Back to all available

QStab: A lightweight video stabilization algorithm robust to high-frequency perturbations

algorithms-and-analysis-of-algorithms
artificial-intelligence
computer-vision
multimedia
neural-networks

Abstract

In this study, QStab, a novel real-time video stabilization method is introduced, specifically designed to be robust against high-frequency perturbations commonly encountered near internal combustion engines or other sources of rapid mechanical vibrations. QStab employs a lightweight queue-based mechanism. This method, termed “frame mirroring”, identifies and displays the frame of the buffer exhibiting the minimum mean squared error relative to an adaptively updated reference frame, thus suppressing jitter while maintaining visual continuity. Experimental evaluations on challenging benchmark datasets (SBMNet and NUS) demonstrate that QStab consistently achieves a perfect cropping ratio of 1.0 across all test categories, thereby preserving full-frame content, a key advantage over existing methods. Additionally, it delivers a strong inter-frame transformation fidelity (ITF) score and competitive distortion metrics, confirming both temporal smoothness and geometric consistency. Although its stability score is slightly lower than that of state-of-the-art deep learning methods, the overall performance reflects a well-balanced trade-off between visual quality and computational simplicity. Given its low complexity and real-time execution, QStab is particularly suitable for embedded systems and real-world surveillance applications in vibration-intensive environments. The source code of our proposed method can be found in our GitHub page.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].