Learning visual object detection and localisation using icVision

Jürgen Leitner, Simon Harding, Pramod Chandrashekhariah, Mikhail Frank, Alexander Förster, Jochen Triesch, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

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. © 2013 Elsevier B.V.
Original languageEnglish (US)
Title of host publicationBiologically Inspired Cognitive Architectures
PublisherElsevier B.V.
Pages29-41
Number of pages13
DOIs
StatePublished - Jan 1 2013
Externally publishedYes

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Experimental and Cognitive Psychology
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learning visual object detection and localisation using icVision'. Together they form a unique fingerprint.

Cite this