| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
Lucas Paletta and Gerhard Paar
ABSTRACT
Visual object recognition using single cue information has been successfully applied in various tasks, in particular for near range. While robust classification and probabilistic representation enhance 2D pattern recognition performance, they are 'per se' restricted due to the limited information content of single cues. The contribution of this work is to demonstrate performance improvement using multi-cue information integrated within a probabilistic framework. 2D and 3D visual information naturally complement one another, each information source providing evidence for the occurrence of the object of interest. We demonstrate preliminary work describing Bayesian decision fusion for object detection and illustrate the method by robust recognition of traffic infrastructure. |
|
| Site generated on Friday, 06 January 2006
|