Abstract: A new method of recovering 3D human motion from monocular videos is presented.First,extracted silhouettes are analyzed to derive 2D positions of spine and end sites.Then,3D poses are recovered by optimizing an object function that encodes the correspondence between the analyzed silhouettes and a pose-parameterized 3D human skeleton.In order to reduce the computational complexity,an effective and computationally efficient object function is devised.A novel iterative optimization process that exploits the human skeleton structure is also proposed to boost the optimization.In addition,we present a new strategy to recover pose sequence that is free from error accumulation.Experimental results show that complex motions of a large variety of types can be recovered by the proposed method.