基于主动漂移矫正的运动目标跟踪算法

针对传统的图像仿射配准(Affine image alignment, AIA)算法无法有效兼顾算法效率和鲁棒性的问题, 提出了一种快速鲁棒的新仿射配准算法---主动漂移矫正(Active drift correction, ADC)算法用于跟踪视频运动目标. 该算法的基本思想是: 通过引入一个漂移矫正项, 来改进传统算法的目标能量函数, 使算法具备抗漂移的能力, 从而提高算法的鲁棒性. 改进后的算法不需要传统算法中为增强鲁棒性而采用的许多复杂措施(如: 被动漂移矫正). 实验结果表明: 本文提出的算法简单、有效, 在不必牺牲算法效率和复杂度的条件下, 可以获得比传统算法更好的鲁棒性.

Tracking Moving Target Using Active Drift Correction Algorithm

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.