CREATE NEW SECURITY AND DETECTION METHODS USING DEEP LEARNING ALGORITHM



Authors

  • 1Balaji Babu Pannem 2Dr. Ratna Raju Mukiri 3S. Amarnath Babu

DOI:

https://doi.org/10.15282/jmes.17.1.2023.10.0759


Keywords:

Violence Detection, Deep Learning, Convolution Neural Networks (CNN), CCTV Footage, Weapon Detection, YOLO, Surveillance.


Abstract

As the need for advanced security measures continues to grow in today's dynamic environment, this study addresses the challenge of weapon detection through the implementation of a cutting-edge deep learning model. Recent advancements in machine learning has shown success in the fields of recognition and object detection. Our system utilizes the You Only Look Once (YOLO V3) object detection model The primary aim of this study is to develop robust and accurate models for the automated detection of violent activities in CCTV footage. The system relies on processing a video feed to detect people carrying different types of weapons by periodically capturing images from the video feed. These images are fed to a convolution neural network (CNN). The CNN then decides if the image contains a threat or not. Security and personal properties, needs and deployment of video surveillance systems can recognize and interpret the scene and anomaly events play a vital role in intelligence monitoring weapon detection using SSD and Faster RCNN algorithms. The system's architecture is designed around convolutional neural networks (CNNs) and various deep learning models that are trained on large-scale weapon image datasets. Moreover detecting weapons or other dangerous materials and preventing harm or risk to human life could be accomplished by integrating this system into sophisticated surveillance and security robots. Additionally the incorporation of AI techniques enables us to provide insights into the decision-making process of these models, enhancing transparency and interpretability. We aim to identify the most suitable model architecture and feature set for accurately detecting violence in diverse real-world scenarios.



Published

2024-06-30

How to Cite