从动态图像序列中恢复非刚性物体的3D运动和结构是计算机视觉领域中重要的研究内容之一.之前大多算法都假设摄像机是仿射摄像机模型,但是这种假设在目标距相机很近时会变得无效和产生较大的重建误差.通过线性递归估计法将非刚体的因式分解从弱透视投影模型扩展到一般透视投影模型,并在线性递归估计过程中使用遗传算法(GA)对迭代因子进行优化.实验结果表明提出的方法具有很高的准确性.
This paper extendes the non-rigid factorization from weak perspective projection model to the general perspective projection model by the linear recursive estimation algorithm.During the linear recursive estimation process,we utilize the genetic algorithm to optimize iterative coefficient.Experimental results show that the proposed method has high accuracy.