Long range thermal image object recognition for perimeter security

Nowadays, the field of long-range thermal image processing is increasingly popular. Although this technology has several advantages in terms of security and monitoring, there are not enough autonomous algorithms for processing these images. In this paper, we aim to address two of the main problems in this field: lack of long-range thermal databases and shortage of autonomous monitoring systems. Firstly, we are introducing a new proprietary database with long-range thermal images. Further, we present a thermal detection algorithm, capable of running on real-time monitoring systems. This algorithm is based on a general-purpose DNN (Deep Neural Network) object detector - the YOLO (You Only Look Once) model. Thus, with minimal computing and hardware resources, this article aims to bring a plus in the field of long-range thermal Image processing.