View in EDS

Robust Kalman filtering for dynamic reconstruction of multiple missing frames in videos.

Saved in:
Bibliographic Details
Title: Robust Kalman filtering for dynamic reconstruction of multiple missing frames in videos.
Authors: Gupta, Sumit1 (AUTHOR) Sumitgupta2@bhu.ac.in, Kumar, Awadhesh2 (AUTHOR) akmcsmmv@bhu.ac.in
Source: Imaging Science Journal. Mar2026, Vol. 74 Issue 2, p147-163. 17p.
Subjects: Kalman filtering, Video processing, Image processing, Statistical accuracy, Estimation theory
Abstract: In modern video-based monitoring systems, video frame analysis has gained significant attention due to its critical applications in medical imaging, traffic surveillance, manufacturing, and security. Continuous video capture and analysis are important for safety and efficiency. This study proposes a Kalman filter-based method to estimate multiple missing frames in videos. Since missing frames may appear at different points in the sequence, proper reconstruction is required to maintain continuity. To overcome the limitations of single-frame estimation methods, this paper presents a Kalman filter-based reconstruction approach that estimates missing frames by integrating information from preceding and subsequent frames in a pixel-wise manner. Experiments were carried out on three publicly available video datasets: UCF101, Sintel, and a traffic dataset. The proposed method achieved better or comparable results with RMSE(4.994) and DSSSIM(0.062) in UCF101, PSNR(32.07 dB) and SSSIM(0.9719) in Sintel, and MSE(13.92), PSNR(28.36), SSIM(0.95), CC(0.96) in traffic dataset as compared to other existing work. [ABSTRACT FROM AUTHOR]
Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:In modern video-based monitoring systems, video frame analysis has gained significant attention due to its critical applications in medical imaging, traffic surveillance, manufacturing, and security. Continuous video capture and analysis are important for safety and efficiency. This study proposes a Kalman filter-based method to estimate multiple missing frames in videos. Since missing frames may appear at different points in the sequence, proper reconstruction is required to maintain continuity. To overcome the limitations of single-frame estimation methods, this paper presents a Kalman filter-based reconstruction approach that estimates missing frames by integrating information from preceding and subsequent frames in a pixel-wise manner. Experiments were carried out on three publicly available video datasets: UCF101, Sintel, and a traffic dataset. The proposed method achieved better or comparable results with RMSE(4.994) and DSSSIM(0.062) in UCF101, PSNR(32.07 dB) and SSSIM(0.9719) in Sintel, and MSE(13.92), PSNR(28.36), SSIM(0.95), CC(0.96) in traffic dataset as compared to other existing work. [ABSTRACT FROM AUTHOR]
ISSN:13682199
DOI:10.1080/13682199.2025.2572924