The invention relates to the field of
engineering auditing, in particular to a construction
project engineering management auditing doubtful point extraction method based on three-dimensional point clouds, which comprises the following steps: step 1, constructing and forming an auditing data
resource pool based on a BIM model as a main body; 2, placing the two types of non-homologous data in the same coordinate
system; 3, associating geometric data of the BIM model with
project management information; 4, pre-training the
laser point cloud semantic segmentation model, and accurately identifying key components in the actually measured
point cloud in the auditing stage; and step 5,
processing the
point cloud data, identifying key
engineering components, performing
geographic space matching and fusion on identification results and BIM model component point cloud, calculating and comparing geometric feature differences of the key components, and completing doubtful point detection. By introducing an advanced three-dimensional point cloud and
machine learning technology, an efficient, accurate and intelligent construction
project engineering management auditing doubtful point extraction method is provided, and powerful
technical support is provided for
engineering management and auditing work.