CAJ | 학술논문

　　针对目标跟踪问题中目标和场景动态变化的问题，提出了一种结合尺度不变特征变换（SIFT）和光流估计算法并改进模板更新策略的目标跟踪算法。SIFT特征是一种局部特征，具有尺度和旋转不变性。光流场反映的是一种全局特征，表示像素点强度的变化。SIFT特征点可以很好地满足光流估计的条件。实验结果表明这种改进后的目标跟踪算法能应用于部分遮挡的情况，并且相对于传统光流法具有更高的精确度。
　　침대목표근종문제중목표화장경동태변화적문제，제출료일충결합척도불변특정변환（SIFT）화광류고계산법병개진모판경신책략적목표근종산법。SIFT특정시일충국부특정，구유척도화선전불변성。광류장반영적시일충전국특정，표시상소점강도적변화。SIFT특정점가이흔호지만족광류고계적조건。실험결과표명저충개진후적목표근종산법능응용우부분차당적정황，병차상대우전통광류법구유경고적정학도。
This paper presents an object tracking algorithm that combines the optical flow estimation algorithm and the Scale In-variant Feature Transform(SIFT)with a new template update strategy for the change of scene and object. The SIFT feature is lo-cal feature which is invariant to the scale and rotation change of the image. The optical flow is a velocity field and the whole fea-ture which represents the change of intensity of the pixel. The SIFT feature satisfies the condition of the optical flow estimation method. The experimental results show that this improved method can be used in partial covering tracking, and can achieve more accurate tracking than the traditional method.