The Figure 8 shows the 3D points that are generated from
the input the matrix of 2D stereo-image points. After this
process, the surface reconstruction or texture mapping
technique [5] is applied as shown in Figure 9.
This study attempt to reconstruction the 3D mountain’s
surface from the triple Fuji’s mountain images. Then
MATLAB and C programming are used to develop system. In
feature points detection, by using SIFT, the matched points all
of rescale and full scale images are the same number of
matched points. Compare the result of accuracy of
correspondent matched points, the SITF appropriate more than
Harris corner detector. The detected feature points of Fuji’s
mountain are covered the entire surface but it could be not
detected on the edge of mountain.