Susanne Wenzel and Wolfgang Förstner, "Learning a compositional representation for facade object categorization", In ISPRS Annals of Photogrammetry, Remote Sensing and the Spatial Information Sciences; Proc. of 22nd Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS). Vol. I-3( 2012), pp. 197-202. 2012.

• Abstract
• BibTeX
• DOI
• Download

Our objective is the categorization of the most dominant objects in facade images, like windows, entrances and balconies. In order to execute an image interpretation of complex scenes we need an interaction between low level bottom-up feature detection and highlevel inference from top-down. A top-down approach would use results of a bottom-up detection step as evidence for some high-level inference of scene interpretation. We present a statistically founded object categorization procedure that is suited for bottom-up object detection. Instead of choosing a bag of features in advance and learning models based on these features, it is more natural to learn which features best describe the target object classes. Therefore we learn increasingly complex aggregates of line junctions in image sections from man-made scenes. We present a method for the classification of image sections by using the histogram of diverse types of line aggregates.

@inproceedings{Wenzel2012Learning,
  author = {Wenzel, Susanne and F\"orstner, Wolfgang},
  title = {Learning a compositional representation for facade object categorization},
  booktitle = {ISPRS Annals of Photogrammetry, Remote Sensing and the Spatial Information Sciences; Proc. of 22nd Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS)},
  year = {2012},
  volume = {I-3},
  number = { 2012},
  pages = {197--202},
  doi = {10.5194/isprsannals-I-3-197-2012}
}

Susanne Wenzel and Lothar Hotz, "The Role of Sequences for Incremental Learning", In ICAART 2010 - Proceedings of the International Conference on Agents and Artificial Intelligence. Joaquim Filipe and Ana L. N. Fred and Bernadette Sharp (Eds.) Valencia, Spain, January, 2010. Vol. 1, pp. 434-439. INSTICC Press. 2010.

• Abstract
• BibTeX
• Download

In this paper, we point out the role of sequences of samples for training an incremental learning method. We define characteristics of incremental learning methods to describe the influence of sample ordering on the performance of a learned model. We show the influence of sequence for two different types of incremental learning. One is aimed on learning structural models, the other on learning models to discriminate object classes. In both cases, we show the possibility to find good sequences before starting the training.

@inproceedings{Wenzel2010Role,
  author = {Wenzel, Susanne and Hotz, Lothar},
  editor = {Joaquim Filipe and Ana L. N. Fred and Bernadette Sharp},
  title = {The Role of Sequences for Incremental Learning},
  booktitle = {ICAART 2010 - Proceedings of the International Conference on Agents and Artificial Intelligence},
  publisher = {INSTICC Press},
  year = {2010},
  volume = {1},
  pages = {434--439}
}

Susanne Wenzel and Wolfgang Förstner, "The Role of Sequences for Incremental Learning", October, 2009.(TR-IGG-P-2009-04) 2009.

• Abstract
• BibTeX
• Download

This report points out the role of sequences of samples for training an incremental learning method. We define characteristics of incremental learning methods to describe the influence of sample ordering on the performance of a learned model. Different types of experiments evaluate these properties for two different datasets and two different incremental learning methods. We show how to find sequences of classes for training just based on the data to get always best possible error rates. This is based on the estimation of Bayes error bounds.

@techreport{Wenzel2009Role,
  author = {Wenzel, Susanne and F\"orstner, Wolfgang},
  title = {The Role of Sequences for Incremental Learning},
  year = {2009},
  number = {TR-IGG-P-2009-04}
}

Susanne Wenzel and Martin Drauschke and Wolfgang Förstner, "Detection of repeated structures in facade images", Pattern Recognition and Image Analysis., September, 2008. Vol. 18(3), pp. 406-411. 2008.

• Abstract
• BibTeX
• DOI
• Download

We present a method for detecting repeated structures, which is applied on facade images for describing the regularity of their windows. Our approach finds and explicitly represents repetitive structures and thus gives initial representation of facades. No explicit notion of a window is used; thus, the method also appears to be able to identify other manmade structures, e.g., paths with regular tiles. A method for detection of dominant symmetries is adapted for detection of multiply repeated structures. A compact description of the repetitions is derived from the detected translations in the image by a heuristic search method and the criterion of the minimum description length.

@article{Wenzel2008Detection,
  author = {Wenzel, Susanne and Drauschke, Martin and F\"orstner, Wolfgang},
  title = {Detection of repeated structures in facade images},
  journal = {Pattern Recognition and Image Analysis},
  year = {2008},
  volume = {18},
  number = {3},
  pages = {406--411},
  doi = {10.1134/S1054661808030073}
}

Susanne Wenzel and Wolfgang Förstner, "Semi-supervised incremental learning of hierarchical appearance models", In 21st Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS). Beijing, China, pp. 399-404 Part B3b-2. 2008.

• Abstract
• BibTeX
• Download

We propose an incremental learning scheme for learning a class hierarchy for objects typically occurring multiple in images. Given one example of an object that appears several times in the image, e.g. is part of a repetitive structure, we propose a method for identifying prototypes using an unsupervised clustering procedure. These prototypes are used for building a hierarchical appearance based model of the envisaged class in a supervised manner. For classification of new instances detected in new images we use linear subspace methods that combine discriminative and reconstructive properties. The used methods are chosen to be capable for an incremental update. We test our approach on facade images with repetitive windows and balconies. We use the learned object models to find new instances in other images, e. g. the neighbouring facade and update already learned models with the new instances.

@inproceedings{Wenzel2008Semi,
  author = {Wenzel, Susanne and F\"orstner, Wolfgang},
  title = {Semi-supervised incremental learning of hierarchical appearance models},
  booktitle = {21st Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS)},
  year = {2008},
  pages = {399--404 Part B3b-2}
}

Susanne Wenzel and Martin Drauschke and Wolfgang Förstner, "Detection and Description of Repeated Structures in Rectified Facade Images", Photogrammetrie, Fernerkundung, Geoinformation (PFG). Vol. 7, pp. 481-490. 2007.

• Abstract
• BibTeX
• Download

We present a method for detecting repeated structures, which is applied on facade images for describing the regularity of their windows. Our approach finds and explicitly represents repetitive structures and thus gives initial representation of facades. No explicit notion of a window is used, thus the method also appears to be able to identify other man made structures, e.g. paths with regular tiles. A method for detection of dominant symmetries is adapted for detection of multiple repeated structures. A compact description of repetitions is derived from translations detected in an image by a heuristic search method and the model selection criterion of the minimum description length.

@article{Wenzel2007Detection,
  author = {Wenzel, Susanne and Drauschke, Martin and F\"orstner, Wolfgang},
  title = {Detection and Description of Repeated Structures in Rectified Facade Images},
  journal = {Photogrammetrie, Fernerkundung, Geoinformation (PFG)},
  year = {2007},
  volume = {7},
  pages = {481--490}
}

Susanne Wenzel and Martin Drauschke and Wolfgang Förstner, "Detection of repeated structures in facade images", In Proceedings of the OGRW-7-2007, 7th Open German/Russian Workshop on Pattern Recognition and Image Understanding. August 20-23, 2007. Ettlingen, Germany. 2007.

• Abstract
• BibTeX
• DOI
• Download

We present a method for detecting repeated structures, which is applied on facade images for describing the regularity of their windows. Our approach finds and explicitly represents repetitive structures and thus gives initial representation of facades. No explicit notion of a window is used, thus the method also appears to be able to identify other man made structures, e.g. paths with regular tiles. A method for detection of dominant symmetries is adapted for detection of multiply repeated structures. A compact description of the repetitions is derived from the detected translations in the image by a heuristic search method and the criterion of the minimum description length.

@inproceedings{Wenzel2007Detectiona,
  author = {Wenzel, Susanne and Drauschke, Martin and F\"orstner, Wolfgang},
  title = {Detection of repeated structures in facade images},
  booktitle = {Proceedings of the OGRW-7-2007, 7th Open German/Russian Workshop on Pattern Recognition and Image Understanding. August 20-23, 2007. Ettlingen, Germany},
  year = {2007},
  doi = {10.1134/S1054661808030073}
}

Susanne Wenzel and Martin Drauschke and Wolfgang Förstner, "Detektion wiederholter und symmetrischer Strukturen in Fassadenbildern", In Publikationen der DGPF: Von der Medizintechnik bis zur Planetenforschung - Photogrammetrie und Fernerkundung für das 21. Jahrhundert. Seyfert, Eckhardt (Eds.) Muttenz, Basel, June, 2007. Vol. 16, pp. 119-126. DGPF. 2007.

• Abstract
• BibTeX
• Download

Regelmäßige Strukturen und Symmetrien kennzeichnen viele Gebäudefassaden oder Objekte im Umfeld von Gebäuden. Für die automatisierte Bildinterpretation weisen diese Strukturen auf künstliche Objekte hin, führen aber auch zu Schwierigkeiten bei klassischen Bildzuordnungsverfahren. Die Suche und Gruppierung zusammengehöriger Merkmale kann daher sowohl zur Identifikation künstlicher Objekte als auch zur Verbesserung von Zuordnungsverfahren dienen. Für die Analyse von entzerrten Fassadenaufnahmen haben wir das Verfahren von [LOY 2006] zur Detektion symmetrischer Bildstrukturen zu einem Verfahren zur Detektion verschiedener, sich wiederholender Bildstrukturen erweitert und aus den detektierten wiederholten Objekten eine minimale Beschreibung der Struktur der Fassadenelemente in Form von achsenparallelen Basiselementen abgeleitet.

@inproceedings{Wenzel2007Detektion,
  author = {Wenzel, Susanne and Drauschke, Martin and F\"orstner, Wolfgang},
  editor = {Seyfert, Eckhardt},
  title = {Detektion wiederholter und symmetrischer Strukturen in Fassadenbildern},
  booktitle = {Publikationen der DGPF: Von der Medizintechnik bis zur Planetenforschung - Photogrammetrie und Fernerkundung f\"ur das 21. Jahrhundert},
  publisher = {DGPF},
  year = {2007},
  volume = {16},
  pages = {119-126}
}

Susanne Wenzel, "Spiegelung und Zuordnung der SIFT-Feature Deskriptoren für die Detektion von Symmetrien und wiederholten Strukturen in Bildern", August, 2007.(TR-IGG-P-2007-04) 2007.

• Abstract
• BibTeX
• Download

This report describes the details for mirroring the descriptors of the SIFT-features. We show how the mirrored versions are derived by simply resorting the descriptor elements. Furthermore, we describe the matching of features within an image. The peculiarity of this task is the search for more than one - the best - match within an single image. The presented methods are based on the work of (Wenzel2006,Detektion). After the introduction the functionallity of the SIFT-feature detector is drafted and the development of the descriptors is described in detail. The following sections describe the details of mirroring and matching the features. Dieser Bericht geht auf die Details zur Spiegelung von SIFT-Feature Deskritoren ein. Es wird gezeigt, wie durch einfaches Umsortieren der Elemente des Feature Deskriptors gespiegelte Versionen der Deskriptoren erlangt werden können. Des Weiteren wird erläutert, wie Features innerhalb eines Bildes zugeordnet werden können. Die Besonderheit dieser Aufgabenstellung liegt in der gesuchten Zuordnung nicht eines - des besten - Matches, sondern in der Zuordnung aller Matches in einem Bild. Die vorgestellten Methoden basieren auf (Wenzel2006,Detektion).

@techreport{Wenzel2007Spiegelung,
  author = {Wenzel, Susanne},
  title = {Spiegelung und Zuordnung der SIFT-Feature Deskriptoren f\"ur die Detektion von Symmetrien und wiederholten Strukturen in Bildern},
  year = {2007},
  number = {TR-IGG-P-2007-04}
}

Susanne Wenzel, "Detektion wiederholter und symmetrischer Strukturen von Objekten in Bildern". Thesis at: Institute of Photogrammetry, University of Bonn. 2006.

• Abstract
• BibTeX
• Download

Sich wiederholende bzw. symmetrische Strukturen sind Hinweise auf künstliche Objekte, führen aber auch zu Schwierigkeiten bei klassischen Bildzuordnungsverfahren. Die Suche und Gruppierung zusammengehöriger Features kann daher zur Identifikation künstlicher Objekte oder zur Verbesserung von Zuordnungsverfahren dienen. Darüber hinaus kann man aus einem Bild eines im Raum symmetrischen Objekts auf die 3D-Struktur dieses Objekts schließen. Die Diplomarbeit soll das von Loy und Eklundh auf der ECCV 2006 vorgestellte Verfahren zur Detektion symmetrischer und wiederholter Bildbereiche implementieren und hinsichtlich seiner Verwendbarkeit für photogrammetrische Gebäudeaufnahmen überprüfen. Insbesondere geht es um die Detektierbarkeit regelmäßiger Fassadenstrukturen in Abhängigkeit von ihrer Komplexität. Darüber hinaus ist zu klären, wie mehrfache Symmetrien identifiziert und ggf. für die 3D-Rekonstruktion des regelmässigen Teils der Fassadenstruktur genutzt werden können.

@mastersthesis{Wenzel2006Detektion,
  author = {Wenzel, Susanne},
  title = {Detektion wiederholter und symmetrischer Strukturen von Objekten in Bildern},
  school = {Institute of Photogrammetry, University of Bonn},
  year = {2006},
  note = {Betreuung: Prof. Dr.-Ing. Wolfgang F\"orstner, Dipl.-Inform. Martin Drauschke}
}