3D structural component recognition and modeling method using color and 3D data for construction progress monitoring

Abstract

Construction progress monitoring has been recognized as one of the key elements that lead to the success of a construction project. By performing construction progress monitoring, corrective measures and other appropriate actions can be taken in a timely manner, thereby enabling the actual performance to be as close as possible to the desired outcome even if the construction performance significantly deviates from the original plan. However, current methods of data acquisition and its use in construction progress monitoring have tended to be manual and time consuming. This paper proposes an efficient, automated 3D structural component recognition and modeling method that employs color and 3D data acquired from a stereo vision system for use in construction progress monitoring. An outdoor experiment was performed on an actual construction site to demonstrate the applicability of the method to 3D modeling of such environments, and the results indicate that the proposed method can be beneficial for construction progress monitoring.