Multi-Resolution Depth Estimation Using Modified Census Transform for Advanced Driver Assistance Systems Loghman, Maziar Mesmakhosroshahi, Maral Kim, Joohee A computer-implemented depth estimation method based on non-parametric Census transform with adaptive window patterns and semi-global optimization. A modified cross-based cost aggregation technique adaptively creates the shape of the cross for each pixel distinctly. In addition, a depth refinement algorithm fills holes within the estimated depth map using the surrounding background depth pixels and sharpens the object boundaries by exerting a trilateral filter to the generated depth map. The trilateral filter uses the curvature of pixels as well as texture and depth information to sharpen the edges. Sponsorship: Illinois Institute of Technology United States Patent 2018-01-04 2017-09-05 Patent application/pdf islandora:9885 9,754,377 http://hdl.handle.net/10560/4195 en CC0 1.0 Universal http://creativecommons.org/publicdomain/zero/1.0/ No Copyright - United States http://rightsstatements.org/page/NoC-US/1.0/ Open Access