Dagstuhl Seminar Proceedings, Volume 8091

Document

08091 Abstracts Collection – Logic and Probability for Scene Interpretation

Authors: Bernd Neumann, Anthony C. Cohn, David C. Hogg, and Ralf Möller

Abstract

From 25.2.2008 to Friday 29.2.2008, the Dagstuhl Seminar 08091 ``Logic and Probability for Scene Interpretation'' was held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. 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.

Cite as

Bernd Neumann, Anthony C. Cohn, David C. Hogg, and Ralf Möller. 08091 Abstracts Collection – Logic and Probability for Scene Interpretation. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{neumann_et_al:DagSemProc.08091.1,
  author =	{Neumann, Bernd and Cohn, Anthony C. and Hogg, David C. and M\"{o}ller, Ralf},
  title =	{{08091 Abstracts Collection – Logic and Probability for Scene Interpretation}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--17},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.1},
  URN =		{urn:nbn:de:0030-drops-16480},
  doi =		{10.4230/DagSemProc.08091.1},
  annote =	{Keywords: Logic, probabilities, scene interpretation}
}

Document

DOI: 10.4230/DagSemProc.08091.2

Abstraction, ontology and task-guidance for visual perception in robots

Authors: Matthias Schlemmer and Markus Vincze

Abstract

For solving recognition tasks in order to navigate in unknown environments and to manipulate objects, humans seem to use at least the following crucial capabilities: abstraction (for storing higher-level concepts of things), common sense knowledge and prediction. Whereas the first and second provide the basis for situated recognition, the second and third serve for pruning the search space as it helps anticipating what (in an abstract sense) they will see next and where. The main goal of our current research is, how we could use such a kind of "common sense world knowledge" for guiding visual perception and understanding scenes. Therefore, we are combining an owl-ontology with the output of vision tools. The additional use of abstraction techniques tries to establish the possibility of detecting higher level concepts, such as arches composed of a variable number of parts. The goal is to finally find concepts such as doors and tables in arbitrary scenes in order to arrive at a generic recognition tool for home robots. The ontology should additionally provide task-specific information about the things to detect.

Cite as

Matthias Schlemmer and Markus Vincze. Abstraction, ontology and task-guidance for visual perception in robots. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{schlemmer_et_al:DagSemProc.08091.2,
  author =	{Schlemmer, Matthias and Vincze, Markus},
  title =	{{Abstraction, ontology and task-guidance for visual perception in robots}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--12},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.2},
  URN =		{urn:nbn:de:0030-drops-16081},
  doi =		{10.4230/DagSemProc.08091.2},
  annote =	{Keywords: Abstraction, ontology, task, vision}
}

Document

DOI: 10.4230/DagSemProc.08091.3

Approximate OWL Instance Retrieval with SCREECH

Authors: Pascal Hitzler, Markus Krötzsch, Sebastian Rudolph, and Tuvshintur Tserendorj

Abstract

With the increasing interest in expressive ontologies for the Semantic Web, it is critical to develop scalable and efficient ontology reasoning techniques that can properly cope with very high data volumes. For certain application domains, approximate reasoning solutions, which trade soundness or completeness for increased reasoning speed, will help to deal with the high computational complexities which state of the art ontology reasoning tools have to face. In this paper, we present a comprehensive overview of the SCREECH approach to approximate instance retrieval with OWL ontologies, which is based on the KAON2 algorithms, facilitating a compilation of OWL DL TBoxes into Datalog, which is tractable in terms of data complexity. We present three different instantiations of the Screech approach, and report on experiments which show that the gain in efficiency outweighs the number of introduced mistakes in the reasoning process.

Cite as

Pascal Hitzler, Markus Krötzsch, Sebastian Rudolph, and Tuvshintur Tserendorj. Approximate OWL Instance Retrieval with SCREECH. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-8, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{hitzler_et_al:DagSemProc.08091.3,
  author =	{Hitzler, Pascal and Kr\"{o}tzsch, Markus and Rudolph, Sebastian and Tserendorj, Tuvshintur},
  title =	{{Approximate OWL Instance Retrieval with SCREECH}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--8},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.3},
  URN =		{urn:nbn:de:0030-drops-16157},
  doi =		{10.4230/DagSemProc.08091.3},
  annote =	{Keywords: Description logics, automated reasoning, approximate reasoning, Horn logic}
}

Document

DOI: 10.4230/DagSemProc.08091.4

Architectural and Representational Requirements for Seeing Processes, Proto-affordances and Affordances

Authors: Aaron Sloman

Abstract

This paper, combining the standpoints of philosophy and Artificial Intelligence with theoretical psychology, summarises several decades of investigation by the author of the variety of functions of vision in humans and other animals, pointing out that biological evolution has solved many more problems than are normally noticed. For example, the biological functions of human and animal vision are closely related to the ability of humans to do mathematics, including discovering and proving theorems in geometry, topology and arithmetic. Many of the phenomena discovered by psychologists and neuroscientists require sophisticated controlled laboratory settings and specialised measuring equipment, whereas the functions of vision reported here mostly require only careful attention to a wide range of everyday competences that easily go unnoticed. Currently available computer models and neural theories are very far from explaining those functions, so progress in explaining how vision works is more in need of new proposals for explanatory mechanisms than new laboratory data. Systematically formulating the requirements for such mechanisms is not easy. If we start by analysing familiar competences, that can suggest new experiments to clarify precise forms of these competences, how they develop within individuals, which other species have them, and how performance varies according to conditions. This will help to constrain requirements for models purporting to explain how the competences work. For example, Gibson’s theory of affordances needs a number of extensions, including allowing affordances to be composed in several ways from lower level proto-affordances. The paper ends with speculations regarding the need for new kinds of information-processing machinery to account for the phenomena.

Cite as

Aaron Sloman. Architectural and Representational Requirements for Seeing Processes, Proto-affordances and Affordances. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-57, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{sloman:DagSemProc.08091.4,
  author =	{Sloman, Aaron},
  title =	{{Architectural and Representational Requirements for Seeing Processes, Proto-affordances and Affordances}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--57},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.4},
  URN =		{urn:nbn:de:0030-drops-16569},
  doi =		{10.4230/DagSemProc.08091.4},
  annote =	{Keywords: Vision, affordances, architectures, development, design space}
}

Document

DOI: 10.4230/DagSemProc.08091.5

Assimilating knowledge from neuroimages in schizophrenia diagnostics

Authors: Paulo Santos, Carlos Thomaz, Luiz Celiberto, Fabio Duran, Wagner Gattaz, and Geraldo Busatto

Abstract

The aim of this article is to propose an integrated framework for classifying and describing patterns of disorders from medical images using a combination of image registration, linear discriminant analysis and region-based ontologies. In a first stage of this endeavour we are going to study and evaluate multivariate statistical methodologies to identify the most discriminating hyperplane separating two populations contained in the input data. This step has, as its major goal, the analysis of all the data simultaneously rather than feature by feature. The second stage of this work includes the development of an ontology whose aim is the assimilation and exploration of the knowledge contained in the results of the previous statistical methods. Automated knowledge discovery from images is the key motivation for the methods to be investigated in this research. We argue that such investigation provides a suitable framework for characterising the high complexity of MR images in schizophrenia.

Cite as

Paulo Santos, Carlos Thomaz, Luiz Celiberto, Fabio Duran, Wagner Gattaz, and Geraldo Busatto. Assimilating knowledge from neuroimages in schizophrenia diagnostics. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-25, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{santos_et_al:DagSemProc.08091.5,
  author =	{Santos, Paulo and Thomaz, Carlos and Celiberto, Luiz and Duran, Fabio and Gattaz, Wagner and Busatto, Geraldo},
  title =	{{Assimilating knowledge from neuroimages in schizophrenia diagnostics}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--25},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.5},
  URN =		{urn:nbn:de:0030-drops-16078},
  doi =		{10.4230/DagSemProc.08091.5},
  annote =	{Keywords: Statistical classification, spatial ontologies}
}

Document

DOI: 10.4230/DagSemProc.08091.6

Bayesian Compositional Hierarchies - A Probabilistic Structure for Scene Interpretation

Authors: Bernd Neumann

Abstract

In high-level vision, it is often useful to organize conceptual models in compositional hierarchies. For example, models of building facades (which are used here as examples) can be described in terms of constituent parts such as balconies or window arrays which in turn may be further decomposed. While compositional hierarchies are widely used in scene interpretation, it is not clear how to model and exploit probabilistic dependencies which may exist within and between aggregates. In this contribution I present Bayesian Aggregate Hierarchies as a means to capture probabilistic dependencies in a compositional hierarchy. The formalism integrates well with object-centered representations and extends Bayesian Networks by allowing arbitrary probabilistic dependencies within aggregates. To obtain efficient inference procedures, the aggregate structure must possess abstraction properties which ensure that internal aggregate properties are only affected in accordance with the hierarchical structure. Using examples from the building domain, it is shown that probabilistic aggregate information can thus be integrated into a logic-based scene interpretation system and provide a preference measure for interpretation steps.

Cite as

Bernd Neumann. Bayesian Compositional Hierarchies - A Probabilistic Structure for Scene Interpretation. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{neumann:DagSemProc.08091.6,
  author =	{Neumann, Bernd},
  title =	{{Bayesian Compositional Hierarchies - A Probabilistic Structure for Scene Interpretation}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--16},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.6},
  URN =		{urn:nbn:de:0030-drops-16050},
  doi =		{10.4230/DagSemProc.08091.6},
  annote =	{Keywords: Scene interpretation, compositional hierarchy, probabilistic inference}
}

Document

DOI: 10.4230/DagSemProc.08091.7

Combining Logic and Probability in Tracking and Scene Interpretation

Authors: Brandon Bennett

Abstract

The paper gives a high-level overview of some ways in which logical representations and reasoning can be used in computer vision applications, such as tracking and scene interpretation. The combination of logical and statistical approaches is also considered.

Cite as

Brandon Bennett. Combining Logic and Probability in Tracking and Scene Interpretation. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{bennett:DagSemProc.08091.7,
  author =	{Bennett, Brandon},
  title =	{{Combining Logic and Probability in  Tracking and Scene Interpretation}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--7},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.7},
  URN =		{urn:nbn:de:0030-drops-16120},
  doi =		{10.4230/DagSemProc.08091.7},
  annote =	{Keywords: Vision, Tracking, Logic, Probability, Spatio-Temporal Continuity}
}

Document

DOI: 10.4230/DagSemProc.08091.8

Implementing probabilistic description logics: An application to image interpretation

Authors: Ralf Möller and Tobias H. Näth

Abstract

This paper presents an application of an optimized implementation of a probabilistic description logic defined by Giugno and Lukasiewicz [9] to the domain of image interpretation. This approach extends a description logic with so-called probabilistic constraints to allow for automated reasoning over formal ontologies in combination with probabilistic knowledge. We analyze the performance of current algorithms and investigate new optimization techniques.

Cite as

Ralf Möller and Tobias H. Näth. Implementing probabilistic description logics: An application to image interpretation. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{moller_et_al:DagSemProc.08091.8,
  author =	{M\"{o}ller, Ralf and N\"{a}th, Tobias H.},
  title =	{{Implementing probabilistic description logics: An application to image interpretation}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--6},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.8},
  URN =		{urn:nbn:de:0030-drops-16186},
  doi =		{10.4230/DagSemProc.08091.8},
  annote =	{Keywords: Probabilistic description logics, image interpretation probabilistic lexicographic entailment}
}

Document

DOI: 10.4230/DagSemProc.08091.9

Learning Grammatical Models for Object Recognition

Authors: Meg Aycinena Lippow, Leslie Pack Kaelbling, and Tomas Lozano-Perez

Abstract

Many object recognition systems are limited by their inability to share common parts or structure among related object classes. This capability is desirable because it allows information about parts and relationships in one object class to be generalized to other classes for which it is relevant. This ability has the potential to allow effective parameter learning from fewer examples and better generalization of the learned models to unseen instances, and it enables more efficient recognition. With this goal in mind, we have designed a representation and recognition framework that captures structural variability and shared part structure within and among object classes. The framework uses probabilistic geometric grammars (PGGs) to represent object classes recursively in terms of their parts, thereby exploiting the hierarchical and substitutive structure inherent to many types of objects. To incorporate geometric and appearance information, we extend traditional probabilistic context-free grammars to represent distributions over the relative geometric characteristics of object parts as well as the appearance of primitive parts. We describe an efficient dynamic programming algorithm for object categorization and localization in images given a PGG model. We also develop an EM algorithm to estimate the parameters of a grammar structure from training data, and a search-based structure learning approach that finds a compact grammar to explain the image data while sharing substructure among classes. Finally, we describe a set of experiments that demonstrate empirically that the system provides a performance benefit.

Cite as

Meg Aycinena Lippow, Leslie Pack Kaelbling, and Tomas Lozano-Perez. Learning Grammatical Models for Object Recognition. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{aycinenalippow_et_al:DagSemProc.08091.9,
  author =	{Aycinena Lippow, Meg and Kaelbling, Leslie Pack and Lozano-Perez, Tomas},
  title =	{{Learning Grammatical Models for Object Recognition}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--15},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.9},
  URN =		{urn:nbn:de:0030-drops-16113},
  doi =		{10.4230/DagSemProc.08091.9},
  annote =	{Keywords: Object recognition, grammars, structure learning}
}

Document

DOI: 10.4230/DagSemProc.08091.10

Probabilistic Scene Modeling for Situated Computer Vision

Authors: Sven Wachsmuth and Agnes Swadzba

Abstract

Verbal statements and vision are a rich source of information in a human-machine interaction scenario. For this reason Situated Computer Vision aims to include knowledge about the communicative situation in which it takes place. This paper presents three approaches how to achieve scene models of such scenarios combining different modalities. Seeing (planar) scenes as configurations of parts leads to a probabilistic modeling with Bayes’ nets relating spoken utterances with results of an object recognition step. In the second approach parallel datasets form the basis for analyzing the statistical dependencies between them through learning a statistical translation model which maps between these datasets (here: words in a text and boundary fragments extracted in 2D images). The third approach deals with complex indoor scenes from which 3D data is acquired. Planar structures in the 3D points and statistics extracted on these planar patches describe the coarse spatial layouts of different indoor room types in such a way that a holistic classification scheme can be provided.

Cite as

Sven Wachsmuth and Agnes Swadzba. Probabilistic Scene Modeling for Situated Computer Vision. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{wachsmuth_et_al:DagSemProc.08091.10,
  author =	{Wachsmuth, Sven and Swadzba, Agnes},
  title =	{{Probabilistic Scene Modeling for Situated Computer Vision}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--15},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.10},
  URN =		{urn:nbn:de:0030-drops-16097},
  doi =		{10.4230/DagSemProc.08091.10},
  annote =	{Keywords: Scene Modeling, Human Robot Interaction}
}

Document

DOI: 10.4230/DagSemProc.08091.11

Qualitative Abstraction and Inherent Uncertainty in Scene Recognition

Authors: Carsten Elfers, Otthein Herzog, Andrea Miene, and Thomas Wagner

Abstract

The interpretation of scenes, e.g., in videos, is demanding at all levels. At the image processing level it is necessary to apply an "intelligent" segmentation and to determine the objects of interest. For the higher symbolic levels it is a challenging task to perform the transition between quantitative and qualitative data and to determine the relations between objects. Here we assume that the position of objects ("agents") in images and videos will already be determined as a minimal requirement for the further analysis. The interpretation of complex and dynamic scenes with embedded intentional agents is one of the most challenging tasks in current AI and imposes highly heterogeneous requirements. A key problem is the efficient and robust representation of uncertainty. We propose that uncertainty should be distinguished with respect to two different epistemological sources: (1) noisy sensor information and (2) ignorance. In this presentation we propose possible solutions to this class of problems. The use and evaluation of sensory information in the field of robotics shows impressive results especially in the fields of localization (e.g. MCL) and map building (e.g. SLAM) but also imposes serious problems on the successive higher levels of processing due to the probabilistic nature. In this presentation we propose that the use of (a) qualitative abstraction (classic approach) from quantitative to (at least partial) qualitative representations and (b) coherence-based perception validation based on Dempster-Shafer (DST) can help to reduce the problem significantly. The second important probability problem class that will be addressed is ignorance. In our presentation we will focus on reducing missing information by inference. We contrast/compare our experiences in an important field of scene interpretation namely plan and intention recognition. The first approach is based on a logical abductive approach and the second approach in contrast uses a probabilistic approach (Relational Hidden Markov Model (RHMM)).

Cite as

Carsten Elfers, Otthein Herzog, Andrea Miene, and Thomas Wagner. Qualitative Abstraction and Inherent Uncertainty in Scene Recognition. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{elfers_et_al:DagSemProc.08091.11,
  author =	{Elfers, Carsten and Herzog, Otthein and Miene, Andrea and Wagner, Thomas},
  title =	{{Qualitative Abstraction and Inherent Uncertainty in Scene Recognition}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--15},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.11},
  URN =		{urn:nbn:de:0030-drops-16141},
  doi =		{10.4230/DagSemProc.08091.11},
  annote =	{Keywords: Scene interpretation, intentional agents, uncertainty, qualitative abstraction, coherence-based perception, abduction, RHMM}
}

Document

DOI: 10.4230/DagSemProc.08091.12

Qualitative Arrangement Information for Matching

Authors: Diedrich Wolter

Abstract

In the context of a generalized robot localization task we investigate the utility of qualitative arrangement information in recognition tasks. Qualitative information allows us to make certain knowledge explicit, separating it from uncertain information that we are facing in recognition tasks. This can give rise to efficient matching algorithms for recognition tasks. Particularly qualitative ordering information is very helpful: it can adequately capture certain spatial knowledge and leads to efficient polynomial-time matching algorithms.

Cite as

Diedrich Wolter. Qualitative Arrangement Information for Matching. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-8, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{wolter:DagSemProc.08091.12,
  author =	{Wolter, Diedrich},
  title =	{{Qualitative Arrangement Information for Matching}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--8},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.12},
  URN =		{urn:nbn:de:0030-drops-16103},
  doi =		{10.4230/DagSemProc.08091.12},
  annote =	{Keywords: Matching, qualitative spatial reasoning}
}

Document

DOI: 10.4230/DagSemProc.08091.13

Robust Multi-Person Tracking from Moving Platforms

Authors: Andreas Ess, Konrad Schindler, Bastian Leibe, and Luc van Gool

Abstract

In this paper, we address the problem of multi-person tracking in busy pedestrian zones, using a stereo rig mounted on a mobile platform. The complexity of the problem calls for an integrated solution, which extracts as much visual information as possible and combines it through cognitive feedback. We propose such an approach, which jointly estimates camera position, stereo depth, object detection, and tracking. We model the interplay between these components using a graphical model. Since the model has to incorporate object-object interactions, and temporal links to past frames, direct inference is intractable. We therefore propose a two-stage procedure: for each frame we first solve a simplified version of the model (disregarding interactions and temporal continuity) to estimate the scene geometry and an overcomplete set of object detections. Conditioned on these results, we then address object interactions, tracking, and prediction in a second step. The approach is experimentally evaluated on several long and difficult video sequences from busy inner-city locations. Our results show that the proposed integration makes it possible to deliver stable tracking performance in scenes of realistic complexity.

Cite as

Andreas Ess, Konrad Schindler, Bastian Leibe, and Luc van Gool. Robust Multi-Person Tracking from Moving Platforms. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{ess_et_al:DagSemProc.08091.13,
  author =	{Ess, Andreas and Schindler, Konrad and Leibe, Bastian and van Gool, Luc},
  title =	{{Robust Multi-Person Tracking from Moving Platforms}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--15},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.13},
  URN =		{urn:nbn:de:0030-drops-16173},
  doi =		{10.4230/DagSemProc.08091.13},
  annote =	{Keywords: Pedestrian detection, tracking, Mobile vision}
}

Document

DOI: 10.4230/DagSemProc.08091.14

Scene Understanding of Urban Road Intersections with Description Logic

Authors: Britta Hummel, Werner Thiemann, and Irina Lulcheva

Abstract

Road recognition from video sequences has been solved robustly only for small, often simplified subsets of possible road configurations. A massive augmentation of the amount of prior knowledge may pave the way towards a generation of estimators of more general applicability. This contribution introduces Description Logic extended by rules as a promising knowledge representation formalism for road and intersection understanding. We have set up a Description Logic knowledge base for arbitrary road and intersection geometries and configurations. Logically stated geometric constraints and road building regulations constrain the hypothesis space. Sensor data from an in-vehicle vision sensor and from a digital map provide evidence for a particular intersection. Partial observability and different abstraction layers of the input data are naturally handled by the representation formalism. Deductive inference services – namely satisfiability, classification, entailment, and consistency – are then used to narrow down the intersection hypothesis space based on the evidence and the background knowledge, and to retrieve intersection information relevant to a user, i.e. a human or a driver assistance system. We conclude with an outlook towards non-deductive reasoning, namely model construction under the answer set semantics.

Cite as

Britta Hummel, Werner Thiemann, and Irina Lulcheva. Scene Understanding of Urban Road Intersections with Description Logic. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{hummel_et_al:DagSemProc.08091.14,
  author =	{Hummel, Britta and Thiemann, Werner and Lulcheva, Irina},
  title =	{{Scene Understanding of Urban Road Intersections with Description Logic}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--16},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.14},
  URN =		{urn:nbn:de:0030-drops-16165},
  doi =		{10.4230/DagSemProc.08091.14},
  annote =	{Keywords: Autonomous Driving;, Road Recognition, Knowledge Representation, Description Logic, Nonmonotonic Reasoning}
}

Document

DOI: 10.4230/DagSemProc.08091.15

The Tower of Knowledge: a novel architecture for organising knowledge combining logic and probability

Authors: Maria Petrou

Abstract

It is argued that the ability to generalise is the most important characteristic of learning and that generalisation may be achieved only if pattern recognition systems learn the rules of meta-knowledge rather than the labels of objects. A structure, called "tower of knowledge'', according to which knowledge may be organised, is proposed. A scheme of interpreting scenes using the tower of knowledge and aspects of utility theory is also proposed. Finally, it is argued that globally consistent solutions of labellings are neither possible, nor desirable for an artificial cognitive system.

Cite as

Maria Petrou. The Tower of Knowledge: a novel architecture for organising knowledge combining logic and probability. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{petrou:DagSemProc.08091.15,
  author =	{Petrou, Maria},
  title =	{{The Tower of Knowledge: a novel architecture for organising knowledge combining logic and probability}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--10},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.15},
  URN =		{urn:nbn:de:0030-drops-16069},
  doi =		{10.4230/DagSemProc.08091.15},
  annote =	{Keywords: Learning by example, learning rules}
}

Document

DOI: 10.4230/DagSemProc.08091.16

Towards a Media Interpretation Framework for the Semantic Web

Authors: S. Espinosa Peraldi, A. Kaya, S. Melzer, Ralf Möller, and M. Wessel

Abstract

We present a framework for media interpretation that leverages low-level information extraction to a higher level of abstraction in order to support semantics-based information retrieval for the Semantic Web. The overall goal of the framework is to provide high-level content descriptions of documents for maximizing precision and recall of semantics-based information retrieval.

Cite as

S. Espinosa Peraldi, A. Kaya, S. Melzer, Ralf Möller, and M. Wessel. Towards a Media Interpretation Framework for the Semantic Web. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{espinosaperaldi_et_al:DagSemProc.08091.16,
  author =	{Espinosa Peraldi, S. and Kaya, A. and Melzer, S. and M\"{o}ller, Ralf and Wessel, M.},
  title =	{{Towards a Media Interpretation Framework for the Semantic Web}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--7},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.16},
  URN =		{urn:nbn:de:0030-drops-16190},
  doi =		{10.4230/DagSemProc.08091.16},
  annote =	{Keywords: }
}

Dagstuhl Seminar Proceedings, Volume 8091

Publication Details

Access Numbers

Documents

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Abstract

Cite as

Filters

Thanks for your feedback!

Could not send message