Ernst Bovenkamp - Academia.edu (original) (raw)
Uploads
Papers by Ernst Bovenkamp
Proceedings of SPIE, Oct 2, 2008
In 2007 TNO started to fly some sensors on an unmanned helicopter platform. These sensors include... more In 2007 TNO started to fly some sensors on an unmanned helicopter platform. These sensors included RGB, B/W and thermal infrared cameras. In 2008 a spectrometer was added. The goal for 2010 is to be able to offer a low altitude flying platform including several sensors. Development of these sensors will take place the next years. Since the total weight
Proceedings of SPIE, Apr 23, 2010
Automated interpretation of complex images requires elaborate knowledge and model-based image ana... more Automated interpretation of complex images requires elaborate knowledge and model-based image analysis, but often needs interaction with an expert as well. This research describes expert interaction with a multiagent image interpretation system using only a restricted vocabulary of high-level user interactions. The aim is to minimize inter- and intra-observer variability by keeping the total number of interactions as low and simple as pos- sible. The multiagent image interpretation system has elaborate high-level knowledge-based control over low-level image segmen- tation algorithms. Agents use contextual knowledge to keep the number of interactions low but, when in doubt, present the user with the most likely interpretation of the situation. The user, in turn, can correct, supplement, and/or confirm the results of image- processing agents. This is done at a very high level of abstraction such that no knowledge of the underlying segmentation methods, parameters or agent functioning is needed. High-level interaction thereby replaces more traditional contour correction methods like inserting points and/or (re)drawing contours. This makes it easier for the user to obtain good results, while inter- and intra-observer variability are kept minimal, since the image segmentation itself remains under control of image-processing agents. The system has been applied to intravascular ultrasound (IVUS) images. Experi- ments show that with an average of 2-3 high-level user interactions per correction, segmentation results substantially improve while the variationisgreatly reduced. Theachievedlevel ofaccuracy and repeatability is equivalent to that of manual drawing by an expert.
Electrical Engineering, Mathematics and Computer Scienc
Proceedings of the ACM workshop on 3D object retrieval - 3DOR '10, 2010
ABSTRACT A robust and efficient method is presented for recognizing objects in unstructured 3D po... more ABSTRACT A robust and efficient method is presented for recognizing objects in unstructured 3D point clouds acquired from photos. The method first finds the locations of target objects using single spin image matching and then retrieves the orientation and quality of the match using the iterative closest point (ICP) algorithm. In contrast to classic use of spin images as object descriptors, no vertex surface normals are needed, but a global orientation of the scene is used. This assumption allows for an efficient and robust way to detect objects in unstructured point data. In our experiments we show that our spin matching approach is capable of detecting cars in a 3D reconstruction from photos. Moreover, the application of the ICP algorithm afterwards allows us (1) to fit a query model in the scene to retrieve the car's orientation and (2) to distinguish between cars with a similar shape and a different shape using the residual error of the fit. This allows us to locate and recognize different types of cars.
this paper a fuzzy time structure is proposed which fits both time points and intervals. The focu... more this paper a fuzzy time structure is proposed which fits both time points and intervals. The focus of this paper is restricted, however, to unimodal normal fuzzy time points of triangular or trapezoid shape. 2 Combinations of fuzzy subsets
Abstract. NK landscapes (NKL) are stochastically generated pseudoboolean functions with N bits (g... more Abstract. NK landscapes (NKL) are stochastically generated pseudoboolean functions with N bits (genes) and K interactions between genes. By means of the parameter K ruggedness as well as the epistasis can be controlled. NKL are particularly useful to understand the dynamics of evolutionary search. We extend NKL from the traditional binary case to a mixed variable case with continuous, nominal discrete, and integer variables. The resulting test function generator is a suitable test model for mixed-integer evolutionary algorithms (MI-EA)- i. e. instantiations of evolution algorithms that can deal with the aforementioned variable types. We provide a comprehensive introduction to mixed-integer NKL and characteristics of the model (global/local optima, computation, etc.). Finally, a first study of the performance of mixed-integer evolution strategies on this problem family is provided, the results of which underpin its applicability for optimization algorithm design. 1
Abstract. Reinforcement learning (RL) agents can benefit from adaptive exploration/exploitation b... more Abstract. Reinforcement learning (RL) agents can benefit from adaptive exploration/exploitation behavior, especially in dynamic environments. We focus on regulating this exploration/exploitation behavior by controlling the action-selection mechanism of RL. Inspired by psychological studies which show that affect influences human decision making, we use artificial affect to influence an agent’s action-selection. Two existing affective strategies are implemented and, in addition, a new hybrid method that combines both. These strategies are tested on ‘maze tasks’ in which a RL agent has to find food (rewarded location) in a maze. We use Soar-RL, the new RL-enabled version of Soar, as a model environment. One task tests the ability to quickly adapt to an environmental change, while the other tests the ability to escape a local optimum in order to find the global optimum. We show that artificial affect-controlled action-selection in some cases helps agents to faster adapt to changes in t...
A novel approach to temporal reasoning is proposed which deals with both uncertain facts and unce... more A novel approach to temporal reasoning is proposed which deals with both uncertain facts and uncertain temporal information in fuzzy logic. Fuzzy time-objects are defined to represent these uncertainties. A point of particular concern when reasoning with both kinds of uncertainty is that temporal uncertainty should not influence factual uncertainty. On the other hand temporal reasoning is exactly about the relation between time and fact. By introducing constrained time-objects we show that a relation between time and fact can be established while avoiding mixing of uncertainties. Then a method to reason with time-objects is introduced. The inference relation between time-objects is thereby decomposed in a fact-fact and a time-time relation. Such a decomposition is only allowed for (semi-) separable time-objects. The decomposition does not prevent time and fact to have mutual influence. 1 Introduction Temporal reasoning with uncertainty has received growing attention over the past ye...
In this paper we compare Mixed-Integer Evolution Strategies (MI-ES) and standard Evolution Strate... more In this paper we compare Mixed-Integer Evolution Strategies (MI-ES) and standard Evolution Strategies (ES) when applied to find optimal solutions for artificial test problems and medical image processing problems. MI-ES are special instantiations of standard ES that can solve optimization problems with different objective variable types (continuous, integer, and nominal discrete). Artificial test problems are generated with a mixed-integer test generator. The practical image processing problem iss the detection of the lumen boundary in IntraVascular UltraSound (IVUS) images. Based on the experimental results, it is shown that MI-ES generally perform better than standard ES on both artifical and practical image processing problems. Moreover it is shown that MI-ES can effectively improve the parameters settings for the IVUS lumen detection algorithm. Categories and Subject Descriptors
Automated interpretation of complex images requires elaborate knowledge and model-based image ana... more Automated interpretation of complex images requires elaborate knowledge and model-based image analysis, but often needs interaction with an expert as well. This research describes expert interaction with a multiagent image interpretation system using only a restricted vocabulary of high-level user interactions. The aim is to minimize inter- and intra-observer variability by keeping the total number of interactions as low and simple as pos- sible. The multiagent image interpretation system has elaborate high-level knowledge-based control over low-level image segmen- tation algorithms. Agents use contextual knowledge to keep the number of interactions low but, when in doubt, present the user with the most likely interpretation of the situation. The user, in turn, can correct, supplement, and/or confirm the results of image- processing agents. This is done at a very high level of abstraction such that no knowledge of the underlying segmentation methods, parameters or agent functioning ...
Lecture Notes in Computer Science, 2001
Chemical shift imaging (CSI), a method which samples 1H NMR-spectra from a grid of volume element... more Chemical shift imaging (CSI), a method which samples 1H NMR-spectra from a grid of volume elements, produces an overwhelming amount of data. Each spectrum contains information about several metabolites in the sampled area. One approach for interpretation of this large amount of data is segmentation of the CSI grid in clusters which share the same features, followed by classification of
Proceedings of SPIE, Oct 2, 2008
In 2007 TNO started to fly some sensors on an unmanned helicopter platform. These sensors include... more In 2007 TNO started to fly some sensors on an unmanned helicopter platform. These sensors included RGB, B/W and thermal infrared cameras. In 2008 a spectrometer was added. The goal for 2010 is to be able to offer a low altitude flying platform including several sensors. Development of these sensors will take place the next years. Since the total weight
Proceedings of SPIE, Apr 23, 2010
Automated interpretation of complex images requires elaborate knowledge and model-based image ana... more Automated interpretation of complex images requires elaborate knowledge and model-based image analysis, but often needs interaction with an expert as well. This research describes expert interaction with a multiagent image interpretation system using only a restricted vocabulary of high-level user interactions. The aim is to minimize inter- and intra-observer variability by keeping the total number of interactions as low and simple as pos- sible. The multiagent image interpretation system has elaborate high-level knowledge-based control over low-level image segmen- tation algorithms. Agents use contextual knowledge to keep the number of interactions low but, when in doubt, present the user with the most likely interpretation of the situation. The user, in turn, can correct, supplement, and/or confirm the results of image- processing agents. This is done at a very high level of abstraction such that no knowledge of the underlying segmentation methods, parameters or agent functioning is needed. High-level interaction thereby replaces more traditional contour correction methods like inserting points and/or (re)drawing contours. This makes it easier for the user to obtain good results, while inter- and intra-observer variability are kept minimal, since the image segmentation itself remains under control of image-processing agents. The system has been applied to intravascular ultrasound (IVUS) images. Experi- ments show that with an average of 2-3 high-level user interactions per correction, segmentation results substantially improve while the variationisgreatly reduced. Theachievedlevel ofaccuracy and repeatability is equivalent to that of manual drawing by an expert.
Electrical Engineering, Mathematics and Computer Scienc
Proceedings of the ACM workshop on 3D object retrieval - 3DOR '10, 2010
ABSTRACT A robust and efficient method is presented for recognizing objects in unstructured 3D po... more ABSTRACT A robust and efficient method is presented for recognizing objects in unstructured 3D point clouds acquired from photos. The method first finds the locations of target objects using single spin image matching and then retrieves the orientation and quality of the match using the iterative closest point (ICP) algorithm. In contrast to classic use of spin images as object descriptors, no vertex surface normals are needed, but a global orientation of the scene is used. This assumption allows for an efficient and robust way to detect objects in unstructured point data. In our experiments we show that our spin matching approach is capable of detecting cars in a 3D reconstruction from photos. Moreover, the application of the ICP algorithm afterwards allows us (1) to fit a query model in the scene to retrieve the car's orientation and (2) to distinguish between cars with a similar shape and a different shape using the residual error of the fit. This allows us to locate and recognize different types of cars.
this paper a fuzzy time structure is proposed which fits both time points and intervals. The focu... more this paper a fuzzy time structure is proposed which fits both time points and intervals. The focus of this paper is restricted, however, to unimodal normal fuzzy time points of triangular or trapezoid shape. 2 Combinations of fuzzy subsets
Abstract. NK landscapes (NKL) are stochastically generated pseudoboolean functions with N bits (g... more Abstract. NK landscapes (NKL) are stochastically generated pseudoboolean functions with N bits (genes) and K interactions between genes. By means of the parameter K ruggedness as well as the epistasis can be controlled. NKL are particularly useful to understand the dynamics of evolutionary search. We extend NKL from the traditional binary case to a mixed variable case with continuous, nominal discrete, and integer variables. The resulting test function generator is a suitable test model for mixed-integer evolutionary algorithms (MI-EA)- i. e. instantiations of evolution algorithms that can deal with the aforementioned variable types. We provide a comprehensive introduction to mixed-integer NKL and characteristics of the model (global/local optima, computation, etc.). Finally, a first study of the performance of mixed-integer evolution strategies on this problem family is provided, the results of which underpin its applicability for optimization algorithm design. 1
Abstract. Reinforcement learning (RL) agents can benefit from adaptive exploration/exploitation b... more Abstract. Reinforcement learning (RL) agents can benefit from adaptive exploration/exploitation behavior, especially in dynamic environments. We focus on regulating this exploration/exploitation behavior by controlling the action-selection mechanism of RL. Inspired by psychological studies which show that affect influences human decision making, we use artificial affect to influence an agent’s action-selection. Two existing affective strategies are implemented and, in addition, a new hybrid method that combines both. These strategies are tested on ‘maze tasks’ in which a RL agent has to find food (rewarded location) in a maze. We use Soar-RL, the new RL-enabled version of Soar, as a model environment. One task tests the ability to quickly adapt to an environmental change, while the other tests the ability to escape a local optimum in order to find the global optimum. We show that artificial affect-controlled action-selection in some cases helps agents to faster adapt to changes in t...
A novel approach to temporal reasoning is proposed which deals with both uncertain facts and unce... more A novel approach to temporal reasoning is proposed which deals with both uncertain facts and uncertain temporal information in fuzzy logic. Fuzzy time-objects are defined to represent these uncertainties. A point of particular concern when reasoning with both kinds of uncertainty is that temporal uncertainty should not influence factual uncertainty. On the other hand temporal reasoning is exactly about the relation between time and fact. By introducing constrained time-objects we show that a relation between time and fact can be established while avoiding mixing of uncertainties. Then a method to reason with time-objects is introduced. The inference relation between time-objects is thereby decomposed in a fact-fact and a time-time relation. Such a decomposition is only allowed for (semi-) separable time-objects. The decomposition does not prevent time and fact to have mutual influence. 1 Introduction Temporal reasoning with uncertainty has received growing attention over the past ye...
In this paper we compare Mixed-Integer Evolution Strategies (MI-ES) and standard Evolution Strate... more In this paper we compare Mixed-Integer Evolution Strategies (MI-ES) and standard Evolution Strategies (ES) when applied to find optimal solutions for artificial test problems and medical image processing problems. MI-ES are special instantiations of standard ES that can solve optimization problems with different objective variable types (continuous, integer, and nominal discrete). Artificial test problems are generated with a mixed-integer test generator. The practical image processing problem iss the detection of the lumen boundary in IntraVascular UltraSound (IVUS) images. Based on the experimental results, it is shown that MI-ES generally perform better than standard ES on both artifical and practical image processing problems. Moreover it is shown that MI-ES can effectively improve the parameters settings for the IVUS lumen detection algorithm. Categories and Subject Descriptors
Automated interpretation of complex images requires elaborate knowledge and model-based image ana... more Automated interpretation of complex images requires elaborate knowledge and model-based image analysis, but often needs interaction with an expert as well. This research describes expert interaction with a multiagent image interpretation system using only a restricted vocabulary of high-level user interactions. The aim is to minimize inter- and intra-observer variability by keeping the total number of interactions as low and simple as pos- sible. The multiagent image interpretation system has elaborate high-level knowledge-based control over low-level image segmen- tation algorithms. Agents use contextual knowledge to keep the number of interactions low but, when in doubt, present the user with the most likely interpretation of the situation. The user, in turn, can correct, supplement, and/or confirm the results of image- processing agents. This is done at a very high level of abstraction such that no knowledge of the underlying segmentation methods, parameters or agent functioning ...
Lecture Notes in Computer Science, 2001
Chemical shift imaging (CSI), a method which samples 1H NMR-spectra from a grid of volume element... more Chemical shift imaging (CSI), a method which samples 1H NMR-spectra from a grid of volume elements, produces an overwhelming amount of data. Each spectrum contains information about several metabolites in the sampled area. One approach for interpretation of this large amount of data is segmentation of the CSI grid in clusters which share the same features, followed by classification of