An Experimental Study of Facial Recognition Performance for Real-Time UAV Surveillance in Urban Environments

Abstract

In today’s era, facial recognition is common in every aspect of life whether in smartphones, security, attendance management, healthcare, and law enforcement. Modern facial recognition uses a state-of-the-art camera mounted on each device, but we need to integrate it at a certain height for security purposes. To solve this problem, this article proposes real-time facial recognition through drone imaging for urban safety and surveillance. In this article, the Unmanned Aerial Vehicle is equipped with sensors and is allowed to fly in urban locations and capture images to find the suspected one through the image processing technique Convolutional Neural Networks (CNNs). In this research, performances of three facial recognition systems, Local Binary Pattern Histogram (LBPH), FaceNet, and Face_Recognition systems have been presented for Frames Per Second, Accuracy, and real-time tracking. A comparative analysis of the proposed work is also presented to validate the work where a minimum confidence threshold of 80% is achieved.