A Cognitive Radar for Classification of Resident Space Objects (RSO) operating on Polarimetric Retina Vision Sensors and Deep Learning

Nowak, Martin A.; Tzikas, Alexandros E.; Giakos, G.C.; Beninati, Anthony; Douard, Nicolas; Lanzi, Joe; Lanzi, Natalie; Hussain, Ridwan; Wang, Yi; Shrestha, Suman; Bolakis, Christos

doi:10.1109/ist48021.2019.9010272

Cited by 5 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new class of sensors aimed to identify target motion classification, namely, the 'Polarimetric Dynamic Vision Sensor p(DVS)s', has been introduced by Giakos and co-workers [4][5][6]. p(DVS) sensors were introduced aiming at further enhancement of the local spatial-temporal contrast and dynamic range of the DVS imaging sensors due to the polarization of light intrinsic characteristics.…”

Section: Introductionmentioning

confidence: 99%

Polarimetric dynamic vision sensor p(DVS) neural network architecture for motion classification

Nowak

Beninati

Douard

et al. 2021

Electronics Letters

Self Cite

View full text Add to dashboard Cite

The purpose of this study is to introduce efficient bio-inspired vision architectures, integrating human cognition capabilities, such as computation and memory emulating neurons and synapses, together with polarization of light properties, that would ultimately revolutionize and give rise to the next-generation highly efficient augmented intelligence vision systems. The system consists of a polarimetric dynamic vision sensor) and a spinning wheel, whose motion is externally modulated and controlled by means of a signal generator, varying its motion pattern and speed, respectively. A neural network has been designed to classify different object speeds and motion patterns. The neural network utilizes a limited number of events within a given time window, instead of fullframe images; as well as two classifiers, which practically take a single input and independently classify both its speed and motion pattern. As a result, both high computational efficiency and motion classification accuracy are achieved.

show abstract

Section: Introductionmentioning

confidence: 99%