Silva L., Bellon O.R.P., Boyer K.L. Robust Range Image Registration using Genetic Algorithms and the Surface

Издательство World Scientific, 2006, -175 pp.The book addresses the range image registration problem for automatic 3D model construction. We focus on obtaining highly precise alignments between different view pairs of the same object to avoid 3D model distortions. In contrast to most prior work, the view pairs may exhibit relatively little overlap and need not be prealigned. To this end, we define a novel effective evaluation metric for registration, the Surface Interpenetration Measure (SIM). This measure quantifies the interleaving of two surfaces as their alignment is refined, putting the qualitative evaluation of splotchiness, often used in reference to renderings of the aligned surfaces, onto a solid mathematical footing. The SIM is shown to be superior to mean squared error (i.e. more sensitive to fine scale changes) in controlling the final stages of the alignment process.
We then combine the SIM with Genetic Algorithms (GAs) to develop a robust approach for range image registration. The results confirm that this technique achieves precise surface registration with no need for prealignment, as opposed to methods based on the Iterative Closest Point (ICP) algorithm, the most popular to date. We present thorough experimental results, including an extensive comparative study and propose enhanced GA-based approaches to improve the registration still further. Additionally, we develop a global multiview registration technique using our GA-based approach. The results show considerable promise in terms of accuracy for 3D modeling.Range Image Registration
Surface Interpenetration Measure (SIM)
Range Image Registration using Genetic Algorithms
Robust Range Registration by Combining GAs and the SIM
Multiview Range Image Registration
Closing Comments