Leitner, Juergen and Harding, Simon and Chandrashekhariah, Pramod and Frank, Mikhail Alexander and Foerster, Alexander Uwe and Triesch, Jochen and Schmidhuber, Juergen (2013) Learning Visual Object Detection and Localisation Using icVision. Biologically Inspired Cognitive Architectures, 5. 29 - 41. ISSN 2212-683X
Full text not available from this repository. (Request a copy)Abstract
Building artificial agents and robots that can act in an intelligent way is one of the main research goals in artificial intelligence and robotics. Yet it is still hard to integrate functional cognitive processes into these systems. We present a framework combining computer vision and machine learning for the learning of object recognition in humanoid robots. A biologically inspired, bottom-up architecture is introduced to facilitate visual perception and cognitive robotics research. It aims to mimic processes in the human brain performing visual cognition tasks. A number of experiments with this icVision framework are described. We showcase both detection and identification in the image plane (2D), using machine learning. In addition we show how a biologically inspired attention mechanism allows for fully autonomous learning of visual object representations. Furthermore localising the detected objects in 3D space is presented, which in turn can be used to create a model of the environment.
| Item Type: | Scientific journal article, Newspaper article or Magazine article |
|---|---|
| Uncontrolled Keywords: | Humanoid robots; Computer vision; Perception; Cognition; Learning; Object detection |
| Subjects: | Engineering > Electronic & electrical engineering > Robotics & cybernetics > Robotics Computer sciences > Artificial intelligence Computer sciences > Artificial intelligence > Computer vision |
| Department/unit: | Dipartimento tecnologie innovative > Istituto Dalle Molle di studi sull'intelligenza artificiale |
| Depositing User: | Juergen Leitner |
| Date Deposited: | 14 Mar 2014 07:49 |
| Last Modified: | 19 May 2016 12:38 |
| URI: | http://repository.supsi.ch/id/eprint/4258 |
Actions (login required)
 |
View Item |