Barnea, S., Dept. of Transportation and Geo-information, Technion - Israel Institute of Technology, Haifa, 32000, Israel
Filin, S., Dept. of Transportation and Geo-information, Technion - Israel Institute of Technology, Haifa, 32000, Israel
Alchanatis, V., Volcani Center ARO, Inst. Of Agricultural Engineering, Bet-Dagan, 50250, Israel

Finding transformations between 3D point clouds is a challenging task as it requires handling huge datasets, irregular point distribution, multiple views, and relatively low textured surfaces. Common approaches for the registration are based in large on the iterative closest point (ICP) algorithm, which is non-linear and requires good initial values to secure convergence to the actual solution. Computing the approximations requires extracting distinct features, devising methods for matching them among the datasets, and then computing the initial transformation parameters to launch the ICP algorithm. In this paper we present a computational approach for the registration problem. In essence we exploit 3D rigid-body transformation invariant features to reduce significantly the computational load involved in the matching between key features. Generally, with the partial overlap among datasets and among the extracted features the identification of corresponding key features can be viewed as subgraph matching problem. This problem is hard to solve, but as the actual matched entities are subjected to a six parameters transformation it becomes manageable. We show that distances, which are invariant to rigid body transformation, are optimal features to apply for solving this problem. We then show that by using selected key points, we can optimize the matching process. Following the presentation of our algorithm, demonstrate its application on a sequence of scans taken in an area featuring a clutter of objects, results and the analysis show its efficiency and robustness.