Measurement of Absolute Depth of the Objects in Images Based on SURF Feature

A method of depth measurement based on SURF without camera calibration and parameter adjustment is presented in this paper. In this method, two images of a same scene are captured by a monocular camera. Then the objects in the two images are matched automatically after the images have been segmented and SURF (Speeded Up Robust Features) points have been extracted from the images respectively. Finally, a pair of straight line segments in the matched objects is chose and depth of the object is calculated according to the lengths of the pair of straight line segments. The results of the experiments show the method is effective.