Embedded Neuromorphic Vision for Humanoid Robots
Abstract
We are developing an embedded vision system for the humanoid robot iCub, inspired by the biology of the mammalian visual system, including concepts such as stimulus-driven, asynchronous signal sensing and processing. It comprises stimulus-driven sensors, a dedicated embedded processor and an event-based software infrastructure for processing visual stimuli. These components are integrated with the existing standard machine vision modules currently implemented on the robot, in a configuration that exploits the best features of both: the high resolution, color, frame-based vision and the neuromorphic low redundancy, wide dynamic range and high temporal resolution event-based sensors. This approach seeks to combine various styles of vision hardware with sensorimotor systems to complement and extend the current state-of-the art.
Cite
Text
Bartolozzi et al. "Embedded Neuromorphic Vision for Humanoid Robots." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981834Markdown
[Bartolozzi et al. "Embedded Neuromorphic Vision for Humanoid Robots." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/bartolozzi2011cvprw-embedded/) doi:10.1109/CVPRW.2011.5981834BibTeX
@inproceedings{bartolozzi2011cvprw-embedded,
title = {{Embedded Neuromorphic Vision for Humanoid Robots}},
author = {Bartolozzi, Chiara and Rea, Francesco and Clercq, Charles and Hofstätter, Michael and Fasnacht, Daniel Bernhard and Indiveri, Giacomo and Metta, Giorgio},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2011},
pages = {129-135},
doi = {10.1109/CVPRW.2011.5981834},
url = {https://mlanthology.org/cvprw/2011/bartolozzi2011cvprw-embedded/}
}