Convolutional Neural Network (CNN) Model to Mobile Remote Surveillance System for Home Security

Abstract

Every citizen wants to eliminate any potential threat to themselves or their belongings. A proper and modern surveillance system is necessary given the enormous increase in the security needs of both persons and organizations. Remote surveillance is one of the major issues which attracted the attention of researchers recently. Surveillance cameras, commonly known as closed-circuit television (CCTV) have grown rapidly in popularity over the last few decades. Nowadays, video surveillance is quite essential. It greatly aids in reducing crime rates and can be used to keep track of the condition of buildings. In this paper, a remote surveillance system using the Convolutional Neural Networks (CNN) model was proposed. This system consists of a camera that takes more than one image of the object that passes in front of it and sends these images to the mobile phone of the intended person (the owner of the place). Images taken by the security camera may be analyzed using the CNN model depending on the region of interest for detection. The system will be delivering an alarm to the user depending on intelligent detection depending on a deep learning approach that can improve a smart home automation structure by detection people. The results of the experiments demonstrate a high degree of accuracy in detecting human beings, the accuracy of the system reached 100% in an ideal time.