A Review Paper on Stereo Vision Based Depth Estimation

Stereo vision is a challenging problem and it is a wide research topic in computer vision. It has got a lot of attraction because it is a cost efficient way in place of using costly sensors. Stereo vision has found a great importance in many fields and applications in today’s world. Some of the applications include robotics, 3-D scanning, 3-D reconstruction, driver assistance systems, forensics, 3-D tracking etc. The main challenge of stereo vision is to generate accurate disparity map. Stereo vision algorithms usually perform four steps: first, matching cost computation; second, cost aggregation; third, disparity computation or optimization; and fourth, disparity refinement. Stereo matching problems are also discussed. A large number of algorithms have been developed for stereo vision. But characterization of their performance has achieved less attraction. This paper gives a brief overview of the existing stereo vision algorithms. After evaluating the papers we can say that focus has been on cost aggregation and multi-step refinement process. Segment-based methods have also attracted attention due to their good performance. Also, using improved filter for cost aggregation in stereo matching achieves better results.