Thesis Details
Výpočet hloubkové mapy ze stereo kamery
This thesis is dedicated to the problem of stereo vision and 3D reconstruction from stereo image. Spatial perception is realized by using depth map, which is created by using disparity map. Main goal of this work is to create an application for estimating object distance from car using methods for depth map estimation. The work also includes description of main steps to achieve goal, like image capturing, stereo camera calibration, image rectification and disparity estimation. The result of this work is an experimental solution for monitoring system used in cars, which focuses on pedestrian detection in front of the car, and calculates its distance by using depth map. Part of this work is also creating test set, which is used for evaluating the accuracy of this system.
Depth map. Disparity map. Stereo camera calibration. Pedestrian detection. C#. EmguCV.
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Strnadel Josef, Ing., Ph.D. (DCSY FIT BUT), člen
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT), člen
@bachelorsthesis{FITBT14888, author = "Daniel Berek", type = "Bachelor's thesis", title = "V\'{y}po\v{c}et hloubkov\'{e} mapy ze stereo kamery", school = "Brno University of Technology, Faculty of Information Technology", year = 2015, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/14888/" }