Monocular Distance Estimated Based on PTZ Camera

This paper introduces an intelligent computational approach for extracting salient objects from images and estimating their distance information with PTZ (Pan-Tilt-Zoom) cameras. PTZ cameras have found wide applications in numerous public places, serving various purposes such as public security management, natural disaster monitoring, and crisis alarms, particularly with the rapid development of Artificial Intelligence and global infrastructural projects. In this paper, we combine Gauss optical principles with the PTZ camera's capabilities of horizontal and pitch rotation, as well as optical zoom, to estimate the distance of the object. We present a novel monocular object distance estimation model based on the Focal Length-Target Pixel Size (FLTPS) relationship, achieving an accuracy rate of over 95% for objects within a 5 km range. The salient object extraction is achieved through a simplified convolution kernel and the utilization of the object's RGB features, which offer significantly faster computing speeds compared to Convolutional Neural Networks (CNNs). Additionally, we introduce the dark channel before the fog removal algorithm, resulting in a 20 dB increase in image definition, which significantly benefits distance estimation. Our system offers the advantages of stability and low device load, making it an asset for public security affairs and providing a reference point for future developments in surveillance hardware.