Depth Calculation using Computer Vision and Sift

Abstract

Robotics has been developed in a high level in the past few years, especially in mobile Robotics. Its main contribution is shown in human entertainment and performance in dangerous works. However, those are not just the only applications they perform. There is a wide field to be developed. Distance calculation is something really important for localization and navigation of mobile robots. The classic way to calculate distances are using sonar and laser radar. But, the use of computer vision in stereo, based on two cameras, is widespread in Robotics. Therefore, algorithms, to detect new points, allows the creation of new methods to execute stereo vision. In those algorithms there is one that has been used, the SIFT (scale-invariant feature transform). It may be used with classic algorithms of stereo vision in the Computer Vision 3D system development. This project’s objective is to develop a distance acquisition system using computer vision in stereo with the help of SIFT method. The results are very close with what we were expecting. The next steps to be done are the execution of quantitative tests to determinate the focal distance of the utilized cameras and to calibrate the system.