Space Target Motion Salient Classification using Polarimetric Retina Vision Sensing Principles

A new remote sensing retina vision system aimed at classifying rapid moving objects, such as Space debris, based on their motion patterns, is presented. The purpose of this study is to investigate how different types of target complex motion patterns can be detected and discriminated with high accuracy. The remote retina vision sensing system consists of an asynchronous event-based neuromorphic camera coupled with polarization filters enabling improved detection, tracking, and discrimination, with high contrast and dynamic range; a spinning light modulating wheel, operating at varying angular frequency, is placed in front of a static target. The outcome of this study indicates that deep learning combined with Polarimetric Dynamic Vision Sensor p(DVS) principles is well suited to accurately classify targets based on distinct salient features, such as motion patterns, rapidly, at low operational bandwidth, low-power consumption, and storage.