pattern analysis & applications, Apr 13, 2024
Cameras are the prevalent sensors used for perception in autonomous robotic systems, but their in... more Cameras are the prevalent sensors used for perception in autonomous robotic systems, but their initial calibration may degrade over time due to dynamic factors. This may lead to a failure of downstream tasks, such as simultaneous localization and mapping (SLAM) or object recognition. Hence, a computationally lightweight process that detects the decalibration is of interest. We describe a modification of StOCaMo, an online calibration monitoring procedure for a stereoscopic system. The method uses robust kernel correlation based on epipolar constraints; it validates extrinsic calibration parameters on a single frame with no temporal tracking. In this paper, we present a modified StOCaMo with an improved recall rate on small decalibrations through a confirmation technique based on resampled variance. With fixed parameters learned on a realistic synthetic dataset from CARLA, StOCaMo and its proposed modification were tested on multiple sequences from two realworld datasets: KITTI and EuRoC MAV. The modification improved the recall of StOCaMo by 25 % (to 91 % and 82 %, respectively), and the accuracy by 12 % (to 94.7 % and 87.5 %, respectively), while labeling at most one-third of the input data as uninformative. The upgraded method achieved the rank correlation between StOCaMo V-index and downstream SLAM error of 0.78 (Spearman).
Lecture Notes in Computer Science, 2023
: This work deals with verish-scale position in 3D space structure matrix{orientation, `radii&... more : This work deals with verish-scale position in 3D space structure matrix{orientation, `radii', and local surface uncertainty Principal plane Normal vector Center Two f-s with dierent surface uncertainty Elimination Good f-s Bad f-s Terrible f-s Acknowledgements: This research has been supported by Czech Ministry of Education in the project Center for Machine Perception, grant No. VS96049 and in part by the Grant Agency of the Czech Republic under grants 102/97/0855 and 102/97/0480. sh-scales position and orientation estimates are biased () the images will not be images of the same physical object and they will not be mutually congruent (, ) as can be seen on planar scene with synthetic texture. Several congruence measures were suggested and tested, e.g. { normalized least squares, { correlation, { rank correlation, { relative rank agreement. The next diÆculties should be overcome. First, the images Dependence on F-S size 0.2 0.4 0.6 0.8 1.2 1.4 1.6 1.8 0.6 0.65 0.7 0.75 0...
Lymphocytic thyroiditis (LT), one of the most frequent thyroid disorders, is a chronic autoimmune... more Lymphocytic thyroiditis (LT), one of the most frequent thyroid disorders, is a chronic autoimmune inflammation of the thyroid gland (WARTO�SKY and IN-GBAR 1991). It usually results in hypothyroidism, which causes serious health problems to the patient. The structure of thyroid tissue is impaired by immune process. Such destruction may be either focal or, most frequently, diffuse. The tissue changes can be mostly detected by a routine method used in the diagnos-
An efficient algorithm for computing correlation tables of binocularly and trinocularly rectified... more An efficient algorithm for computing correlation tables of binocularly and trinocularly rectified stereo images is described. It is shown the proposed algorithms have a low complexity linearly proportional to a size of the images, independent on the correlation window size.
2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), 2017
Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided F... more Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided Filter based method proposed by Hosni, the cost map is smoothed by Guided Filter using original image as a guiding image. However, the Guided Filter sometimes fails when there are regions whose textures are same but disparities are different. Thus, parameter tuning for filter size of Guided Filter is difficult to obtain the best accuracy. In this paper we propose an algorithm for automatic filter size selection for each pixel of Guided Filter based stereo matching based on the response of the Different of Gaussian (DoG). In our algorithm, we generate the Filter-Size map whose pixel value for each pixel is appropriate filter size. The value of the Filter-Size map is the largest size of the filtering area around the pixel in interest calculated such that more than two edges are not included in filtering area. In our experiments, we evaluated accuracy of Guided Filter based method with our algorithm for selecting filter size compared with the original Guided Filter based method without our algorithm. By using the Middle-bury datasets, the experimental results shows our algorithm's superiority in accuracy.
This work deals with verification of local planar 3D geometric model recovered from noisy data. V... more This work deals with verification of local planar 3D geometric model recovered from noisy data. Verification is understood as making decision about consistency of the model with a set of images. To evaluate the consistency, a statistical measure is chosen and a novel procedure for testing statistical dependence among a set of random variables is proposed. 1 Introduction In various computer vision tasks it is possible to encounter the problem of verification of a 3D model. The purpose of verification is to assess the consistency between the model and a set of images that are supposed to be views of the scene that is modeled. For example, Baillard et al. [2] describe the reconstruction of 3D urban site models from aerial images. The local candidate models for each building roof are recovered from edge-based stereo. The roof regions are then verified in the input images based on the mutual consistency of image values. A similar problem has been reported in [4], where local planar surfa...
One of the basic diagnostic and monitoring tools for the diseases of the thyroid gland is sonogra... more One of the basic diagnostic and monitoring tools for the diseases of the thyroid gland is sonography. Nonetheless, conventional sonography is still qualitative. To improve the diagnosis reliability, quantitative image analysis is highly desirable. In this paper, we report preliminary results on computer distinguishing between an ultrasound image of chronic inflammation – Hashimoto’s lymphocytic thyreoiditis and healthy tissue. The combination of texture entropy, correlation and uniformity of energy and combination of cluster tendency, texture homogeneity and uniformity of energy proved to be most efficient parameters for discriminative power and recognition stability. There is possibility to use this quantitative tissue characterisation in clinical diagnostic process. Other conditions will be studied in the future.