Design of Smart Home Security System using Object Recognition and PIR Sensor

摘要

This research aims to design and implement a home security system with the capability for human detection. The traditional home security system, i.e. closed circuit television (CCTV) can only capture and record the video without able to give warning feedback if there is any suspicious object. Therefore, an additional object detection and warning method is required if there is an intruder. The proposed design is implemented using Raspberry Pi 3 and Arduino, which are connected by USB cable. The PIR sensor is installed on the Arduino and the webcam is mounted on Raspberry Pi 3. The Raspberry Pi 3 is used to process inputs from received sensors and process images for human detection. The PIR sensor detects the movement around the sensor to activate the webcam to capture a picture. Then, the object recognition is performed using histogram of gradient (HoG) and support vector machine (SVM) to detect the suspicious object. If the suspicious object is detected, then alarm is activated to warn the house owner about the existence of intruder. The evaluation results show that it takes in average 2 seconds for proposed system to detect the intruder. It also shows that the system can successfully detects the intruder with accuracy of 89%.