Semantic Reasoning for Scene Interpretation

Date

2008-01-01

Author

Jensen, Lars B. W.
Baseski, Emre
Kalkan, Sinan
Pugeault, Nicolas
Woergoetter, Florentin
Krueger, Norbert

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

32
views

0
downloads

In this paper, we propose a hierarchical architecture for representing scenes, covering 2D and 3D aspects of visual scenes as well as the semantic relations between the different aspects. We argue that labeled graphs are a suitable representational framework for this representation and demonstrate its potential by two applications. As a first application, we localize lane structures by the semantic descriptors and their relations in a Bayesian framework. As the second application, which is in the context of vision based grasping, we show how the semantic relations can be associated to actions that allow for grasping without using any object knowledge.

Subject Keywords

cognitive vision, semantic reasoning, bayesian classification

URI

https://hdl.handle.net/11511/96596

DOI

https://doi.org/10.1007/978-3-540-92781-5_10

Conference Name

4th International Cognitive Vision Workshop (ICVW 2008)

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Semantic discontinuities: investigating designers' product expressions versus users' product impressions Khalaj, Javad; Pedgley, Owaın Francıs; Department of Industrial Design (2015) The doctoral thesis investigates issues in design communication between a designer’s semantic intention and users’ initial experience of a product, with a focus on visual qualities. The starting argumentation is that there can exist a level of discontinuity between meanings as intended to be expressed (by the designer of a product) and meanings as actually construed (by target users of that product). The primary purpose of the research is to develop and implement a methodology to identify where, and to what...
Hierarchical representations for visual object tracking by detection Beşbınar, Beril; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2015) Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have improved the state of the art in many areas such as visual object detection, scene understanding or speech recognition. Rebirth of these fairly old computational models is usually related to the availability of large datasets, increase in the computational power of current hardware and more recently proposed unsupervised training methods that exploit the internal structure of very lar...
A scene representation based on multi-modal 2D and 3D features Başeski, Emre; Kraft, Dirk; Pugeault, Nicolas; Wörgötter, Florentin; Kalkan, Sinan; Krüger, Norbert (2007-12-01) Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the different dimensions according to the requirements of the problem and use them together to combine the reliability of 2D information with the richness of 3D information. In this article, we use 2D and 3D information in a feature-based vision system and demonstrate their complementary properties on different applications (namely: depth pr...
Supervised mesh segmentation for 3D objects with graph Convolutional neural networks Perek, Emir Kaan; Sahillioğlu, Yusuf; Department of Computer Engineering (2019) Mesh segmentation is a fundamental application that is primarily used for understanding and analyzing 3D shapes in a broad range of areas in Computer Science. With the increasing trend of deep learning, there have been many learning-based solutions to the mesh segmentation problem based on the classification of the individual mesh polygons. In this thesis, we cast mesh segmentation as a supervised graph labeling problem by using Graph Convolutional Neural Networks (GCNN). We treat a mesh object as a graph t...
Visual structures for generative design search spaces / Abbas, Günsu Merin; Gürsel Dino, İpek; Baykan, Ahmet Can; Department of Architecture (2014) With the adoption of computational strategies in design, the act of design, the process of problem solving, and the interaction, understanding and the representation of design artefacts has changed. With generative design methods, the understanding of design as artefact gives way to design as process. Generative methods entail multiple design solutions, which enlarge the design search space due to the large number of possible design solutions. Regarding the automated design generation process, the interacti...

Citation Formats

L. B. W. Jensen, E. Baseski, S. Kalkan, N. Pugeault, F. Woergoetter, and N. Krueger, “Semantic Reasoning for Scene Interpretation,” Santorini, Yunanistan, 2008, vol. 5329, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/96596.