Efficient computer vision using bio-inspired computing.

Overview

Traditional computer vision (CV) algorithms often require significant computational resources, limiting their applicability in resource-constrained environments like environment monitoring, and defense. To address this, researchers are exploring biologically inspired approaches to enhance energy efficiency and accuracy in CV tasks, e.g. neuromorphic computing.

This project will explore and adapt traditional CV algorithms to brain inspired neuromorphic platforms, for energy efficient and fast processing.

Research engagement

1) Familiarization and setting up of the neuromorphic platform.

2) Research and translation of select CV algorithm to neuromorphic platform.

3) Innovate augmentations to improve performance of CV algorithms (optional).

4) Writing up, publishing and presenting research outcomes.

Outcomes

The project aims to adapt conventional CV algorithms to neuromorphic software-hardware platforms.

Skills and experience

• strong math background
• programming experience (preferably Python) are required.

Start date

1 November, 2024

End date

28 February, 2025

Location

QUT gardens point.

Keywords

• Computer vision
• Neuromorphic computing
• Machine Learning

Contact

Dr. Chayan Banerjee, c.banerjee@qut.edu.au