Integration of imaging and simulation for earthmoving productivity analysis

Earthwork productivity varies depending on a unique geologic condition, types of earthwork equipment, and an equipment allocation plan. For this reason, it is difficult to accurately estimate the productivity of an earthwork. To address this issue, this paper develops an imaging-to-simulation method in which a real jobsite data is automatically collected and used for analyzing the earthwork productivity. Object existence and its location in image data are identified by convolutional networks, and they are used to infer the earthwork context. The context information is transformed into the simulation input by the context reasoning processes. A productivity report is produced by using the WebCYCLONE simulation. The developed method was tested in a tunnel construction site, providing a new equipment allocation plan, which minimize the cost and time compared with the original plan.