Description

This Ph.D. dissertation seeks to contribute to developing a bio-inspired event-camera system for ego-motion estimation, which can be later employed in visual localization and mapping for mobile robotic systems. Event cameras are naturally suitable for motion-relevant tasks such as optical flow estimation or ego-motion estimation, which forms the basis of tracking and SLAM in the computer vision and robotics community. Spiking Neural Network (SNN) is the ideal candidate for event-based camera. This dissertation aims to exploit the advantage of event-camera and bio-inspired visual motion processing methods. The expected results may provide insights for efficient computational vision motion perception systems.

The work is under the scope of the following projects:

• EB-SLAM: Event-based simultaneous localization and mapping (web)
• MINNA: Módulos de posicionado preciso para manipulación aérea (web)