Home / Current Issue / Paper 1717054
Real-Time Intelligent Action-Based Surveillance System
Subject area: Science,Engineering and Technology · Area of research: Computer Vision
DOI: https://doi.org/10.64388/IREV9I10-1717054
Abstract
Video surveillance systems play an important role in maintaining safety and security in public and private areas. However, traditional CCTV systems continuously record video without analysing activities in real time, which leads to large storage usage and delayed identification of abnormal events. To solve this problem, this paper presents a Real-Time Intelligent Action-Based Surveillance System using a custom trained YOLOv8 model to detect and classify human activities as normal or abnormal. The system highlights normal activities with green bounding boxes and abnormal activities with red bounding boxes, and automatically sends email alerts with captured images when suspicious behaviour is detected. In addition, the system records video only when activity is present, which helps in reducing unnecessary storage usage. The proposed system is implemented with a web interface for live monitoring and alert management. Experimental results show that the system achieves good detection accuracy while improving storage efficiency, making it suitable for real-time smart surveillance applications.
Keywords
YOLOv8, Human Activity Recognition, Anomaly Detection, Automated Alert System, Smart Surveillance, Event- Triggered Recording, Real-Time Detection, Abnormal Activity.
How to cite this paper
@article{1717054,
author = {Sai Kumar Yaradesi, Chittineni Suneetha, Tarun Sai Vallabhuni},
title = {Real-Time Intelligent Action-Based Surveillance System},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {3702-3707},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717054.pdf},
abstract = {Video surveillance systems play an important role in maintaining safety and security in public and private areas. However, traditional CCTV systems continuously record video without analysing activities in real time, which leads to large storage usage and delayed identification of abnormal events. To solve this problem, this paper presents a Real-Time Intelligent Action-Based Surveillance System using a custom trained YOLOv8 model to detect and classify human activities as normal or abnormal. The system highlights normal activities with green bounding boxes and abnormal activities with red bounding boxes, and automatically sends email alerts with captured images when suspicious behaviour is detected. In addition, the system records video only when activity is present, which helps in reducing unnecessary storage usage. The proposed system is implemented with a web interface for live monitoring and alert management. Experimental results show that the system achieves good detection accuracy while improving storage efficiency, making it suitable for real-time smart surveillance applications.},
keywords = {YOLOv8, Human Activity Recognition, Anomaly Detection, Automated Alert System, Smart Surveillance, Event- Triggered Recording, Real-Time Detection, Abnormal Activity.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1717054}
}