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

It is one of very important and basic problem in compute vision field that recovering depth information of objects from two-dimensional images. In view of the shortcomings of existing methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature Transform) is presented in this paper. The approach can estimate the depths of objects in two images which are captured by an un-calibrated ordinary monocular camera. In this approach, above all, the first image is captured. All of the camera parameters remain unchanged, and the second image is acquired after moving the camera a distance d along the optical axis. Then image segmentation and SIFT feature extraction are implemented on the two images separately, and objects in the images are matched. Lastly, an object depth can be computed by the lengths of a pair of straight line segments. In order to ensure that the best appropriate a pair of straight line segments are chose and reduce the computation, the theory of convex hull and the knowledge of triangle similarity are employed. The experimental results show our approach is effective and practical.

Recovering the depth information from a single image is a fundamental problem in computer vision field and has broad application prospects. To solve the problem that the accuracy of the depth recovered from a single image is not high enough, especially when there are several edges very close or intersecting, or when the edge is weak, a novel method to depth measurement is proposed in this article. Four steps are included in our method. Firstly, we obtain depth value of object edge point indirectly by measuring the defocusing degree of the object edge point. The gradient information of the 8 directions of edge point are employed during the process of measuring. Secondly, wavelet analysis is used to judge whether the measured depth value needs to be corrected or not. If necessary, it is corrected according to our formula. A sparse depth map is got when the depth values of all of edge points are measured and are corrected if necessary. Thirdly, the joint bilateral filter is employed to refine the sparse depth map. Lastly, the sparse depth map is extended to a dense depth map by the method of Matting Laplacian. The results of experiments show our method is effective.