SMART SURVEILLANCE SYSTEM WITH FACE RECOGNITION USING OPEN-SOURCE COMPUTER VISION

Abstract

The current project is primarily concerned with ensuring a secure environment and also free from the hold-ups that occur in your surroundings. This automated surveillance system detects intruders using various devices with software. The major software employed in the current work is Open CV (open-source computer vision). The primary method utilized in the present work is if any person appears in front of the pi camera. It will switch on by observing for probable matches that have previously been stored in our database. If the module finds a match, then it continues to record until an intruder comes. If the face is not recognized then the unknown person’s face will be captured and a snapshot will be sent to the user’s email. The device is developed using Raspberry Pi with a 1.4 GHz quad-core processor, a raspberry pi camera with 12MP high-resolution, and a Wireless dongle to communicate with users’ email. For motion detection, most existing systems employ a Passive Infrared (PIR) motion sensor. Despite its inexpensive cost, such a system has some demerits. For example, as a result of an exceptional situation, such as rapid heating induced by sun exposure, false alarms may be triggered. To increase the efficiency of motion detection, a smart surveillance system is constructed using Open CV on a Raspberry Pi 3 Model B. According to the findings, the built smart surveillance security system using Open CV has a detection rate of 96%, whereas the PIR motion sensorbased security system has a detection rate of 76%.