Advanced home security: detecting unusual movements using the single shot detector technique

Abstract

As area surveillance technology, the camera is still suboptimal because it cannot detect suspicious human movement and there is no real-time security alert. Although motion detection is implemented, it is only activated when a person passes the PIR sensor, triggering the camera to capture the object. Due to its lengthy process, it is less effective. This study aims to develop a home surveillance system that uses object detection technology to detect unusual human movements. The system is also equipped with real-time early warning through a Telegram Messenger application. The system is then tested using various parameters that may impact the precision of detection results, including object poses, camera height, and camera distance. The system can detect objects that make unusual movements in 69 images or 57.5% of the tests, based on the analysis of 120 test data. Through the integration of object detection technology and real-time Telegram-based alerts, this home surveillance system significantly demonstrates the capability to accurately identify suspicious human motions thereby enhancing area surveillance effectiveness and adaptability to various environmental conditions.

Keywords

• computer vision
• early warning
• movement detection
• single shot detector