Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository
Video prediction is essential for recreating absent frames in video sequences while maintaining temporal and spatial coherence. This procedure, known as video inpainting, seeks to reconstruct missing segments by utilizing data from available frames. Frame interpolation, a fundamental component of th...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016125002481 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471810884599808 |
|---|---|
| author | Mohana Priya P UlagaPriya K |
| author_facet | Mohana Priya P UlagaPriya K |
| author_sort | Mohana Priya P |
| collection | DOAJ |
| description | Video prediction is essential for recreating absent frames in video sequences while maintaining temporal and spatial coherence. This procedure, known as video inpainting, seeks to reconstruct missing segments by utilizing data from available frames. Frame interpolation, a fundamental component of this methodology, detects and produces intermediary frames between input sequences. The suggested methodology presents a Bidirectional Video Prediction Network (BVPN) for precisely forecasting absent frames that occur before, after, or between specified input frames. The BVPN framework incorporates temporal aggregation and recurrent propagation to improve forecast accuracy. Temporal aggregation employs a series of reference frames to generate absent content by harnessing existing spatial and temporal data, hence assuring seamless coherence. Recurrent propagation enhances temporal consistency by integrating pertinent information from prior time steps to progressively improve predictions. The timing of frames is constantly controlled through intermediate activations in the BVPN, allowing for accurate synchronization and improved temporal alignment. A fusion module integrates intermediate interpretations to generate cohesive final outputs. Experimental assessments indicate that the suggested method surpasses current state-of-the-art techniques in video inpainting and prediction, attaining enhanced smoothness and precision. Surveillance video datasets demonstrate substantial enhancements in predictive accuracy, highlighting the strength and efficacy of the suggested strategy in practical application. • The proposed method integrates bidirectional video prediction, temporal aggregation, and recurrent propagation to effectively reconstruct missing intermediate video frames with enhanced accuracy. • Comparative analysis using the UCF-Crime dataset demonstrates higher PSNR and SSIM values for the proposed method, indicating improved frame quality and temporal consistency over existing techniques. • This research provides a robust framework for future advancements in video frame prediction, contributing to applications in anomaly detection, surveillance, and video restoration. |
| format | Article |
| id | doaj-art-00ab59a8e3eb4b3ebd56a64447cae5f1 |
| institution | Kabale University |
| issn | 2215-0161 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj-art-00ab59a8e3eb4b3ebd56a64447cae5f12025-08-20T03:24:43ZengElsevierMethodsX2215-01612025-06-011410340210.1016/j.mex.2025.103402Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repositoryMohana Priya P0UlagaPriya K1Corresponding author.; Department of Computer Science & Engineering, Vels Institute of Science, Technology & Advanced Studies(VISTAS), Chennai, IndiaDepartment of Computer Science & Engineering, Vels Institute of Science, Technology & Advanced Studies(VISTAS), Chennai, IndiaVideo prediction is essential for recreating absent frames in video sequences while maintaining temporal and spatial coherence. This procedure, known as video inpainting, seeks to reconstruct missing segments by utilizing data from available frames. Frame interpolation, a fundamental component of this methodology, detects and produces intermediary frames between input sequences. The suggested methodology presents a Bidirectional Video Prediction Network (BVPN) for precisely forecasting absent frames that occur before, after, or between specified input frames. The BVPN framework incorporates temporal aggregation and recurrent propagation to improve forecast accuracy. Temporal aggregation employs a series of reference frames to generate absent content by harnessing existing spatial and temporal data, hence assuring seamless coherence. Recurrent propagation enhances temporal consistency by integrating pertinent information from prior time steps to progressively improve predictions. The timing of frames is constantly controlled through intermediate activations in the BVPN, allowing for accurate synchronization and improved temporal alignment. A fusion module integrates intermediate interpretations to generate cohesive final outputs. Experimental assessments indicate that the suggested method surpasses current state-of-the-art techniques in video inpainting and prediction, attaining enhanced smoothness and precision. Surveillance video datasets demonstrate substantial enhancements in predictive accuracy, highlighting the strength and efficacy of the suggested strategy in practical application. • The proposed method integrates bidirectional video prediction, temporal aggregation, and recurrent propagation to effectively reconstruct missing intermediate video frames with enhanced accuracy. • Comparative analysis using the UCF-Crime dataset demonstrates higher PSNR and SSIM values for the proposed method, indicating improved frame quality and temporal consistency over existing techniques. • This research provides a robust framework for future advancements in video frame prediction, contributing to applications in anomaly detection, surveillance, and video restoration.http://www.sciencedirect.com/science/article/pii/S2215016125002481Bidirectional Video Prediction Network |
| spellingShingle | Mohana Priya P UlagaPriya K Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository MethodsX Bidirectional Video Prediction Network |
| title | Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository |
| title_full | Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository |
| title_fullStr | Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository |
| title_full_unstemmed | Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository |
| title_short | Video prediction based on temporal aggregation and recurrent propagation for surveillance videosThe datasets analysed during the current study are available in the weblink repository |
| title_sort | video prediction based on temporal aggregation and recurrent propagation for surveillance videosthe datasets analysed during the current study are available in the weblink repository |
| topic | Bidirectional Video Prediction Network |
| url | http://www.sciencedirect.com/science/article/pii/S2215016125002481 |
| work_keys_str_mv | AT mohanapriyap videopredictionbasedontemporalaggregationandrecurrentpropagationforsurveillancevideosthedatasetsanalysedduringthecurrentstudyareavailableintheweblinkrepository AT ulagapriyak videopredictionbasedontemporalaggregationandrecurrentpropagationforsurveillancevideosthedatasetsanalysedduringthecurrentstudyareavailableintheweblinkrepository |