Intelligent Repair Method for Archival Videos Based on the Super-SloMo Technology
-
Hui Li
Abstract
Due to equipment limitations in the early shooting of video files, and the damage and aging in the later file storage process, some historic video materials in video archives can easily suffer from defects such as poor action coherence. This paper proposes an intelligent enhanced repair method for archival videos. The method first obtains the frame rate of the input video, then calculates the dynamic coefficient of the video according to the frame rate and duration number, uses the artificial intelligence algorithm Super-SloMo technology to fix the problematic digital video to the required frame rate, improves the video's dynamic coefficient, and finally achieves the purpose of getting the enhanced repaired digital copies of the original video materials from video archives. This paper also proposes an intelligent enhanced repair prototype system based on the method. The experiment shows that the enhanced repair effect is effective and improves the clarity and coherence of the video. Users get more coherent copies of historic video materials. This solves the problem of the poor perception caused by the loss of frames, preserves the original information, and makes the information obtained from archival videos intuitive.
Zusammenfassung
Schlechte Aufnahmebedingungen sowie Schäden durch mechanische Einwirkungen oder Materialveränderungen bei der Lagerung können die Qualität von historischem Videomaterial vermindern. In diesem Beitrag wird eine Methode zur Verbesserung solcher archivierter Videos vorgestellt. Dabei wird zunächst die Bildrate des Eingangsvideos ermittelt und dann der Dynamikkoeffizient des Videos entsprechend der Bildrate und der Dauer berechnet. Dabei wird der Algorithmus der künstlichen Intelligenz Super-SloMo-Technologie verwendet, um das digitale Video auf die erforderliche Bildrate einzustellen und den Videodynamikkoeffizienten zu verbessern. Die derart optimierte digitale Kopie wird schließlich archiviert. Darüber hinaus diskutiert der Beitrag auch ein verbessertes System zur Reparatur des Prototyps, das auf dieser Methode basiert. Das Experiment zeigt, dass die Methode sowohl Klarheit als auch Kohärenz des Videos verbessert und Benutzerinnen und Benutzer visuell einheitliche Kopien von historischem Videomaterial erhalten. Dies löst das Problem der durch den Verlust von Einzelbildern verursachten gestörten Wahrnehmung, bewahrt die ursprünglichen Informationen und macht die aus archivierten Videos gewonnenen Informationen intuitiv erfahrbar.
References
Huaizu, J., D. Sun, V. Jampani, M. H. Yang, E. Learned-Miller, and J. Kautz. 2018. “Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation.” Computer Vision and Pattern Recognition 35 (2): 9000–8.Suche in Google Scholar
Jianming, Z. 2022. “Application of Super-resolution Reconstruction Technology Based on AI Deep Learning in Image Archive Restoration.” China Archives 852 (11): 36–7.Suche in Google Scholar
Meifang, L. 2022. “Innovation and Practice of Audio and Video Archives Management Mode – Take Guangzhou National Archives as an Example.” Chinese Archives 842 (1): 40–1.Suche in Google Scholar
National Technical Committee for the Standardization of Archival Work. 2017. “Specification for Digitization of Audio-Visual Records (DA/T 62-2017).” Compilation of Standards for Archival Work 1 (11): 77–97.Suche in Google Scholar
Ruiyu, Z., and L. Yunbo. 1993. “Digital Method – a New Method to Repair Audio and Video Archives.” Lantai World 81 (9): 18.Suche in Google Scholar
Shanshan, L., W. Minmin, and L. Xin. 2022. “Digital Intelligence Enables Audio and Video File Repair: The Real Need, the Inevitable Policy.” Archival Communications 263 (5): 93–100.Suche in Google Scholar
Xin, S., and L. Guoxuan. 2022. “Construction of Intelligent Archives: Dilemma Identification and Action Framework.” Beijing Archives 449 (7): 11–4.Suche in Google Scholar
Xuanzhe, Z. 2022. “Analysis of the Intelligent Annotation Application of Digital Audio and Image Archives.” Beijing Archives 451 (9): 32–4.Suche in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Original Work
- Some Practical Aspects of Nanocellulose Film: Characterization, Expansion and Shrinking Tests, and Techniques to Create Remoistenable Nanocellulose
- Technical Note
- Hidden Players: Small Paper Nails—Manufacture and Application of Paper Nails in Chinese Double-Leaved Books
- Original Works
- Barriers to Preservation for Digital Information Resources in University Libraries of Pakistan
- Intelligent Repair Method for Archival Videos Based on the Super-SloMo Technology
Artikel in diesem Heft
- Frontmatter
- Original Work
- Some Practical Aspects of Nanocellulose Film: Characterization, Expansion and Shrinking Tests, and Techniques to Create Remoistenable Nanocellulose
- Technical Note
- Hidden Players: Small Paper Nails—Manufacture and Application of Paper Nails in Chinese Double-Leaved Books
- Original Works
- Barriers to Preservation for Digital Information Resources in University Libraries of Pakistan
- Intelligent Repair Method for Archival Videos Based on the Super-SloMo Technology
