先端研の研究領域

研究事例

PLAUSIBLE RECONSTRUCTION OF AN APPROXIMATED MESH MODEL FOR NEXT-BEST VIEW PLANNING OF SFM-MVS

Structure-from-Motion (SfM) and Multi-View Stereo (MVS) are widely used methods in three dimensional (3D) model reconstructionfor an infrastructure maintenance purpose. However, if a set of images is not captured from well-placed positions, the final dense modelcan contain low-quality regions. Since MVS requires a much longer processing time than SfM as larger amounts of images are provided,it is impossible for surveyors to wait for the SfM–MVS process to complete and evaluate the geometric quality of a final dense modelon-site. This challenge results in response inefficiency and the deterioration of dense models in 3D model reconstruction. If the qualityof the final dense model can be predicted immediately after SfM, it will be possible to revalidate the images much earlier and to obtainthe dense model with better quality than the existing SfM–MVS process. Therefore, we propose a method for reconstructing a moreplausible 3D mesh model that accurately approximates the geometry of the final dense model only from sparse point clouds generatedfrom SfM. This approximated mesh model can be generated using Delaunay triangulation for the sparse point clouds and triangle aswell as tetrahedron filtering. The approximated model can be used to predict the geometric quality of the final dense model and for anoptimization-based view planning. Some experimental results showed that our method is effective in predicting the quality of the finaldense model and finding the potentially degraded regions. Moreover, it was confirmed that the average reconstruction errors of thedense model generated by the optimization-based view planning went below tens of millimeters and falls within an acceptable rangefor an infrastructure maintenance purpose.