Object Detection and Tracking Turret based on Cascade Classifiers and Single Shot Detectors

Abstract

The involvement of embedded systems and computer vision is increasing day by day in various segments of consumer market like industrial automation, traffic monitoring, medical imaging, modern appliance market, augmented reality systems, etc. These technologies are bound to make new developments in the domain of commercial and home security surveillance. Our project aims to make contributions to the domain of video surveillance by making use of embedded computer vision systems. Our implementation, built around the Raspberry Pi 4 SBC aims to utilize computer vision techniques like motion detection, face recognition, object detection, etc to segment the region of interest from the captured video footage. This technique is superior as compared to traditional surveillance systems as it requires minimum human interaction and intervention at the control room of such security systems. The proposed system is capable of sensing suspicious events like detection of an unknown face in the captured video or motion detection/object detection in a closed section of a building. Moreover, with the help of the turret mechanism built using servo motors, the camera integrated in the system is capable of having 360◦ rotation and can track a detected face or object of interest within its range. Apart from automated tracking, the system can also be manually controlled by the operator.