Genetic algorithms for 3D reconstruction with supershapes
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
BADGr-A toolbox for box-based approximation, decomposition and GRasping
Robotics and Autonomous Systems
| Hi-index | 0.00 |
Automatic unloading of piled box-like objects is undoubtedlyof great importance to the industry. In this contributiona system addressing this problem is described: Weemploy a laser range finder for data acquisition, and globallydeformable Superquadrics [2], [22] for object modeling.Our technique is based on a hypothesis generation andrefinement scheme. The vertices of the piled objects are extractedand Superquadric seeds are aligned at these vertices.The model parameter recovery task is decomposedinto two subproblems, each dealing with a subset of themodel's parameter set. Both region and boundary based informationsources are used for parameter estimation. Comparedto a widespread strategy for superquadric recovery[11], our method shows advantages in terms of robustnessand computational efficiency. In addition, our system exhibitsversatility with regard to existing industrial systems,since it can effectively deal with both neatly placed and jumbledconfigurations of objects