Object tracking in infrared image sequence by Monte-Carlo method

This paper presents a robust tracking algorithm for infrared objects in the image sequence, which is based on particle filer. Particle filter is a powerful tool for tracking especially in non-Gaussian condition, but the selection of samples is still a challenging problem. According to the frame-to-frame correlation, two basic assumptions are proposed. Borrowing the idea from Sequence Importance Sampling, Monte-Carlo method will be applied to solve the well-known shortcomings of Particle filter in this paper. Technologically, the proposed algorithm could also track multiple objects successfully. The experimental result has demonstrated its feasibility and validity.