|
Title:
|
3D OBJECT RECOGNITION AND LOCALIZATION EMPLOYING ANALYSIS BY SYNTHESIS |
|
Author(s):
|
M. Langer , L. Kuhnert , M.ax , D. N. Van , H. Schmick , K.-d. Kuhnert |
|
ISBN:
|
978-972-8924-97-3 |
|
Editors:
|
Hans Weghorn and Pedro Isaías |
|
Year:
|
2009 |
|
Edition:
|
V I, 2 |
|
Keywords:
|
Intelligent Systems, Algorithms, Applied Information Systems, Data Mining |
|
Type:
|
Full Paper |
|
First Page:
|
132 |
|
Last Page:
|
140 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Object recognition in a 3D environment forms a ubiquitous problem in digital image processing. Classic systems try to
solve this problem strictly view-based, while modern systems also take 3D model data into account.
In this paper we present a novel approach in 3D object recognition based on an analysis by synthesis system. This
iterative system consists of two major software components: a flexible 3D object renderer to generate arbitrary synthetic
views of the objects to recognize (synthesis part), and a recognition and pose estimator component (analysis part) capable
of detecting and recognizing objects as well as estimating their exact pose and location. |
|
|
|
|
|
|
