Recognition of User-Defined Video Object Models using Weighted Graph Homomorphisms


Farin, Dirk ; With, Peter H. N. de ; Effelsberg, Wolfgang



URL: http://www.researchgate.net/publication/2558531_Re...
Document Type: Conference or workshop publication
Year of publication: 2003
Book title: Image and video communications processing 2003 : 21 - 24 January 2002, Santa Clara, California, USA ; [proceedings of Electronic Imaging, Science and Technology 2003]
The title of a journal, publication series: Proceedings of SPIE
Volume: 5022
Page range: 542-553
Publisher: Vasudev, Bashkaran
Place of publication: Bellingham, Wash.
Publishing house: SPIE Press
ISBN: 0-8194-4822-2
Publication language: English
Institution: School of Business Informatics and Mathematics > Praktische Informatik IV (Effelsberg 1989-2017)
Subject: 004 Computer science, internet
Abstract: In this paper, we propose a new system for video object detection based on user-defined models. Object models are described by model graphs in which nodes represent image regions and edges denote spatial proximity. Each node is attributed with color and shape information about the corresponding image region. Model graphs are specified manually based on a sample image of the object. Object recognition starts with automatic color segmentation of the input image. For each region, the same features are extracted as specified in the model graph. Recognition is based on finding a subgraph in the image graph that matches the model graph. Evidently, it is not possible to find an isomorph subgraph, since node and edge attributes will not match exactly. Furthermore, the automatic segmentation step leads to an oversegmented image. For this reason, we employ emph{inexact} graph matching, where several nodes of the image graph may be mapped onto a single node in the model graph. We have applied our object recognition algorithm to cartoon sequences. This class of sequences is difficult to handle with current automatic segmentation algorithms because the motion estimation has difficulties arising from large homogeneous regions and because the object appearance is typically highly variable. Experiments show that our algorithm can robustly detect the specified objects and also accurately locates the object boundary.




Dieser Eintrag ist Teil der Universitätsbibliographie.




Metadata export


Citation


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item