Depth map estimation using modified Census transform and semi-global matching
Maziar Loghman, Kwanghoon Chung, Yun‐Sik Lee, Joohee Kim · 2014
Generating a dense disparity image is one of the essential prerequisite for many applications such as rendering virtual views, 3D scene reconstruction, and advanced driver assistance systems (ADAS). In this paper, a depth estimation technique is proposed which is based on non-parametric Census transform and semi-global optimization. Simulation results indicate that the proposed method fulfills the aims of the algorithm by enhancing the quality of the estimated depth maps and reducing the computational complexity.