Direkt zum Inhalt | Direkt zur Navigation

Sektionen

agas-news: "Parallelized Energy Minimization for Real-Time Markov Random Field Terrain Classification in Natural Environments" accepted at the ROBIO 2012; Projektpraktikum Robbie 19; AFCEA Preis 2012 für Nicolai Wojke; VDI prize 2012 for master thesis of Susanne Thierfelder; Koblenzer Studenten international erfolgreich mit Roboter Lisa; Koblenzer Studierende schaffen es beim RoboCup German Open ins Finale; Frank Neuhaus erhält Hochschulpreis der Wirtschaft 2012; Detlev Droege has been elected as board member of the COGAIN Association; Computervisualistik veröffentlicht Vorstellungsfilm; "Hierarchical Loop Detection for Mobile Outdoor Robots" accepted at the SPIE - Electronical Imaging 2012; "Moving Vehicle Detection and Tracking in Unstructured Environments" accepted at the ICRA 2012; "Calibration of Multiple Cameras to a 3D Laser Range Finder" accepted at the ESPA 2012; VDI prize for diploma thesis of Christian Winkens; "Spline Templates for Fast Path Planning in Unstructured Environments" accepted at the IROS 2011; "Terrain Classiﬁcation with Markov Random Fields on fused Camera and 3D Laser Range Data" accepted at the ECMR 2011; Johannes Pellenz defends his PhD thesis "Aktive Sensorik für autonome mobile Systeme"; Stipend for diploma thesis of Marc Arends; Weiter…

Startseite → Campus Koblenz → Fachbereich 4: Informatik → Wissenschaftliche Einrichtungen → Institut für Computervisualistik → Active Vision Group → Research → Color Image Processing

Color Image Processing

Color based object Recognition

The research topic is color based object recognition by using specific object information with methods for localizing and identification. For this purpose, an image database contains several objects taken under different illuminations and orientations. An ideal recognition method is determined regarding the selected object during the training. In this phase the position of the objects within the images of the training set is known. This leads to a processing chain adapted to the specific object which gives the best recognition results. The chain consists of noise filters, algorithms of color constancy, color space conversions, histogram methods, etc. The final process should work for all objects in all scenes with unknown illumination and orientation using the determined chain from the training phase and a known query object.

Camera calibration

The results obtained by the object recognition task should be examined additionally in terms of knowing the image formation process. There it needs to be resolved in how far the (spectral) camera response, illumination, and object reflectances, influence the recognition rates?

Staff

Prof. Dr.-Ing. Dietrich Paulus

B 308

+49 261 287-2788

paulus at uni-koblenz.de

Dipl.-Ing. Wolfram Hans

hans at uni-koblenz.de

Literature

Hans2007SEE

Hans, Wolfram; Bäckermann, Florian; Müller, Stefan; Paulus, Dietrich (2007): Spektrale Eigenschaften einer HDR-Kamera. In: Hans, Wolfram; Droege, Detlev; Paulus, Dietrich: 13. Workshop Farbbildverarbeitung. Tönning: Der Andere Verlag. S. 65-73.

Steinmetz2007SUV

Steinmetz, Sarah; Paulus, Dietrich; Hans, Wolfram (2007): Schattenentfernung unter Verwendung des Retinex-Algorithmus. In: Paulus, Dietrich; Droege, Detlev: Diagnostic Reasoning supported by Content-Based ImageRetrieval. Koblenz: Universität Koblenz-Landau. Nr. 11-2005. S. 93-104.

Hans2006MDB1

Hans, Wolfram; Grosch, Thorsten; Feldmann, Tobias; Paulus, Dietrich; Müller, Stefan (2006): Modell der Bildentstehung mit HDR-Kameras. In: 12. Workshop Farbbildverarbeitung. S. 97-108.

zuletzt verändert: 06.07.2010 01:05

Kontakt