Blob Feature Extraction for Event Detection Cameras

Author

Joseph Naim Raffoul, University of Dayton

Date of Award

2020

Degree Name

M.S. in Electrical Engineering

Department

Department of Electrical and Computer Engineering

Advisor/Chair

Advisor: Keigo Hirakawa

Abstract

Neuromorphic (a.k.a. event detection) cameras emerged out of biologically inspired visual perception. A key component of neuromorphic cameras is the dynamic vision sensor or DVS, which generates an asynchronous data stream reporting temporal log-intensity changes (or "events") of the pixel-sized photodiodes. In this thesis a novel blob feature extraction technique for neuromorphic cameras is proposed. Using asynchronous 3D distance transform, we are able to track a blob, describe its size/shape/orientation, efficiently match the feature descriptors, and perform image correspondence across multiple neuromorphic cameras.

Keywords

Electrical Engineering

Rights Statement

Copyright © 2020, author

Recommended Citation

Raffoul, Joseph Naim, "Blob Feature Extraction for Event Detection Cameras" (2020). Graduate Theses and Dissertations. 6708.
https://ecommons.udayton.edu/graduate_theses/6708