An IoT based House Intruder Detection and Alert System using Histogram of Oriented Gradients

This research aims to design and implement a home security system with human detection capability. Traditional home security systems, i.e., Closed-Circuit Television (CCTV) can only capture and record videos without the ability of giving warning feedback if there is any suspicious object. Therefore, an additional object detection and warning method is required. The proposed design is implemented using Raspberry Pi 3 and Arduino, that is connected by USB cable. The PIR sensor is installed on Arduino and webcam is mounted on Raspberry Pi 3. The Raspberry Pi 3 is used to process inputs from sensors and process images for human detection. 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 Oriented Gradients (HOG) and Support Vector Machine (SVM) to detect the suspicious object. If the suspicious object is detected, then the alarm is activated and sends an email to warn the house owner about the existence of the intruder. The results show that it takes on average 2 seconds for the proposed system to detect an intruder and that the system can successfully detect the intruder with accuracy of 90%.