Aerial Infrared Target Tracking in Complex Background Based on Combined Tracking and Detecting

Abstract

Aerial infrared target tracking is the basis of many weapon systems, especially the air-to-air missile. Till now, it is still challenging research to track the aircraft in the event of complex background. In this paper, we focus on developing an algorithm that could track the aircraft fast and accurately based on infrared image sequence. We proposed a framework composed of a tracker T based on correlation filter and a detector D based on deep learning, which we call combined tracking and detecting (CTAD). With such collaboration, the algorithm enjoys both the high efficiency provided by correlation filter and the strong discriminative power provided by deep learning. Finally, we performed experiments on three representative infrared image sequences and two sequences from VOT-TIR2016 dataset to quantitatively evaluate the performance of our algorithm. To evaluate our algorithm scientifically, we present the experiments performed on two sequences from AMCOM FLIR dataset of the proposed algorithm. The experimental results demonstrate that our algorithm could track the infrared target reliably, which shows comparable performance with the deep tracker, while running at a fast speed of about 18.1 fps.