<title>Rapid target tracking algorithm using Gabor representation of target signature and Lie derivatives</title>

Deformable target tracking method based on Lie algebra

“…while the traditional approaches [5][6][7][8]12,13] Advantages of this replace will be discussed in Sec3. 3.…”

“…We also analyze essence of motion parameters, and optimize parameters directly on the manifold, which can be determined by exponential mapping between a Lie group and its Lie algebra. We compare this method to traditional algorithms [5,6,[12][13] ; experimental results demonstrate that Lie algebra method outperforms other classic algorithms in efficiency, stabilization and accuracy.…”

“…Taylor and Kriegman [11] proposed minimization techniques based on successive parameterization of Lie groups in an unpublished technical report, but they provided neither theory analysis nor simulation results. Tsao and Wen [12,13 ] have recently proposed a tracking algorithm based on Lie derivatives. It is similar to the work of Hager [5], but explains affine transformation using Lie group, and replaces Jacobian images with Lie derivative.…”

“…Conventional correlation-based trackers [1,2] use either a region's gray information or edges and other features as the target signatures, but it is difficult to solve the problem of object region deformation in the tracking. Over the last 10 years, numerous approaches [3][4][5][6][7][8][12][13] have been proposed to address this problem. One classic method treats tracking as a nonlinear optimization: Hager and Belhumeur [5] developed geometric parameter models for the image motions of points within a target region，where the best parameters are estimated through minimizing the sum of squared differences (SSD) between a reference template and a region of the image.…”