Open AccessThe estimation of stereovision precision in road inspection
Author(s) -
Marcin Staniek
Publication year - 2014
Publication title -
budownictwo i architektura
Language(s) - English
Resource type - Journals
eISSN - 1899-0665
pISSN - 2544-3275
DOI - 10.35784/bud-arch.1855
Subject(s) - computer vision , road surface , artificial intelligence , computer science , feature (linguistics) , representation (politics) , engineering , philosophy , linguistics , civil engineering , politics , law , political science
The estimation of stereovision precision in road inspection was determined by the analysis of the distribution of differences between measurements: the stereo vision method and the method of direct measurement with the use of laser distance meter. The carried out analysis is aimed at verifying the type of mapping error of a road surface. The input data was obtained from 160 measurement sections which feature both a different type and a different condition of road pavement.
The estimated method of road inspection is based on the stereo vision method of surface representation. Spatial representation of the road is obtained from the images recorded through taking stereo sequences of images by the measurement vehicle moving along the studied section of the road. The proper analysis of the image-based data and the application of mathematical transformations allow for determination of technical and functional parameters of the road. Spatial description allows for a precise evaluation of the state of a road pavement, which in traditional methods of image processing, without information about the depth, is difficult to be achieved and often burdened with errors of qualification of road distresses.