M. Proesmans - Academia.edu (original) (raw)
Papers by M. Proesmans
ICANN ’93, 1993
We investigate the potential of coupled non-linear diffusion processes to provide an efficient an... more We investigate the potential of coupled non-linear diffusion processes to provide an efficient and implementable model for the processing that takes place in the first stages along the visual pathway, and study their role in edge preserving smoothing and noise suppression. The basic idea is that several maps undergo coupled development towards an equilibrium state. These maps could e.g. contain intensity, local edge strength, range, or another quantity. All these maps, including the edge map, contain continuous rather than all-or-nothing information, following a strategy of least commitment. Each of the approaches has been developed and tested on a parallel transputer network.
2015 Digital Heritage, 2015
In this paper, we describe a novel approach for acquiring and managing digital models of archaeol... more In this paper, we describe a novel approach for acquiring and managing digital models of archaeological sites. More in detail, we present an approach to digitization based on a robotic platform and a cloud-based information system. Our robot is the result of over two years of efforts by a group of cultural heritage experts, computer scientists and roboticists. Exploiting the large and heterogeneous amount data provided by the robotic platform requires this data to be managed, organized and analyzed. To this extent we developed ARIS (ARchaeological Information System), a software that exploits modern information retrieval and machine learning systems.
Lecture Notes in Computer Science, 1999
Systems of coupled, non-linear diffusion equations are pro- posed as a computational tool for gro... more Systems of coupled, non-linear diffusion equations are pro- posed as a computational tool for grouping. Grouping tasks are divided into two classes - local and bilocal - and for each a prototypical set of equations is presented. It is shown how different cues can be used for grouping given these two blueprints plus cue-specific specialisations. Results are shown for intensity, texture orientation, stereo disparity, opti- cal flow, mirror symmetry, and regular textures. The proposed equations are particularly well suited for parallel implementations. They also show some interesting analogies with basic architectural characteristics of the cortex.
International Conference on Multisensor Fusion and Integration for Intelligent Systems, 1996
A sensor is proposed with interesting characteristics for applications such as autonomous navigat... more A sensor is proposed with interesting characteristics for applications such as autonomous navigation and virtual reality. The system extracts both 3D shape and surface texture. It is based on the projection of a regular pattern, observed by a single camera. It is cheap, requiring only a slide projector and a camera. Shape and intensity are extracted from one and the
International Conference on Pattern Recognition, 1996
Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1996
Over recent years, symmetry research has shifted from the detection of affinely to perspectively ... more Over recent years, symmetry research has shifted from the detection of affinely to perspectively skewed mirror symmetry. Also, links between invariance research and symmetry-specific geometric constraints have been established. The paper aims to contribute to both strands. Several sets of symmetry specific invariants are derived, that can be used in different situations, depending on the a priori assumptions made. It is also argued that all the results directly apply to the case of perspectively skewed point symmetry
Proceedings Tenth IEEE International Workshop on Rapid System Prototyping. Shortening the Path from Specification to Prototype (Cat. No.PR00246)
When implementing a 3D image reconstruction algorithm on a DSP architecture, we find ourselves co... more When implementing a 3D image reconstruction algorithm on a DSP architecture, we find ourselves confronted with a large memory transfer overhead, reducing the possible speedup attainable on recent multi-media oriented architectures. This paper describes how the critical part of the algorithm is re-specified and aggressively transformed at the algorithm code level, to improve the data access locality of the multi-dimensional image signal, while preserving the input/output behaviour. Experiments show that a close to optimal reuse of the data in the foreground memory and registers is obtained, removing the data transfer and storage bottleneck and enabling real-time prototyping of the algorithm on a DSP architecture.
Proceedings of the ACM symposium on Virtual reality software and technology - VRST '97, 1997
A method is presented that extracts the 3D shape of objects, together with their surface texture.... more A method is presented that extracts the 3D shape of objects, together with their surface texture. Both shape and texture are obtained from a single image. The paper sketches the complete system but focuses on the problem of texture extraction. The underlying principle is based on an active technique. A high resolution pattern is projected onto the object and the deformations as observed by a single camera yield the 3rd dimension. The surface texture is extracted from the same image by literally reading between the lines that are used for the shape extraction. This is done using a combination of interpolation and non-linear diffusion techniques. Because the whole procedure is based on a single image, a frame-byframe reconstruction of a video taken with the pattern projected throughout, yields 3D shape dynamics. 1 A paradigm shift in 3D Most methods for three-dimensional shape extraction go via the explicit calculation of the distance between the sensor and the object. The 3D shape of the surface then follows from the variation of this distance. This is what 3D acquisition devices for reverse engineering, shape inspection, and mobile robotics wotild typically do. More recent applications, however, focus on visualization, such as virtual and augmented reality, 3D on the Internet, special effects in movies, etc. These kind of applications come with different priorities: l Extracting the absolute scale of objects usually is not crucial. Objects. will be shown at completely different scales anyway.
Proceedings of 13th International Conference on Pattern Recognition, 1996
ABSTRACT An active 3D acquisition system is presented that is based on the projection a simple pa... more ABSTRACT An active 3D acquisition system is presented that is based on the projection a simple pattern of squares. Through the observation of the projected pattern, and assuming pseudo-orthographic projection, the 3D shape of the scene can be retrieved up to a single parameter, that can be determined through a particularly simple calibration. An algorithm has been developed to automatically detect the lines and crossings of the projected pattern in the image. Experiments on a variety of scenes show that the algorithm is robust and provides accurate 3D reconstructions. Its one-shot operation enables the system to retrieve the shape of moving objects
Proceedings of International Conference on Image Processing, 1997
When using the original slope-intercept parameterisation for the Hough transform, the resulting p... more When using the original slope-intercept parameterisation for the Hough transform, the resulting parameter space actually corresponds to the dual space. Indeed, lines are transformed into points, and for every point there is also a corresponding line. This paper presents a way of exploiting this special property, by the introduction of the Cascaded Hough Transform, or CHT for short. This allows to look for the overall structure in an image, such as lines intersecting in a point or intersection points lying on a line. An interesting example is the detection of vanishing points and vanishing lines.
Image and Vision Computing, 1998
ABSTRACT This article discusses a specific class of planar projective transformations, planar hom... more ABSTRACT This article discusses a specific class of planar projective transformations, planar homologies, and illustrates their importance for geometry based grouping operations. Indeed, planar homologies keep to pop up in several areas of computer vision. Two examples are given in the article: the analysis of planar shapes and their shadows and the detection of extruded shapes. The parameters that are needed to specify homologies are given, as well as their invariants. Since only 5 parameters are required, these invariants are simpler than general projective invariants. The work therefore further corroborates the existence of grouping-specific invariants.
Lecture Notes in Computer Science, 1997
The conservation of archeological sites and historical build-ings is an important goal for both, ... more The conservation of archeological sites and historical build-ings is an important goal for both, scientists as well as the general public. Accurate models of such sites is often a prereq-uisite for conservation, maintenance, restoration, security, and
Computer VisionECCV'96, 1996
The media and communications providers share an increasing interest in 3D models of people, objec... more The media and communications providers share an increasing interest in 3D models of people, objects, and scenes. The paper focuses on features that 3D acquisition systems ought to have in order to optimally serve these markets, where emphasis is on realistic visualisation. It is argued that 3D acquisition techniques developed for traditional applications such as visual inspection aren't necessarily the best option. Techniques should be developed that are dedicated to visualisation-specific requirements. This is exemplified ...
Computer Vision — ECCV '94
Lecture Notes in Computer Science, 1997
ABSTRACT In this paper we present new methods to simultaneously extract and exploit the three-dim... more ABSTRACT In this paper we present new methods to simultaneously extract and exploit the three-dimensional shape of a face and its surface texture. It is based on an active technique, i.e. special illumination, but in contrast to traditional active sensing does not require scanning or sequential projection of multiple patterns. This one-shot nature of the devise allows to capture moving objects, e.g. for making a D reconstruction of a face even when the person is talking. The use of the system is illustrated using simple methods to extract both textural and geometrical features from faces, that can be used for authentication purposes. The advantage of using 3D data is that both types of features can be made more invariant under changes in head pose or illumination conditions.
Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999
3D shape models are often put together from several partial reconstructions. There a r e g o od a... more 3D shape models are often put together from several partial reconstructions. There a r e g o od algorithms available now to perform the necessary, precise registration automatically, but only after the partial reconstructions have been brought into approximate positions. This paper proposes a technique to do precisely that. Automatic`crude registration' is illustrated for Euclidean and a ne transformations between parts. The technique is based on the extraction and invariant characterisation of bitangent curve pairs. These can be found and matched e ciently. Registration of these curves yields the crude initialisation that more precise registration algorithms like ICP or mutual information maximisation can start from.
Applications of Digital Image Processing XVIII, 1995
ABSTRACT This paper describes a new approach for computer based visual grouping. A number of comp... more ABSTRACT This paper describes a new approach for computer based visual grouping. A number of computational principles are defined related to results on neurophysiological and psychophysical experiments. The grouping principles have been subdivided into two groups. The 'first-order processes' perform local operations on 'basic' features such as luminance, color, and orientation. 'Second-order processes' consider bilocal interactions (stereo, optical flow, texture, symmetry). The computational scheme developed in this paper relies on the solution of a set of nonlinear differential equations. They are referred to as 'coupled diffusion maps'. Such systems obey the prescribed computational principles. Several maps, corresponding to different features, evolve in parallel, while all computations within and between the maps are localized in a small neighborhood. Moreover, interactions between maps are bidirectional and retinotopically organized, features also underlying processing by the human visual system. Within this framework, new techniques are proposed and developed for e.g. the segmentation of oriented textures, stereo analysis, optical flow detection, etc. Experiments show that the underlying algorithms prove to be successful for first-order as well as second-order grouping processes and show the promising possiblities such a framework can offer for a large number of low-level vision tasks.
Proceedings of 3rd IEEE International Conference on Image Processing, 1996
ABSTRACT An active 3D acquisition system is presented that projects a simple pattern of squares o... more ABSTRACT An active 3D acquisition system is presented that projects a simple pattern of squares on a scene and views it from a different angle. This paper describes how the observed pattern can be extracted from the image data. The underlying algorithm automatically detects the lines and crossings of the projected pattern in the image. Experiments show that the algorithm is robust and provides accurate three-dimensional (3D) reconstructions. Its one-shot operation principle enables the system to retrieve the shape of moving objects
ICANN ’93, 1993
We investigate the potential of coupled non-linear diffusion processes to provide an efficient an... more We investigate the potential of coupled non-linear diffusion processes to provide an efficient and implementable model for the processing that takes place in the first stages along the visual pathway, and study their role in edge preserving smoothing and noise suppression. The basic idea is that several maps undergo coupled development towards an equilibrium state. These maps could e.g. contain intensity, local edge strength, range, or another quantity. All these maps, including the edge map, contain continuous rather than all-or-nothing information, following a strategy of least commitment. Each of the approaches has been developed and tested on a parallel transputer network.
2015 Digital Heritage, 2015
In this paper, we describe a novel approach for acquiring and managing digital models of archaeol... more In this paper, we describe a novel approach for acquiring and managing digital models of archaeological sites. More in detail, we present an approach to digitization based on a robotic platform and a cloud-based information system. Our robot is the result of over two years of efforts by a group of cultural heritage experts, computer scientists and roboticists. Exploiting the large and heterogeneous amount data provided by the robotic platform requires this data to be managed, organized and analyzed. To this extent we developed ARIS (ARchaeological Information System), a software that exploits modern information retrieval and machine learning systems.
Lecture Notes in Computer Science, 1999
Systems of coupled, non-linear diffusion equations are pro- posed as a computational tool for gro... more Systems of coupled, non-linear diffusion equations are pro- posed as a computational tool for grouping. Grouping tasks are divided into two classes - local and bilocal - and for each a prototypical set of equations is presented. It is shown how different cues can be used for grouping given these two blueprints plus cue-specific specialisations. Results are shown for intensity, texture orientation, stereo disparity, opti- cal flow, mirror symmetry, and regular textures. The proposed equations are particularly well suited for parallel implementations. They also show some interesting analogies with basic architectural characteristics of the cortex.
International Conference on Multisensor Fusion and Integration for Intelligent Systems, 1996
A sensor is proposed with interesting characteristics for applications such as autonomous navigat... more A sensor is proposed with interesting characteristics for applications such as autonomous navigation and virtual reality. The system extracts both 3D shape and surface texture. It is based on the projection of a regular pattern, observed by a single camera. It is cheap, requiring only a slide projector and a camera. Shape and intensity are extracted from one and the
International Conference on Pattern Recognition, 1996
Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1996
Over recent years, symmetry research has shifted from the detection of affinely to perspectively ... more Over recent years, symmetry research has shifted from the detection of affinely to perspectively skewed mirror symmetry. Also, links between invariance research and symmetry-specific geometric constraints have been established. The paper aims to contribute to both strands. Several sets of symmetry specific invariants are derived, that can be used in different situations, depending on the a priori assumptions made. It is also argued that all the results directly apply to the case of perspectively skewed point symmetry
Proceedings Tenth IEEE International Workshop on Rapid System Prototyping. Shortening the Path from Specification to Prototype (Cat. No.PR00246)
When implementing a 3D image reconstruction algorithm on a DSP architecture, we find ourselves co... more When implementing a 3D image reconstruction algorithm on a DSP architecture, we find ourselves confronted with a large memory transfer overhead, reducing the possible speedup attainable on recent multi-media oriented architectures. This paper describes how the critical part of the algorithm is re-specified and aggressively transformed at the algorithm code level, to improve the data access locality of the multi-dimensional image signal, while preserving the input/output behaviour. Experiments show that a close to optimal reuse of the data in the foreground memory and registers is obtained, removing the data transfer and storage bottleneck and enabling real-time prototyping of the algorithm on a DSP architecture.
Proceedings of the ACM symposium on Virtual reality software and technology - VRST '97, 1997
A method is presented that extracts the 3D shape of objects, together with their surface texture.... more A method is presented that extracts the 3D shape of objects, together with their surface texture. Both shape and texture are obtained from a single image. The paper sketches the complete system but focuses on the problem of texture extraction. The underlying principle is based on an active technique. A high resolution pattern is projected onto the object and the deformations as observed by a single camera yield the 3rd dimension. The surface texture is extracted from the same image by literally reading between the lines that are used for the shape extraction. This is done using a combination of interpolation and non-linear diffusion techniques. Because the whole procedure is based on a single image, a frame-byframe reconstruction of a video taken with the pattern projected throughout, yields 3D shape dynamics. 1 A paradigm shift in 3D Most methods for three-dimensional shape extraction go via the explicit calculation of the distance between the sensor and the object. The 3D shape of the surface then follows from the variation of this distance. This is what 3D acquisition devices for reverse engineering, shape inspection, and mobile robotics wotild typically do. More recent applications, however, focus on visualization, such as virtual and augmented reality, 3D on the Internet, special effects in movies, etc. These kind of applications come with different priorities: l Extracting the absolute scale of objects usually is not crucial. Objects. will be shown at completely different scales anyway.
Proceedings of 13th International Conference on Pattern Recognition, 1996
ABSTRACT An active 3D acquisition system is presented that is based on the projection a simple pa... more ABSTRACT An active 3D acquisition system is presented that is based on the projection a simple pattern of squares. Through the observation of the projected pattern, and assuming pseudo-orthographic projection, the 3D shape of the scene can be retrieved up to a single parameter, that can be determined through a particularly simple calibration. An algorithm has been developed to automatically detect the lines and crossings of the projected pattern in the image. Experiments on a variety of scenes show that the algorithm is robust and provides accurate 3D reconstructions. Its one-shot operation enables the system to retrieve the shape of moving objects
Proceedings of International Conference on Image Processing, 1997
When using the original slope-intercept parameterisation for the Hough transform, the resulting p... more When using the original slope-intercept parameterisation for the Hough transform, the resulting parameter space actually corresponds to the dual space. Indeed, lines are transformed into points, and for every point there is also a corresponding line. This paper presents a way of exploiting this special property, by the introduction of the Cascaded Hough Transform, or CHT for short. This allows to look for the overall structure in an image, such as lines intersecting in a point or intersection points lying on a line. An interesting example is the detection of vanishing points and vanishing lines.
Image and Vision Computing, 1998
ABSTRACT This article discusses a specific class of planar projective transformations, planar hom... more ABSTRACT This article discusses a specific class of planar projective transformations, planar homologies, and illustrates their importance for geometry based grouping operations. Indeed, planar homologies keep to pop up in several areas of computer vision. Two examples are given in the article: the analysis of planar shapes and their shadows and the detection of extruded shapes. The parameters that are needed to specify homologies are given, as well as their invariants. Since only 5 parameters are required, these invariants are simpler than general projective invariants. The work therefore further corroborates the existence of grouping-specific invariants.
Lecture Notes in Computer Science, 1997
The conservation of archeological sites and historical build-ings is an important goal for both, ... more The conservation of archeological sites and historical build-ings is an important goal for both, scientists as well as the general public. Accurate models of such sites is often a prereq-uisite for conservation, maintenance, restoration, security, and
Computer VisionECCV'96, 1996
The media and communications providers share an increasing interest in 3D models of people, objec... more The media and communications providers share an increasing interest in 3D models of people, objects, and scenes. The paper focuses on features that 3D acquisition systems ought to have in order to optimally serve these markets, where emphasis is on realistic visualisation. It is argued that 3D acquisition techniques developed for traditional applications such as visual inspection aren't necessarily the best option. Techniques should be developed that are dedicated to visualisation-specific requirements. This is exemplified ...
Computer Vision — ECCV '94
Lecture Notes in Computer Science, 1997
ABSTRACT In this paper we present new methods to simultaneously extract and exploit the three-dim... more ABSTRACT In this paper we present new methods to simultaneously extract and exploit the three-dimensional shape of a face and its surface texture. It is based on an active technique, i.e. special illumination, but in contrast to traditional active sensing does not require scanning or sequential projection of multiple patterns. This one-shot nature of the devise allows to capture moving objects, e.g. for making a D reconstruction of a face even when the person is talking. The use of the system is illustrated using simple methods to extract both textural and geometrical features from faces, that can be used for authentication purposes. The advantage of using 3D data is that both types of features can be made more invariant under changes in head pose or illumination conditions.
Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999
3D shape models are often put together from several partial reconstructions. There a r e g o od a... more 3D shape models are often put together from several partial reconstructions. There a r e g o od algorithms available now to perform the necessary, precise registration automatically, but only after the partial reconstructions have been brought into approximate positions. This paper proposes a technique to do precisely that. Automatic`crude registration' is illustrated for Euclidean and a ne transformations between parts. The technique is based on the extraction and invariant characterisation of bitangent curve pairs. These can be found and matched e ciently. Registration of these curves yields the crude initialisation that more precise registration algorithms like ICP or mutual information maximisation can start from.
Applications of Digital Image Processing XVIII, 1995
ABSTRACT This paper describes a new approach for computer based visual grouping. A number of comp... more ABSTRACT This paper describes a new approach for computer based visual grouping. A number of computational principles are defined related to results on neurophysiological and psychophysical experiments. The grouping principles have been subdivided into two groups. The 'first-order processes' perform local operations on 'basic' features such as luminance, color, and orientation. 'Second-order processes' consider bilocal interactions (stereo, optical flow, texture, symmetry). The computational scheme developed in this paper relies on the solution of a set of nonlinear differential equations. They are referred to as 'coupled diffusion maps'. Such systems obey the prescribed computational principles. Several maps, corresponding to different features, evolve in parallel, while all computations within and between the maps are localized in a small neighborhood. Moreover, interactions between maps are bidirectional and retinotopically organized, features also underlying processing by the human visual system. Within this framework, new techniques are proposed and developed for e.g. the segmentation of oriented textures, stereo analysis, optical flow detection, etc. Experiments show that the underlying algorithms prove to be successful for first-order as well as second-order grouping processes and show the promising possiblities such a framework can offer for a large number of low-level vision tasks.
Proceedings of 3rd IEEE International Conference on Image Processing, 1996
ABSTRACT An active 3D acquisition system is presented that projects a simple pattern of squares o... more ABSTRACT An active 3D acquisition system is presented that projects a simple pattern of squares on a scene and views it from a different angle. This paper describes how the observed pattern can be extracted from the image data. The underlying algorithm automatically detects the lines and crossings of the projected pattern in the image. Experiments show that the algorithm is robust and provides accurate three-dimensional (3D) reconstructions. Its one-shot operation principle enables the system to retrieve the shape of moving objects