Learning Visual Object Detection and Localisation Using icVision

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)


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.

Actions (login required)

View Item View Item