Three dimensional (3D) shape reconstruction that aims to reconstruct 3D surface of objects
using acquired images, is one of the main problems in computer vision. There are many
applications of 3D shape reconstruction, from satellite imaging to material sciences, considering
a continent on earth or microscopic surface properties of a material. One of these
applications is the automated firearm identification that is an old, yet an unsolved problem in
forensic science. Firearm evidence matching algorithms rely on the fact that a firearm creates
characteristic marks on surfaces of the bullets and the cartridge cases. These marks should
be digitized unaffected from different surface material properties of evidences. Accuracy of
3D shape is one of the most important parameters affecting the overall identification performance.
A very high resolution, accurate 3D data have to be reconstructed in the order of
minutes. Photometric stereo (PS) method is capable of reconstructing high resolution surfaces
in a fast manner. But, the metallic material and the surface topology of the firearm evidences
generate highlights and shadows on their images that does not comply with the assumptions
of conventional PS. In the scope of this work, it is intended to design an accurate, fast and
robust 3D shape reconstruction scheme using PS considering highlights and shadows. These
new PS procedures to be developed here should not be limited only to the ballistic evidences
but they also could be used for a wider range of objects reflection properties and texture. For
this purpose, masked PS methods which are quite fast when compared to other approaches,
were classified and implemented. Simple additional masking methods are also proposed. A
novel weighted PS method, using weighted least square estimation, is presented to eliminate
false edges created by the masks. Concurrently, the calibration processes and the illumination
configuration were improved. The disturbances due to close light sources were removed
by image calibrations. From experimental tests to simulate the light positioning problem, it
is concluded that the double zenith illumination configuration have better performance than
the optimal single zenith illumination configuration, when the highlights and the shadows are
considered. Double zenith illumination configuration results were further improved by the
weighted normal PS with a small additional computation cost. All the implemented methods
were tested firstly on the controlled environment using synthetic images. Later the same tests
were conducted on real objects with varying characteristics as well as the firearm evidences.
| Identifer | oai:union.ndltd.org:METU/oai:etd.lib.metu.edu.tr:http://etd.lib.metu.edu.tr/upload/12613749/index.pdf |
| Date | 01 September 2011 |
| Creators | Buyukatalay, Soner |
| Contributors | Halici, Ugur |
| Publisher | METU |
| Source Sets | Middle East Technical Univ. |
| Language | English |
| Detected Language | English |
| Type | Ph.D. Thesis |
| Format | text/pdf |
| Rights | To liberate the content for public access |
Page generated in 0.232 seconds