Optical flow estimation using the Fisher–Rao metric. Issue 2 (8th November 2021)

• Record Type: Journal Article
• Authors: Maybank, Stephen J; Ieng, Sio-Hoi; Migliore, Davide; Benosman, Ryad
• Is Part Of: Neuromorphic computing and engineering. Volume 1:Issue 2(2021)
• Publication Date: 2021-11-08
• Subjects: address event representation -- AER -- asynchronous image sensor -- event camera -- Fisher–Rao metric -- Kullback–Leibler divergence -- optical flow; Neural networks (Computer science) -- Periodicals; Neural computers -- Periodicals; Neuromorphics -- Periodicals; 006.3
• DOI: 10.1088/2634-4386/ac2bed
• Languages: English
• ISSNs: 2634-4386

Abstract

Abstract: The optical flow in an event camera is estimated using measurements in the address event representation (AER). Each measurement consists of a pixel address and the time at which a change in the pixel value equalled a given fixed threshold. The measurements in a small region of the pixel array and within a given window in time are approximated by a probability distribution defined on a finite set. The distributions obtained in this way form a three dimensional family parameterized by the pixel addresses and by time. Each parameter value has an associated Fisher–Rao matrix obtained from the Fisher–Rao metric for the parameterized family of distributions. The optical flow vector at a given pixel and at a given time is obtained from the eigenvector of the associated Fisher–Rao matrix with the least eigenvalue. The Fisher–Rao algorithm for estimating optical flow is tested on eight datasets, of which six have ground truth optical flow. It is shown that the Fisher–Rao algorithm performs well in comparison with two state of the art algorithms for estimating optical flow from AER measurements.