运动轨迹估计算法在关键人物自动捕获中的应用

Application of Trajectory Estimation Algorithm in the Automatic Capture of Key Figures

关键人物与背景区域的颜色过于接近,造成二者的颜色差异不明显。传统算法是基于相邻图像灰度差值进行关键人物捕获的,无法避免由于关键人物与背景区域颜色差异过小造成的颜色差异不明显的缺陷,降低了关键人物自动捕获的精度。为了解决上述问题,提出了一种基于运动轨迹估计算法的关键人物自动捕获方法,即提取关键人物特征参数,预测关键人物运动轨迹,从而完成关键人物的自动捕获。实验证明,这种算法提高了关键人物自动捕获的准确率,取得了令人满意的效果。

Because the color of the key figures and the background area is too close, the color difference between the both is not obvious. The traditional algorithm is based on the different date of the gray scale of adjacent images to catch the key figures and it can＇t avoid the defects in which the color difference is not obvious bacause the color difference be- tween the key figures and the background area is too small, so it will reduce the precision in which the key character is captured automatically. A method based on the trajectory estimation algorithm for automatic acquisition of key figures was proposed in this paper to solve the above problem. The method extracts the characteristic parameters of the key fig- ures, and predicts the critical movement trajectory of the key figures to complete the automatic capture of key figures. The experiments show that this algorithm enhances the accurate rate of key figures automation capture, and gets a satis- factory result.