Non-line-of-sight target tracking with improved recurrent extreme learning machine

Abstract

Target tracking provides important location-based services in many applications. The main challenge of target tracking is to combat the severe degradation problem in Non-Line-of-Sight (NLOS) scenario. Most Deep Learning algorithms available in literature to address this issue belong to batch learning with high complexity. This paper proposes a novel online sequential learning algorithm, Improved Recurrent Extreme Learning Machine (IRELM), to solve the NLOS target tracking problem as a position series prediction task. IRELM is able to train Recurrent Neural Network (RNN) inputs one-by-one and adaptively update the input weight, hidden weight, feedback weight and output weight. Extensive simulations and experiments prove the superior tracking performance and feasible complexity of IRELM over the state-of-the-art Deep Learning methods.