Robust infrared target tracking based on particle filter with embedded saliency detection

Infrared target tracking has attracted extensive research efforts in recent years. However, effective and efficient infrared target tracking is still a hard problem due to the low signal-to-noise ratio, difficulty of robustly describing complicated appearance variations as well as the abrupt motion of targets. In this paper, we propose a tracking method under the Particle Filtering framework by using a hierarchical sampling method, in which two complementary appearance models are used. Firstly, a saliency appearance model is proposed to suppress the cluttered background and properly guide particles to appropriate states. Then the eigen space model is employed as the other observation method to accurately estimate the target state. The hierarchical sampling process is proposed to incorporate the two complementary observation models to account for the abrupt motion efficiently. Experimental results on AMCOM FLIR sequences and comparisons with the state-of-the-art methods demonstrate that the proposed method is robust to appearance changes as well as drastic abrupt motions.