Stereoscopic 3D images have depth perception as one of characteristics differ from conventional 2D images. Therefore, the conventional 2D oriented visual attention model cannot be directly applied to stereoscopic 3D images. In addition, visual fatigue is considered as another 3D related characteristics when viewing stereoscopic 3D images. In this paper, we propose a novel 3D visual attention model that combines bottom-up and top-down methods which considers comfortable viewing. The proposed model is based on 2D oriented features extracted from the image : intensity, colour, local orientation information, and the detection of human representation. Then, this model is combined with depth information obtained by considering the comfortable viewing. The experimental results show that the proposed model increase the simulation efficiency of visual characteristics of human visual system.