Automatic Traffic Video Summarization for Indian Roads using Yolo
International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)
DOI: 10.15662/ijeetr.2026.0802047 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von Mr. K. Venkatesan und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Traffic surveillance systems generate a massive amount of video data on a daily basis, especially on Indian roads where traffic conditions are highly dynamic and complex due to heterogeneous vehicles, unpredictable pedestrian movement, and frequent rule violations. Manually monitoring and analyzing these long-duration traffic videos is time-consuming, inefficient, and prone to human error, making it difficult for authorities to extract meaningful insights in real time. Existing systems primarily focus on simple recording or basic motion detection and lack the ability to automatically identify and summarize important traffic events such as congestion, accidents, and violations. To address these limitations, the proposed system introduces an automated traffic video summarization framework using a hybrid YOLOv8 and Convolutional Neural Network (CNN) approach. YOLOv8 is employed for real-time object detection and localization of vehicles, pedestrians, and other road users, generating bounding boxes and confidence scores, while the CNN model extracts deep spatial and temporal features to analyze motion patterns and identify significant events across video frames. The system processes continuous traffic video input, extracts relevant frames, tracks detected objects, and selects key events based on predefined criteria to generate concise and informative video summaries. This approach reduces data redundancy, minimizes storage requirements, and enhances the efficiency of traffic monitoring systems. Experimental results demonstrate improved accuracy, faster processing, and reliable detection of critical traffic events, making the system suitable for real-world deployment in smart traffic management and surveillance applications. Overall, the proposed framework provides an efficient, scalable, and automated solution for transforming lengthy traffic videos into meaningful summaries, supporting better decision-making and improved road safety
Zitieren
APA
Venkatesan, M. K., Hariprasath, M. R., Thakur, M. D. K., & Balaguru, M. M. (2026). Automatic Traffic Video Summarization for Indian Roads using Yolo. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802047
Vancouver
Venkatesan MK, Hariprasath MR, Thakur MDK, Balaguru MM. Automatic Traffic Video Summarization for Indian Roads using Yolo. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802047
BibTeX
@article{Venkatesan2026,
author = {Venkatesan, Mr. K. and Hariprasath, Mr. R. and Thakur, Mr. Dhiraj Kumar and Balaguru, Mr. M.},
title = {Automatic Traffic Video Summarization for Indian Roads using Yolo},
journal = {International Journal of Engineering & Extended Technologies Research},
year = {2026},
volume = {08},
number = {02},
doi = {10.15662/ijeetr.2026.0802047}
}
EUVIMED