CCTV Footage Summarization for Increasing Efficiency in Surveillance (using ML)


Authors : Lishika Goel; Rachna Jain

Volume/Issue : Volume 10 - 2025, Issue 4 - April


Google Scholar : https://tinyurl.com/3jh9szk7

Scribd : https://tinyurl.com/4ujmtyx5

DOI : https://doi.org/10.38124/ijisrt/25apr1554

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.


Abstract : Surveillance cameras are ubiquitous in this era of the future. Whether a house, office, shopping complex, or highway, CCTV cameras are ubiquitous that monitor the activities on a day-to-day basis. Surveillance is a significant activity. They help in identifying any suspicious activity and serve as effective evidence. Yet, the quantity of video recording is huge. Useful information it holds most of the time is extremely minimal. It then becomes an extremely challenging task to sift through such many hours of video to pick out useful information. Storage space for the videos is also wasted on a vast scale. So, there's a need perceived for surveillance products that can make such long recordings into short ones without losing essential events. Our system can condense hours of video recorded by CCTV cameras into a single clip that displays all interesting events at once. All moving objects in the video are detected and tracked by our software. These events are overlaid on one clip, and the timestamps for each event are also displayed, thereby allowing the user to conduct surveillance for multiple events. Our model employs the KNN model for background subtraction and video extract in addition to a special Object Tracking algorithm to identify moving objects that are overlapped on the extracted background.

Keywords : Video summarization, Surveillance, KNN, Object Tracking algorithm, Multi-video summarization, Deep learning.

References :

[1]. Hussain, T., Wang, Y., & Liu, Y. (2021). A comprehensive survey on multi-view video summarization: IEEE Transactions on Multimedia, 23(1), 40-56.  

[2] Wang, Z., Zhang, H., & Liu, Y. (2022). A survey of deep learning-based video summarization methods. ACM Computing Surveys (CSUR), 55(1), 1-37.

[3].Zhang, H., Wang, Y., & Liu, Y. (2022). A survey on video summarization for intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 23(1), 5772.

[4] Wang, Y., Zhang, H., & Liu, Y. (2022). A survey on video summarization for socially aware applications ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 18(3), 1-34.

[5] Zhang, H., Wang, Y., & Liu, Y. (2022). A survey on multi-task video summarization.

[6].  Zhang, Y., Wang, Y., & Liu, Y. (2023). A survey on video summarization for event detection.

[7].Wang, X., Zhang, H., & Liu, Y. (2023). A survey on video summarization for visual question answering.

[8]. A. Ghosh and V. Ramanathan (2023). Video summarization using deep learning techniques: A survey”, Multimedia Tools and Applications , 2023, pp. 1-26.

[9]."Video Summarization Using Deep Neural Networks: A Survey" by Evlampios Apostolidis, Eleni Adamantidou, Alexandros I. Metsai, Vasileios Mezaris, and Ioannis Patras

[10]. Y. Wang, H. Feng, Z. Chen, X. Hu, and J. Wu, "Video summarization using deep reinforcement learning," Applied Sciences, vol. 22, no. 19, p. 7689, 2022.

[11]. A. Khan, S. Ullah, M. A. Khan, M. A. Khan, and A. Khan, "Video summarization techniques: A review," *International Journal of Multimedia and Information Retrieval*, vol. 8, no. 2, pp. 103-114, 2019.

[12].A. Ghosh and V. Ramanathan, "An effective video summarization framework based on the object of interest using deep learning," Multimedia Processing and Enhancement, vol. 2022, p. 7453744, 2022.

[13]. F. Sultana, A. Sufian, and P. Dutta, "A Review of YOLO Algorithm Developments," Procedia Computer Science, vol. 185, pp. 141-148, 2022.

[14].Y. Liu, J. Wang, Y. Yang, and Y. Zhang, "Object Detection Using YOLO: A Review," Applied Sciences, vol. 12, no. 23, p. 13644, 2022.

[15].Y. Wang, H. Feng, Z. Chen, X. Hu, and J. Wu, "Unsupervised video summarization using deep reinforcement learning," Applied Sciences, vol. 23, no. 7, p. 3384, 2023.

[16].Y. Wang, H. Feng, Z. Chen, X. Hu, and J. Wu, "Unsupervised video summarization using deep reinforcement learning with interpolation," Applied Sciences, vol. 23, no. 7, p. 3384, 2023.

[17].P. Kadam, D. Vora, S. Mishra, and S. Patil, "Recent Challenges and Opportunities in Video Summarization With Machine Learning Algorithms," IEEE Access, vol. 10, pp. 1-15, 2022.

[18]. Kamath, A., S, B., Westbenson, K. L., Sharma, S., & Sinam, N. (2021). Summarization of CCTV Videos using KNN Classifier.Journal of Emerging Technologies and Innovative Research (JETIR).

[19]Wang, Y., Wang, L., & Lu, H. (2021). A Novel Key-Frames Selection Framework for Comprehensive Video Summarization. IEEE Transactions on Multimedia, 23(3), 838-850.

[20].Zhang, J., Li, Y., & Gao, W. (2021). DSNet: A Flexible Detect-to-Summarize Network for Video Summarization. IEEE Transactions on Image Processing, 30(2), 948-962.

Surveillance cameras are ubiquitous in this era of the future. Whether a house, office, shopping complex, or highway, CCTV cameras are ubiquitous that monitor the activities on a day-to-day basis. Surveillance is a significant activity. They help in identifying any suspicious activity and serve as effective evidence. Yet, the quantity of video recording is huge. Useful information it holds most of the time is extremely minimal. It then becomes an extremely challenging task to sift through such many hours of video to pick out useful information. Storage space for the videos is also wasted on a vast scale. So, there's a need perceived for surveillance products that can make such long recordings into short ones without losing essential events. Our system can condense hours of video recorded by CCTV cameras into a single clip that displays all interesting events at once. All moving objects in the video are detected and tracked by our software. These events are overlaid on one clip, and the timestamps for each event are also displayed, thereby allowing the user to conduct surveillance for multiple events. Our model employs the KNN model for background subtraction and video extract in addition to a special Object Tracking algorithm to identify moving objects that are overlapped on the extracted background.

Keywords : Video summarization, Surveillance, KNN, Object Tracking algorithm, Multi-video summarization, Deep learning.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe