In this work an alternative method to classical road survey techniques is presented. Today, a tipical road survey employs a team, that consist of 3 operators at least , and a truemeter mounted on the rear of the vehicle, in order to measure the road travelled along the survey . Furthermore in some areas of interest the survey is stopped and the team makes sketches, on which the required informations are reported. This procedure do not allow to carry out rapid surveys, actually in suburban areas a distance between 2 - 4 Km is covered, every day, and a smaller part in urban areas, where the surveying environment is less uniform. It seems obvious, that in this manner a road survey is time and human resources expensive, and it can affect heavily the final cost of the project (up to 40%). A possible solution of these problems resides in the integration of modern positioning systems, as GPS and INS, with the computer vision technology. In this work we present GEOVISION, a software that implements computer vision algorithms and digital photogrammetric techniques, in order to achieve the 3D position of a feature selected on a pair of digital images . This software consists of two separated, but not indipendent, tools: STEREOCALIB, that deals with the calibration of the left and right cameras system, and EPSEARCH, used for image matching , triangulation computation , 3D feature position deter-mination and measurements on the images between selected features.

Geovision: a digital photogrammetric software for road survey.

GUARNIERI, ALBERTO;VETTORE, ANTONIO
1999

Abstract

In this work an alternative method to classical road survey techniques is presented. Today, a tipical road survey employs a team, that consist of 3 operators at least , and a truemeter mounted on the rear of the vehicle, in order to measure the road travelled along the survey . Furthermore in some areas of interest the survey is stopped and the team makes sketches, on which the required informations are reported. This procedure do not allow to carry out rapid surveys, actually in suburban areas a distance between 2 - 4 Km is covered, every day, and a smaller part in urban areas, where the surveying environment is less uniform. It seems obvious, that in this manner a road survey is time and human resources expensive, and it can affect heavily the final cost of the project (up to 40%). A possible solution of these problems resides in the integration of modern positioning systems, as GPS and INS, with the computer vision technology. In this work we present GEOVISION, a software that implements computer vision algorithms and digital photogrammetric techniques, in order to achieve the 3D position of a feature selected on a pair of digital images . This software consists of two separated, but not indipendent, tools: STEREOCALIB, that deals with the calibration of the left and right cameras system, and EPSEARCH, used for image matching , triangulation computation , 3D feature position deter-mination and measurements on the images between selected features.
Reports of Geodesy, Warsaw University of Technology
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/169549
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact