Artificial Microsaccade Compensation: Stable Vision for an Ornithopter

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Burner, Levi, de Croon, Guido, Aloimonos, Yiannis
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909942013755392
author Burner, Levi
de Croon, Guido
Aloimonos, Yiannis
author_facet Burner, Levi
de Croon, Guido
Aloimonos, Yiannis
contents Animals with foveated vision, including humans, experience microsaccades, small, rapid eye movements that they are not aware of. Inspired by this phenomenon, we develop a method for "Artificial Microsaccade Compensation". It can stabilize video captured by a tailless ornithopter that has resisted attempts to use camera-based sensing because it shakes at 12-20 Hz. Our approach minimizes changes in image intensity by optimizing over 3D rotation represented in SO(3). This results in a stabilized video, computed in real time, suitable for human viewing, and free from distortion. When adapted to hold a fixed viewing orientation, up to occasional saccades, it can dramatically reduce inter-frame motion while also benefiting from an efficient recursive update. When compared to Adobe Premier Pro's warp stabilizer, which is widely regarded as the best commercial video stabilization software available, our method achieves higher quality results while also running in real time.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03995
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Artificial Microsaccade Compensation: Stable Vision for an Ornithopter
Burner, Levi
de Croon, Guido
Aloimonos, Yiannis
Robotics
Computer Vision and Pattern Recognition
Animals with foveated vision, including humans, experience microsaccades, small, rapid eye movements that they are not aware of. Inspired by this phenomenon, we develop a method for "Artificial Microsaccade Compensation". It can stabilize video captured by a tailless ornithopter that has resisted attempts to use camera-based sensing because it shakes at 12-20 Hz. Our approach minimizes changes in image intensity by optimizing over 3D rotation represented in SO(3). This results in a stabilized video, computed in real time, suitable for human viewing, and free from distortion. When adapted to hold a fixed viewing orientation, up to occasional saccades, it can dramatically reduce inter-frame motion while also benefiting from an efficient recursive update. When compared to Adobe Premier Pro's warp stabilizer, which is widely regarded as the best commercial video stabilization software available, our method achieves higher quality results while also running in real time.
title Artificial Microsaccade Compensation: Stable Vision for an Ornithopter
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.03995