Recovering depth information of objects from two-dimensional images is one of the very\nimportant and basic problems in the field of computer vision. In view of the shortcomings of\nexisting methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature\nTransform) is presented in this paper. The approach can estimate the depths of objects in two images\nwhich are captured by an un-calibrated ordinary monocular camera. In this approach, above all,\nthe first image is captured. All of the camera parameters remain unchanged, and the second image\nis acquired after moving the camera a distance d along the optical axis. Then image segmentation\nand SIFT feature extraction are implemented on the two images separately, and objects in the images\nare matched. Lastly, an object�s depth can be computed by the lengths of a pair of straight line\nsegments. In order to ensure that the most appropriate pair of straight line segments are chosen,\nand also reduce computation, convex hull theory and knowledge of triangle similarity are employed.\nThe experimental results show our approach is effective and practical.
Loading....