Tracking Moving Target Using Active Drift Correction Algorithm
基于主动漂移矫正的运动目标跟踪算法

For the traditional problem of non-compatibility between the robustness and the efficiency of affine image alignment algorithm, we propose a new fast and robust affine image alignment algorithm called ADC (active drift correction) for tracking the visual moving target. The basic idea of our method is: By incorporating a drift correction term into the traditional goal energy function, the new algorithm has the natural ability of anti-drift, which then, therefore, can boost the performance of robustness. Many extra techniques (typically as passive drift correction) in traditional methods for high robustness are no longer necessary in our algorithm. The experimental results show that our algorithm is simple and efficient. It can attain a higher performance of robustness than the traditional methods without compromise with the complexity or real time performance of the algorithm.