Active drift correction template tracking algorithm

Baojie Fan, Yingkui Du, Yang Cong, Yandong Tang

Abstract: This paper presents a novel active drift correction template tracking algorithm. Compared to Matthews' algorithm in [8], the proposed algorithm achieves synchronously object tracking and drift correction, and save half running time. For the template drift problem during long sequential object tracking, we introduce the active drift correction term into inverse compositional affine image alignment algorithm. This operation can avoid the template drift before it occurs, or reduce the drift after it happens. The total energy function consists of two terms: the tracking term and the active drift correction term. By minimizing the total energy function with the steepest descent algorithm, the proposed algorithm can decrease the accumulative tracking error, and prevent the drift during the tracking process effectively. Various object tracking experiments show that our method has super performance than the passive drift correction algorithm in [8].