Scene understanding is a central field in computer vision that attempts to detect objects in a scene and reason about their spatial, functional and semantic relations. While many works focus on things (objects with a well-defined shape), less attention has been given to stuff classes (amorphous background regions). However, stuff classes are important as they allow to explain many aspects of an image, including the scene type, thing classes likely to be present and physical attributes of all objects in the scene. The goal of this thesis is to restore the balance between stuff and things in scene understanding. In particular, we investigate how the recognition of stuff differs from things and develop methods that are suitable to deal with both. We use stuff to find things and annotate a large-scale dataset to study stuff and things in context. First, we present two methods for semantic segmentation of stuff and things. Most methods require manual class weighting to counter imbalanced class frequency distributions, particularly on datasets with stuff and thing classes. We develop a novel joint calibration technique that takes into account class imbalance, class competition and overlapping regions by calibrating for the pixel-level evaluation criterion. The second method shows how to unify the advantages of region-based approaches (accurately delineated object boundaries) and fully convolutional approaches (end-to-end training). Both are combined in a universal framework that is equally suitable to deal with stuff and things. Second, we propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. This is particularly important if we want to scale scene understanding to real-world applications with thousands of classes, without having to exhaustively annotate millions of images. Finally, we present COCO-Stuff - the largest existing dataset with dense stuff and thing annotations. Existing datasets are much smaller and were made with expensive polygon-based annotation. We use a very efficient stuff annotation protocol to densely annotate 164K images. Using this new dataset, we provide a detailed analysis of the dataset and visualize how stuff and things co-occur spatially in an image. We revisit the question whether stuff or things are easier to detect and which is more important based on visual and linguistic analysis.

Die vorliegende Arbeit liefert eine ausführliche systematische Untersuchung der Gestellschwingungen von Rollen- und Bogen-Offsetdruckmaschinen. Sie dient dazu, die modalen Eigenschaften (Eigenfrequenzen, Eigenformen) zu identifizieren und die erzwungenen Schwingungen zu simulieren. An drei Rollen-Offsetdruckmaschinen wurden experimentelle und theoretische Modalanalysen durchgeführt. Es wurden die Einflüsse des Baugrundes, der Aufstellung und der Schraubenverbindung auf die modalen Eigenschaften analysiert. Weiterhin wurde die Standsicherheit bei seismischer Erregung überprüft. Für alle vier untersuchten Offsetdruckmaschinen wurden FE-Modelle unter Berücksichtigung ihrer Besonderheiten gebildet und mittels der Messergebnisse abgesichert. Bei Bogen-Offsetdruckmaschinen wurden erzwungene Schwingungen bei vier verschiedenen Erregungen und bei ungleichmäßiger Aufstellung simuliert. Aus den vorliegenden Resultaten können Schlussfolgerungen für die Weiterentwicklung von Druckmaschinen gezogen werden. / This work provides a detailed systematical research about the frame vibrations of web-offset-printing machines and sheetfed-offset-printing machines. It serves to identify the modal properties (natural frequencies and mode shapes) and to simulate the forced vibrations. The experimental and theoretical modal analysis have been realised at three web-offset-printing machines. The influences of the base, installation and screw connection on the modal properties have been analysed, furthermore the stand security under seismic excitation has been verified. The FE-models of all four investigated offset-printing machines have been built under consideration of their characteristics and have been updated with measurement results. Forced vibrations of sheetfed-offset-printing machines have been simulated on four different excitations and for uneven installation. The results of this work can be used for the further development of printing-machines.

No description available.

This thesis proposes tasks of exercises for mentioned course and design and creation of automated evaluation system for these exercises. This thesis focuses on discussion and exemplary solutions of possible tasks of each exercise and description of created automated evaluation system. For evaluation program are made tests with chosen special data sets, which will prove it’s functionality in general data sets.

Die vorliegende Arbeit liefert eine ausführliche systematische Untersuchung der Gestellschwingungen von Rollen- und Bogen-Offsetdruckmaschinen. Sie dient dazu, die modalen Eigenschaften (Eigenfrequenzen, Eigenformen) zu identifizieren und die erzwungenen Schwingungen zu simulieren. An drei Rollen-Offsetdruckmaschinen wurden experimentelle und theoretische Modalanalysen durchgeführt. Es wurden die Einflüsse des Baugrundes, der Aufstellung und der Schraubenverbindung auf die modalen Eigenschaften analysiert. Weiterhin wurde die Standsicherheit bei seismischer Erregung überprüft. Für alle vier untersuchten Offsetdruckmaschinen wurden FE-Modelle unter Berücksichtigung ihrer Besonderheiten gebildet und mittels der Messergebnisse abgesichert. Bei Bogen-Offsetdruckmaschinen wurden erzwungene Schwingungen bei vier verschiedenen Erregungen und bei ungleichmäßiger Aufstellung simuliert. Aus den vorliegenden Resultaten können Schlussfolgerungen für die Weiterentwicklung von Druckmaschinen gezogen werden. / This work provides a detailed systematical research about the frame vibrations of web-offset-printing machines and sheetfed-offset-printing machines. It serves to identify the modal properties (natural frequencies and mode shapes) and to simulate the forced vibrations. The experimental and theoretical modal analysis have been realised at three web-offset-printing machines. The influences of the base, installation and screw connection on the modal properties have been analysed, furthermore the stand security under seismic excitation has been verified. The FE-models of all four investigated offset-printing machines have been built under consideration of their characteristics and have been updated with measurement results. Forced vibrations of sheetfed-offset-printing machines have been simulated on four different excitations and for uneven installation. The results of this work can be used for the further development of printing-machines.