Pieter P Jonker | Delft University of Technology (original) (raw)
Papers by Pieter P Jonker
Journal of Imaging, 2022
Applying machine learning (ML), and especially deep learning, to understand visual content is bec... more Applying machine learning (ML), and especially deep learning, to understand visual content is becoming common practice in many application areas. However, little attention has been given to its use within the multimedia creative domain. It is true that ML is already popular for content creation, but the progress achieved so far addresses essentially textual content or the identification and selection of specific types of content. A wealth of possibilities are yet to be explored by bringing the use of ML into the multimedia creative process, allowing the knowledge inferred by the former to influence automatically how new multimedia content is created. The work presented in this article provides contributions in three distinct ways towards this goal: firstly, it proposes a methodology to re-train popular neural network models in identifying new thematic concepts in static visual content and attaching meaningful annotations to the detected regions of interest; secondly, it presents var...
Applied Nursing Research, 2016
RoboCup 2001: Robot Soccer World Cup V, 2002
Abstract: Een samenleving waarin robot en mens volledig coëxisteren, is dat sciencefiction of nab... more Abstract: Een samenleving waarin robot en mens volledig coëxisteren, is dat sciencefiction of nabije toekomst? Wat moet de mens ermee dat over twintig jaar misschien robots over straat lopen, opa's en oma's verzorgen, operaties uitvoeren en oorlogen voor ons ...
Relation, 2005
This document provides a brief report on the Dutch AIBO Team in 2004, its first year of existence... more This document provides a brief report on the Dutch AIBO Team in 2004, its first year of existence. The team setup is described, as are the research plans for 2004. In addition, the results obtained and scores achieved are presented, together with an outlook for 2005. ... At the end of 2003, several institutes in the Netherlands have joined forces and formed The Dutch AIBO Team. We are a group of researchers and students from the universities of Amsterdam, Delft, Twente and Utrecht, and the DECIS Lab. Our goal is to stimulate research, teaching, and ...
Proc. Robocup 2004 Symposium, Mar 1, 2004
At the end of last year, several institutes in the Netherlands have joined forces and formed The ... more At the end of last year, several institutes in the Netherlands have joined forces and formed The Dutch AIBO Team. We are a group of researchers and students from the universities of Amsterdam, Delft, Twente and Utrecht, and the DECIS Lab. Our goal is to stimulate research, teaching, and applications in the fields of artificial intelligence and collaborative robotics in the Netherlands by joining the international RoboCup community.
In a widely connected world, communicating through multimedia content has exponentially been gain... more In a widely connected world, communicating through multimedia content has exponentially been gaining popularity. Mostly for common use, technology that enables the production of quality content for sharing in social media, plays nowadays an essential role. The main goal is to achieve content production the faster and the better as possible. Yet, taking a photograph and applying a filter is now a quite conventional type of content production. Thus, the new challenge in multimedia communication comes in finding creative approaches for content creation, towards using technology for building new smart and appealing solutions. In light of this new market demand, this paper presents Fotoinmotion: a system for producing automatic videos based on a still image. Instead of using animation templates transverse to the content of a photograph, this framework takes into account semantic information to produce storytelling videos, focusing on the relevant features of the input image. The resultin...
Twin-to-Twin Transfusion Syndrome (TTTS) is a condition that occurs in about 10% of pregnancies i... more Twin-to-Twin Transfusion Syndrome (TTTS) is a condition that occurs in about 10% of pregnancies involving monochorionic twins. This complication can be treated with fetoscopic laser coagulation. The procedure could greatly benefit from panorama reconstruction to gain an overview of the placenta. Current state-of-the-art methods focus on panorama reconstruction in an ex-vivo setting. However, these methods fail in the in-vivo surgical setting. This paper describes the panorama reconstruction approach, the challenges posed by the in-vivo setting and the influence of these challenges on the panorama reconstruction. With experiments we show that the viewing quality is greatly reduced and that the limited motion of the fetoscope complicates and limits the precision of the image registration. We also identify the aspect necessary to shift from ex-vivo to in-vivo panorama reconstruction. Following our recommendations it should be possible to develop an approach that can be applied to TTTS ...
Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval - ICMR '18, 2018
In this paper, a method for direct trajectory generation for robotic manipulators is proposed. Th... more In this paper, a method for direct trajectory generation for robotic manipulators is proposed. The method is specifically designed for obstacle avoidance and can incorporate kinematic constraints into the avoidance motion. In particular, a point-to-point and multi-point trajectory generator is proposed in which different levels of constraints can be established on via- and end-points. The approach is direct in the sense that at every time instant a new trajectory is generated, which allows the trajectory to be changed at runtime. Moreover, when the final conditions of the trajectory are altered such that constraints would be violated, an optimization procedure is employed in order to extend the execution time of the trajectory. This effectively makes the trajectory time-optimal. The approach is experimentally verified with a 7-DOF anthropomorphic manipulator with time-synchronization of multiple trajectories. I. INTRODUCTION With the increasing demand of integrating robotics into ev...
2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2016
In this paper we introduce a method to handle the challenges posed by image registration for plac... more In this paper we introduce a method to handle the challenges posed by image registration for placenta reconstruction from fetoscopic video as used in the treatment of Twinto-Twin Transfusion Syndrome (TTTS). Panorama reconstruction of the placenta greatly supports the surgeon in obtaining a complete view of the placenta to localize vascular anastomoses. The found shunts can subsequently be blocked by coagulation in the correct order. By using similarity learning in training a Convolutional Neural Network we created a novel feature extraction method, allowing robust matching of keypoints for image registration and therefore taking the most critical step in placenta reconstruction from fetoscopic video. The fetoscopic video we used for our experiments was acquired from a training simulator for TTTS surgery. We compared our method with state-of-the-art methods. The matching performance of our method is up to three times better while the mean projection error is reduced with 64% for the...
In the last decade many architectures for low-level image 2- Image processing tasks. processing w... more In the last decade many architectures for low-level image 2- Image processing tasks. processing were developed. But simultaneously the image processing tasks were growing and changing, resulting in a As we look at tasks that are performed in image processing different set of basic operations than was needed ten years nowadays a few profiles can be sketched, without ago. An attempt is made to classify the existing and pretending to beexhaustive: proposed architectures over the past ten years followed by the results of a theoretical comparison on three of the main 2.1 Industrial inspection and robotics: groups of architectures, the pipelines, the processor arrays and the linear processor arrays. One of the conclusions is Industrial inspection and robotics is nowadays a main that recursive neighbourhood operations appear to be an application field of the classical 20 image processing efficient way to implement global operations and object sequence. operations. But is there support from...
In this paper we propose an object-driven online segmentation system for mobile robots. Among exi... more In this paper we propose an object-driven online segmentation system for mobile robots. Among existing tracking and segmentation methods, the methods themselves are highly emphasized while properties of objects are usually not exploited enough. We propose an adaptive selection mechanism based on the properties of the objects to automatically choose an optimal tracking algorithm. For textured objects, a tracking algorithm which combines Lucas-Kanade tracker and model based detector using Random Forests classifier is adopted; for uniform objects, a color based tracker with a smooth constraint enforcement is used to ensure a robust performance. Moreover, a two-step object segmentation using Gaussian Mixture Models and graph cuts is applied to obtain detailed shape information. The experimental results on a variety of objects show the effectiveness of the adaptive tracking selection mechanism. The system also yields very promising performance in very challenging conditions with occlusio...
An cvaluation is made of hardware and software rcquircmcnts to support window-, crinkle- and pyra... more An cvaluation is made of hardware and software rcquircmcnts to support window-, crinkle- and pyramid-mapping on a lincar and a squarc proccssor array. The diffcrcnt mapping stratcgics also lcad to diffcrcnt algorithms to solvc imagc proccssing problcms. Thrcc imagc proccssing problems servc as an cxarnplc of thc algorithmic diffcrcnccs causcd by the mapping mcthods. For thc invcstigatcd 2D proccssor array, thc pyramid mapping givcs thc fastcst rcsults.
This paper proposes a quality of service multi-sensor bootstrap filter for automated driving that... more This paper proposes a quality of service multi-sensor bootstrap filter for automated driving that deals with time-varying or state dependent conditions. In this way, the reliability of the sensor data fusion system is continuously evaluated in order to detect potentially dangerous conditions such as sensor failure or adverse environmental conditions such as rain and fog. Simulations show that the proposed robust multi-sensor bootstrap filter is able to robustly estimate the quality of service of the sensors. Furthermore, the filter outperforms tracking filters that assume a perfect detection profile. In addition, real world experiments in a fog simulator show that the proposed multi-sensor local-bootstrap-LMB filter outperforms all other filters in foggy conditions.
TechUnited is the Robocup midsize league team of Eindhoven and Delft Universities of Technology. ... more TechUnited is the Robocup midsize league team of Eindhoven and Delft Universities of Technology. It is a carrier project for research streams on mechatronics, computer vision, software architecture and engineering, and sensing and planning. In addition, its industrial complexity makes the project a case study for researching processes and practices of integrated high-tech systems development projects. The team is set up mid 2005, with the ambitious goal of competing in the 2006 Robocup World Championships. Reuse of the knowledge of the former Dutch Robocup team Clockwork Orange plays a key role in this strategy.
Journal of Imaging, 2022
Applying machine learning (ML), and especially deep learning, to understand visual content is bec... more Applying machine learning (ML), and especially deep learning, to understand visual content is becoming common practice in many application areas. However, little attention has been given to its use within the multimedia creative domain. It is true that ML is already popular for content creation, but the progress achieved so far addresses essentially textual content or the identification and selection of specific types of content. A wealth of possibilities are yet to be explored by bringing the use of ML into the multimedia creative process, allowing the knowledge inferred by the former to influence automatically how new multimedia content is created. The work presented in this article provides contributions in three distinct ways towards this goal: firstly, it proposes a methodology to re-train popular neural network models in identifying new thematic concepts in static visual content and attaching meaningful annotations to the detected regions of interest; secondly, it presents var...
Applied Nursing Research, 2016
RoboCup 2001: Robot Soccer World Cup V, 2002
Abstract: Een samenleving waarin robot en mens volledig coëxisteren, is dat sciencefiction of nab... more Abstract: Een samenleving waarin robot en mens volledig coëxisteren, is dat sciencefiction of nabije toekomst? Wat moet de mens ermee dat over twintig jaar misschien robots over straat lopen, opa's en oma's verzorgen, operaties uitvoeren en oorlogen voor ons ...
Relation, 2005
This document provides a brief report on the Dutch AIBO Team in 2004, its first year of existence... more This document provides a brief report on the Dutch AIBO Team in 2004, its first year of existence. The team setup is described, as are the research plans for 2004. In addition, the results obtained and scores achieved are presented, together with an outlook for 2005. ... At the end of 2003, several institutes in the Netherlands have joined forces and formed The Dutch AIBO Team. We are a group of researchers and students from the universities of Amsterdam, Delft, Twente and Utrecht, and the DECIS Lab. Our goal is to stimulate research, teaching, and ...
Proc. Robocup 2004 Symposium, Mar 1, 2004
At the end of last year, several institutes in the Netherlands have joined forces and formed The ... more At the end of last year, several institutes in the Netherlands have joined forces and formed The Dutch AIBO Team. We are a group of researchers and students from the universities of Amsterdam, Delft, Twente and Utrecht, and the DECIS Lab. Our goal is to stimulate research, teaching, and applications in the fields of artificial intelligence and collaborative robotics in the Netherlands by joining the international RoboCup community.
In a widely connected world, communicating through multimedia content has exponentially been gain... more In a widely connected world, communicating through multimedia content has exponentially been gaining popularity. Mostly for common use, technology that enables the production of quality content for sharing in social media, plays nowadays an essential role. The main goal is to achieve content production the faster and the better as possible. Yet, taking a photograph and applying a filter is now a quite conventional type of content production. Thus, the new challenge in multimedia communication comes in finding creative approaches for content creation, towards using technology for building new smart and appealing solutions. In light of this new market demand, this paper presents Fotoinmotion: a system for producing automatic videos based on a still image. Instead of using animation templates transverse to the content of a photograph, this framework takes into account semantic information to produce storytelling videos, focusing on the relevant features of the input image. The resultin...
Twin-to-Twin Transfusion Syndrome (TTTS) is a condition that occurs in about 10% of pregnancies i... more Twin-to-Twin Transfusion Syndrome (TTTS) is a condition that occurs in about 10% of pregnancies involving monochorionic twins. This complication can be treated with fetoscopic laser coagulation. The procedure could greatly benefit from panorama reconstruction to gain an overview of the placenta. Current state-of-the-art methods focus on panorama reconstruction in an ex-vivo setting. However, these methods fail in the in-vivo surgical setting. This paper describes the panorama reconstruction approach, the challenges posed by the in-vivo setting and the influence of these challenges on the panorama reconstruction. With experiments we show that the viewing quality is greatly reduced and that the limited motion of the fetoscope complicates and limits the precision of the image registration. We also identify the aspect necessary to shift from ex-vivo to in-vivo panorama reconstruction. Following our recommendations it should be possible to develop an approach that can be applied to TTTS ...
Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval - ICMR '18, 2018
In this paper, a method for direct trajectory generation for robotic manipulators is proposed. Th... more In this paper, a method for direct trajectory generation for robotic manipulators is proposed. The method is specifically designed for obstacle avoidance and can incorporate kinematic constraints into the avoidance motion. In particular, a point-to-point and multi-point trajectory generator is proposed in which different levels of constraints can be established on via- and end-points. The approach is direct in the sense that at every time instant a new trajectory is generated, which allows the trajectory to be changed at runtime. Moreover, when the final conditions of the trajectory are altered such that constraints would be violated, an optimization procedure is employed in order to extend the execution time of the trajectory. This effectively makes the trajectory time-optimal. The approach is experimentally verified with a 7-DOF anthropomorphic manipulator with time-synchronization of multiple trajectories. I. INTRODUCTION With the increasing demand of integrating robotics into ev...
2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2016
In this paper we introduce a method to handle the challenges posed by image registration for plac... more In this paper we introduce a method to handle the challenges posed by image registration for placenta reconstruction from fetoscopic video as used in the treatment of Twinto-Twin Transfusion Syndrome (TTTS). Panorama reconstruction of the placenta greatly supports the surgeon in obtaining a complete view of the placenta to localize vascular anastomoses. The found shunts can subsequently be blocked by coagulation in the correct order. By using similarity learning in training a Convolutional Neural Network we created a novel feature extraction method, allowing robust matching of keypoints for image registration and therefore taking the most critical step in placenta reconstruction from fetoscopic video. The fetoscopic video we used for our experiments was acquired from a training simulator for TTTS surgery. We compared our method with state-of-the-art methods. The matching performance of our method is up to three times better while the mean projection error is reduced with 64% for the...
In the last decade many architectures for low-level image 2- Image processing tasks. processing w... more In the last decade many architectures for low-level image 2- Image processing tasks. processing were developed. But simultaneously the image processing tasks were growing and changing, resulting in a As we look at tasks that are performed in image processing different set of basic operations than was needed ten years nowadays a few profiles can be sketched, without ago. An attempt is made to classify the existing and pretending to beexhaustive: proposed architectures over the past ten years followed by the results of a theoretical comparison on three of the main 2.1 Industrial inspection and robotics: groups of architectures, the pipelines, the processor arrays and the linear processor arrays. One of the conclusions is Industrial inspection and robotics is nowadays a main that recursive neighbourhood operations appear to be an application field of the classical 20 image processing efficient way to implement global operations and object sequence. operations. But is there support from...
In this paper we propose an object-driven online segmentation system for mobile robots. Among exi... more In this paper we propose an object-driven online segmentation system for mobile robots. Among existing tracking and segmentation methods, the methods themselves are highly emphasized while properties of objects are usually not exploited enough. We propose an adaptive selection mechanism based on the properties of the objects to automatically choose an optimal tracking algorithm. For textured objects, a tracking algorithm which combines Lucas-Kanade tracker and model based detector using Random Forests classifier is adopted; for uniform objects, a color based tracker with a smooth constraint enforcement is used to ensure a robust performance. Moreover, a two-step object segmentation using Gaussian Mixture Models and graph cuts is applied to obtain detailed shape information. The experimental results on a variety of objects show the effectiveness of the adaptive tracking selection mechanism. The system also yields very promising performance in very challenging conditions with occlusio...
An cvaluation is made of hardware and software rcquircmcnts to support window-, crinkle- and pyra... more An cvaluation is made of hardware and software rcquircmcnts to support window-, crinkle- and pyramid-mapping on a lincar and a squarc proccssor array. The diffcrcnt mapping stratcgics also lcad to diffcrcnt algorithms to solvc imagc proccssing problcms. Thrcc imagc proccssing problems servc as an cxarnplc of thc algorithmic diffcrcnccs causcd by the mapping mcthods. For thc invcstigatcd 2D proccssor array, thc pyramid mapping givcs thc fastcst rcsults.
This paper proposes a quality of service multi-sensor bootstrap filter for automated driving that... more This paper proposes a quality of service multi-sensor bootstrap filter for automated driving that deals with time-varying or state dependent conditions. In this way, the reliability of the sensor data fusion system is continuously evaluated in order to detect potentially dangerous conditions such as sensor failure or adverse environmental conditions such as rain and fog. Simulations show that the proposed robust multi-sensor bootstrap filter is able to robustly estimate the quality of service of the sensors. Furthermore, the filter outperforms tracking filters that assume a perfect detection profile. In addition, real world experiments in a fog simulator show that the proposed multi-sensor local-bootstrap-LMB filter outperforms all other filters in foggy conditions.
TechUnited is the Robocup midsize league team of Eindhoven and Delft Universities of Technology. ... more TechUnited is the Robocup midsize league team of Eindhoven and Delft Universities of Technology. It is a carrier project for research streams on mechatronics, computer vision, software architecture and engineering, and sensing and planning. In addition, its industrial complexity makes the project a case study for researching processes and practices of integrated high-tech systems development projects. The team is set up mid 2005, with the ambitious goal of competing in the 2006 Robocup World Championships. Reuse of the knowledge of the former Dutch Robocup team Clockwork Orange plays a key role in this strategy.