Some Enhancement of Aerial and Terrestrial Photo for 3D Modeling of Texture-Less Object Surface

Today, the combination of Aerial and Terrestrial photos has been more
implemented for 3D modelling purposes. This 3D modelling technique getting
popular because it is supporting with photogrammetry structure from motion algorithm (SFM). The SFM algorithm makes automation in the processing step. One of
the main problems that will occur in the automation of 3D modelling objects with
the SFM algorithm is whether objects have texture-less surfaces. The purpose of
this research is to evaluate some enhancement processes that were applied before
running the SFM algorithm for 3D modelling. Some pre-processing enhancements
are a combination Contrast-Limited Adaptive Histogram Equalization (CLAHE)
from Fiji-ImageJ and JPEG to RAW Ai artefact algorithm from Topaz Labs. Two
sample objects are tested which are a heritage object that has a texture-less wall
surface object and a paddy field that has a similar object pattern. Some aerial and
terrestrial photos have been enhanced before processing in 3D modelling. The result
shows that applying preprocessing enhancement can improve the completeness of
the object, especially in texture-less wall surface area. Pre-processing enhancement
improves the geometric accuracy and number of vertex and surfaces also. In the
future, the combination of the Jpeg to Raw Ai and the CLAHE enhancement should
be explored for the best 3D model solution.