Automatic reconstruction of unknown 3-D objects is a main part of the machine vision technology and it has a variety of applications such as robot navigation, medical imaging and industrial inspection, etc. In this paper, a new view planning method for reconstructing unknown 3-D models automatically was proposed based on the limit visual surface. Firstly, the visual region of the laser-vision system was obtained. And the limit visual surface was modeled by means of the known boundary data obtained from initial view and was used to predict the unknown object surface information. Then the next viewpoint visibility was determined according to the visual region of the system and the visible area of next viewpoint was obtained. Finally, the position which can obtain the maximum visible area was selected as the next best view position. The experimental results of the real models showed that the method is effective in practical implementation.