14 Search Results for "Denzler, Joachim"


Document
Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382)

Authors: Philipp Berens, Kyle Cranmer, Neil D. Lawrence, Ulrike von Luxburg, and Jessica Montgomery

Published in: Dagstuhl Reports, Volume 12, Issue 9 (2023)


Abstract
This report documents the programme and the outcomes of Dagstuhl Seminar 22382 "Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling". Today’s scientific challenges are characterised by complexity. Interconnected natural, technological, and human systems are influenced by forces acting across time- and spatial-scales, resulting in complex interactions and emergent behaviours. Understanding these phenomena - and leveraging scientific advances to deliver innovative solutions to improve society’s health, wealth, and well-being - requires new ways of analysing complex systems. The transformative potential of AI stems from its widespread applicability across disciplines, and will only be achieved through integration across research domains. AI for science is a rendezvous point. It brings together expertise from AI and application domains; combines modelling knowledge with engineering know-how; and relies on collaboration across disciplines and between humans and machines. Alongside technical advances, the next wave of progress in the field will come from building a community of machine learning researchers, domain experts, citizen scientists, and engineers working together to design and deploy effective AI tools. This report summarises the discussions from the seminar and provides a roadmap to suggest how different communities can collaborate to deliver a new wave of progress in AI and its application for scientific discovery.

Cite as

Philipp Berens, Kyle Cranmer, Neil D. Lawrence, Ulrike von Luxburg, and Jessica Montgomery. Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382). In Dagstuhl Reports, Volume 12, Issue 9, pp. 150-199, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


Copy BibTex To Clipboard

@Article{berens_et_al:DagRep.12.9.150,
  author =	{Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica},
  title =	{{Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382)}},
  pages =	{150--199},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2023},
  volume =	{12},
  number =	{9},
  editor =	{Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.9.150},
  URN =		{urn:nbn:de:0030-drops-178125},
  doi =		{10.4230/DagRep.12.9.150},
  annote =	{Keywords: machine learning, artificial intelligence, life sciences, physical sciences, environmental sciences, simulation, causality, modelling}
}
Document
08422 Abstracts Collection -- Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes

Authors: Joachim Denzler and Michael Koch

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
From 12.10. to 15.10.2008, the Dagstuhl Event 08422 was held in Schloss Dagstuhl~--~Leibniz Center for Informatics. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. Links to extended abstracts or full papers are provided, if available.

Cite as

Joachim Denzler and Michael Koch. 08422 Abstracts Collection -- Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{denzler_et_al:DagSemProc.08422.1,
  author =	{Denzler, Joachim and Koch, Michael},
  title =	{{08422 Abstracts Collection -- Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.1},
  URN =		{urn:nbn:de:0030-drops-18699},
  doi =		{10.4230/DagSemProc.08422.1},
  annote =	{Keywords: Computer Vision, Camera Networks, Natural Scenes}
}
Document
Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes

Authors: Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
Sensor or camera networks will play an important role in future applications, from surveillance tasks for workplace safety or security in general, over driver assisting systems in automotive and last but not least intelligent homes or assisted living for the elderly. Computer vision in sensor or camera networks defines a couple of currently unsolved problems. First of all, how can we calibrate cameras distributed arbitrarily in the scene without placing artificial or natural calibration patterns in the scene? Second, how do we select and fuse the information provided by different, also multimodal sensors to solve a given problem? Finally, can we handle reconstruction, recognition and tracking tasks in complex and highly dynamic natural scenes which are in almost all cases the environment camera networks are designed for?

Cite as

Joachim Denzler. Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{denzler:DagSemProc.08422.2,
  author =	{Denzler, Joachim},
  title =	{{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.2},
  URN =		{urn:nbn:de:0030-drops-18657},
  doi =		{10.4230/DagSemProc.08422.2},
  annote =	{Keywords: Computer Vision, Camera Networks,Natural Scenes}
}
Document
3-D Reconstruction in Piecewise Planar Environments

Authors: Olaf Kähler and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
The structure-from-motion problem is central in applications like visual robot navigation and visual 3d modeling. Typical solutions split the problem into feature tracking and geometric reconstruction steps. Instead we present a combined solution, where the tracking step is implicitly supported by a feedback of 3d information, and the geometric reconstruction is statistically optimal in case of Gaussian noise on image intensities. Experiments confirm an increased accuracy and reliability, and despite a significant computational overhead, the combined solution still runs at 5-10 fps.

Cite as

Olaf Kähler and Joachim Denzler. 3-D Reconstruction in Piecewise Planar Environments. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{kahler_et_al:DagSemProc.08422.3,
  author =	{K\"{a}hler, Olaf and Denzler, Joachim},
  title =	{{3-D Reconstruction in Piecewise Planar Environments}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.3},
  URN =		{urn:nbn:de:0030-drops-18671},
  doi =		{10.4230/DagSemProc.08422.3},
  annote =	{Keywords: Structure-from-motion, tracking, 3d reconstruction}
}
Document
Minimum Uncertainty Triangle Paths for Multi Camera Calibration

Authors: Ferid Bajramovic and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
Multi camera systems become increasingly important in computer vision. For many applications, however, the system has to be calibrated, i.e. the intrinsic and extrinsic parameters of the cameras have to be determined. We present a method for calibrating the extrinsic parameters without any scene knowledge or user interaction. In particular, we assume known intrinsic parameters and one image from each camera as input.

Cite as

Ferid Bajramovic and Joachim Denzler. Minimum Uncertainty Triangle Paths for Multi Camera Calibration. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{bajramovic_et_al:DagSemProc.08422.4,
  author =	{Bajramovic, Ferid and Denzler, Joachim},
  title =	{{Minimum Uncertainty Triangle Paths for Multi Camera Calibration}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.4},
  URN =		{urn:nbn:de:0030-drops-18638},
  doi =		{10.4230/DagSemProc.08422.4},
  annote =	{Keywords: Multi camera, calibration, uncertainty}
}
Document
Active Self Calibration of a Multi Sensor System

Authors: Marcel Brückner and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
The combination of a multi camera system with different sensor types like PMD cameras or motion sensors is called multi sensor system. Such systems offer many different application scenarios, e.g. motion studies of animals and sportsmen, 3D reconstruction or object tracking tasks. In order to work properly, each of this applications needs an accurately calibrated multi sensor system. Calibration consists of estimating the intrinsic parameters of each camera and determining the relative poses (rotation and translation) between the sensors. The second step is known as extrinsic calibration and forms the focus of this work. Self-calibration of a multi sensor system is desirable since a manual calibration is a time consuming and difficult task.

Cite as

Marcel Brückner and Joachim Denzler. Active Self Calibration of a Multi Sensor System. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{bruckner_et_al:DagSemProc.08422.5,
  author =	{Br\"{u}ckner, Marcel and Denzler, Joachim},
  title =	{{Active Self Calibration of a Multi Sensor System}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.5},
  URN =		{urn:nbn:de:0030-drops-18641},
  doi =		{10.4230/DagSemProc.08422.5},
  annote =	{Keywords: Relative pose, extrinsic calibration, multi sensor system, common field of view}
}
Document
Automated Evaluation of 3D Reconstruction Results for Benchmarking View Planning

Authors: Christoph Munkelt and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
To obtain complete 3D object reconstructions using optical measurements, several views of the object are necessary. The task of determining good sensor positions to achieve a 3D reconstruction with low error, high completeness and few required views is called the Next Best View (NBV) problem. Solving the NBV problem is an important task for automated 3D reconstruction. However, comparison of different planning methods has been difficult, since only few dedicated test methods exist. We present an extension to our NBV benchmark framework, that allows for faster, automated evaluation of large result data sets. We show that the method introduces insignificant error, while considerably reducing evaluation runtime and increasing robustness.

Cite as

Christoph Munkelt and Joachim Denzler. Automated Evaluation of 3D Reconstruction Results for Benchmarking View Planning. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{munkelt_et_al:DagSemProc.08422.6,
  author =	{Munkelt, Christoph and Denzler, Joachim},
  title =	{{Automated Evaluation of 3D Reconstruction Results for Benchmarking View Planning}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.6},
  URN =		{urn:nbn:de:0030-drops-18596},
  doi =		{10.4230/DagSemProc.08422.6},
  annote =	{Keywords: Next Best View, View Planning, Optical 3D Reconstruction, Benchmarking}
}
Document
Evaluating Guided KLT Tracking for Next Best View Planning in 3D Reconstruction

Authors: Michael Trummer and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
This report considers the task of 3D reconstruction within a Next Best View (NBV) planning approach. Particular attention is given to the possibilities of extending the well-known Kanade-Lucas-Tomasi (KLT) tracker for the ap- plication within a controlled planning framework. The benefit of the tracker’s extensions to the planning procedure is evaluated quantitatively.

Cite as

Michael Trummer and Joachim Denzler. Evaluating Guided KLT Tracking for Next Best View Planning in 3D Reconstruction. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{trummer_et_al:DagSemProc.08422.7,
  author =	{Trummer, Michael and Denzler, Joachim},
  title =	{{Evaluating Guided KLT Tracking for Next Best View Planning in 3D Reconstruction}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.7},
  URN =		{urn:nbn:de:0030-drops-18620},
  doi =		{10.4230/DagSemProc.08422.7},
  annote =	{Keywords: 3d reconstruction, KLT tracking, sensor planning, Next Best View}
}
Document
Generic Object Recognition

Authors: Doaa Hegazy and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
The object recognition problem has challenged the computer vision community for long time due to the huge change in the scale, occlusion and lighting conditions which have a great effect on the appearance of the objects. The problem of generic object recognition (GOR) has the previously mentioned difficulties in addition to the intra-class and inter-class variability problems. Despite the difficulties of the generic object recognition problem many approaches appeared trying to provide a solution to this problem. We present our model for 2D generic object recognition which achieves good performance on difficult object category datasets. Moreover, we present a model for generic 3D object recognition from range images.

Cite as

Doaa Hegazy and Joachim Denzler. Generic Object Recognition. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{hegazy_et_al:DagSemProc.08422.8,
  author =	{Hegazy, Doaa and Denzler, Joachim},
  title =	{{Generic Object Recognition}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.8},
  URN =		{urn:nbn:de:0030-drops-18668},
  doi =		{10.4230/DagSemProc.08422.8},
  annote =	{Keywords: Generic object recognition, Boosting, Range images}
}
Document
Theory of Learning with Few Examples and Object Localization

Authors: Erik Rodner and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
Visual object localization and categorization is still a big challenge for current research and gets even more difficult when confronted with few training examples. Therefore we will present a Bayesian concept to enhance state-of-the-art machine learning techniques even when dealing with just a single view of an object category. Furthermore an object localization approach is presented, which can serve as a baseline for researchers within the area of object localization.

Cite as

Erik Rodner and Joachim Denzler. Theory of Learning with Few Examples and Object Localization. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{rodner_et_al:DagSemProc.08422.9,
  author =	{Rodner, Erik and Denzler, Joachim},
  title =	{{Theory of Learning with Few Examples and Object Localization}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.9},
  URN =		{urn:nbn:de:0030-drops-18613},
  doi =		{10.4230/DagSemProc.08422.9},
  annote =	{Keywords: Object detection, one-shot learning, knowledge transfer}
}
Document
Model-based Surface Defect Detection and Condition Monitoring in Wire Ropes

Authors: Esther Platzer and Joachim Denzler

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
Wire ropes are exposed to huge external powers everyday. Therefore strict rules for a regular visual inspection exist. Many approaches for textural defect detection in textiles or other materials exist. However, until today no real possibility to control rope attributes like lay length or diameter over the whole rope curse exist. To meet this drawback we present an automatic inspection approach based on a geometric rope model. The parameters of the rope model are estimated over time given raw 2-d image data and local surface defects are located by comparison of the real data with a 2-d projection of the ideal model.

Cite as

Esther Platzer and Joachim Denzler. Model-based Surface Defect Detection and Condition Monitoring in Wire Ropes. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{platzer_et_al:DagSemProc.08422.10,
  author =	{Platzer, Esther and Denzler, Joachim},
  title =	{{Model-based Surface Defect Detection and Condition Monitoring in Wire Ropes}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.10},
  URN =		{urn:nbn:de:0030-drops-18602},
  doi =		{10.4230/DagSemProc.08422.10},
  annote =	{Keywords: Defect detection, visual inspection, analysis-by-synthesis}
}
Document
Universal Image Statistics as a Basis for Esthetic Perception

Authors: Michael Koch, Joachim Denzler, and Christoph Redies

Published in: Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)


Abstract
In the last decades many neuroscientists have started to investigate the perception of nature and art by the human visual system. Natural scenes lead to an esthetically pleasing perception, therefore scientists have begun to research the reasons to understand the processing principles of the human visual system.

Cite as

Michael Koch, Joachim Denzler, and Christoph Redies. Universal Image Statistics as a Basis for Esthetic Perception. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2009)


Copy BibTex To Clipboard

@InProceedings{koch_et_al:DagSemProc.08422.11,
  author =	{Koch, Michael and Denzler, Joachim and Redies, Christoph},
  title =	{{Universal Image Statistics as a Basis for Esthetic Perception}},
  booktitle =	{Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural  Scenes},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{8422},
  editor =	{Joachim Denzler and Michael Koch},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.11},
  URN =		{urn:nbn:de:0030-drops-18689},
  doi =		{10.4230/DagSemProc.08422.11},
  annote =	{Keywords: Esthetic, Aesthetic, PCA, Power Spectrum, Principal Component Analysis}
}
Document
06311 Abstracts Collection – Sensor Data and Information Fusion in Computer Vision and Medicine

Authors: Joachim Denzler, Joachim Hornegger, Josef Kittler, and Calvin R. Maurer JR.

Published in: Dagstuhl Seminar Proceedings, Volume 6311, Sensor Data and Information Fusion in Computer Vision and Medicine (2007)


Abstract
From 30.07.06 to 04.08.06, the Dagstuhl Seminar 06311 ``Sensor Data and Information Fusion in Computer Vision and Medicine'' was held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. Sensor data fusion is of increasing importance for many research fields and applications. Multi-modal imaging is routine in medicine, and in robitics it is common to use multi-sensor data fusion. During the seminar, researchers and application experts working in the field of sensor data fusion presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. The second part briefly summarizes the contributions.

Cite as

Joachim Denzler, Joachim Hornegger, Josef Kittler, and Calvin R. Maurer JR.. 06311 Abstracts Collection – Sensor Data and Information Fusion in Computer Vision and Medicine. In Sensor Data and Information Fusion in Computer Vision and Medicine. Dagstuhl Seminar Proceedings, Volume 6311, pp. 1-12, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2007)


Copy BibTex To Clipboard

@InProceedings{denzler_et_al:DagSemProc.06311.1,
  author =	{Denzler, Joachim and Hornegger, Joachim and Kittler, Josef and Maurer JR., Calvin R.},
  title =	{{06311 Abstracts Collection – Sensor Data and Information Fusion in Computer Vision and Medicine}},
  booktitle =	{Sensor Data and Information Fusion in Computer Vision and Medicine},
  pages =	{1--12},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2007},
  volume =	{6311},
  editor =	{Joachim Denzler and Joachim Hornegger and Josef Kittler and Calvin R. Maurer JR},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.06311.1},
  URN =		{urn:nbn:de:0030-drops-8552},
  doi =		{10.4230/DagSemProc.06311.1},
  annote =	{Keywords: multi-sensor fusion, multi-modal perception, multiple expert fusion, fusion paradigms, multi-modal and intra-modal experts, non-rigid registration, human robot interaction, attention systems, computer vision, image processing, medical image analysis, multi-modal tissue classification, intensity correction, real-time tracking, non-parmetric density estimation, assignment problem, artificial voice}
}
Document
06311 Executive Summary – Sensor Data and Information Fusion in Computer Vision and Medicine

Authors: Joachim Denzler, Joachim Hornegger, Josef Kittler, and Calvin R. Maurer JR.

Published in: Dagstuhl Seminar Proceedings, Volume 6311, Sensor Data and Information Fusion in Computer Vision and Medicine (2007)


Abstract
Today many technical systems are equipped with multiple sensors and information sources, like cameras, ultrasound sensors or web data bases. It is no problem to generate an exorbitantly large amount of data, but it is mostly unsolved how to take advantage of the expectation that the collected data provide more information than the sum of its parts. The design and analysis of algorithms for sensor data and information acquisition and fusion as well as the usage in a differentiated application field was the major focus of the Seminar held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. 24 researchers, practitioners, and application experts from different areas met to summarize the current state-of-the-art technology in data and information fusion, to discuss current research problems in fusion, and to envision future demands of this challenging research field. The considered application scenarios for data and information fusion were in the fields of computer vision and medicine.

Cite as

Joachim Denzler, Joachim Hornegger, Josef Kittler, and Calvin R. Maurer JR.. 06311 Executive Summary – Sensor Data and Information Fusion in Computer Vision and Medicine. In Sensor Data and Information Fusion in Computer Vision and Medicine. Dagstuhl Seminar Proceedings, Volume 6311, pp. 1-3, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2007)


Copy BibTex To Clipboard

@InProceedings{denzler_et_al:DagSemProc.06311.2,
  author =	{Denzler, Joachim and Hornegger, Joachim and Kittler, Josef and Maurer JR., Calvin R.},
  title =	{{06311 Executive Summary – Sensor Data and Information Fusion in Computer Vision and Medicine}},
  booktitle =	{Sensor Data and Information Fusion in Computer Vision and Medicine},
  pages =	{1--3},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2007},
  volume =	{6311},
  editor =	{Joachim Denzler and Joachim Hornegger and Josef Kittler and Calvin R. Maurer JR},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.06311.2},
  URN =		{urn:nbn:de:0030-drops-8542},
  doi =		{10.4230/DagSemProc.06311.2},
  annote =	{Keywords: Sensor and data fusion, adaptive fusion, multimodal fusion, multiple classifier fusion, computer vision, robotics, medical imaging}
}
  • Refine by Author
  • 13 Denzler, Joachim
  • 2 Hornegger, Joachim
  • 2 Kittler, Josef
  • 2 Koch, Michael
  • 2 Maurer JR., Calvin R.
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Artificial intelligence
  • 1 Computing methodologies → Machine learning

  • Refine by Keyword
  • 2 3d reconstruction
  • 2 Computer Vision
  • 2 Next Best View
  • 2 computer vision
  • 1 Aesthetic
  • Show More...

  • Refine by Type
  • 14 document

  • Refine by Publication Year
  • 11 2009
  • 2 2007
  • 1 2023

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail