3D Recognition by Parts: A Complete Solution using Parameterized Volumetric Models
Dı́bio Leandro Borges · 1996
This paper presents a complete solution to the problem of recognizing 3D objects, using shape information extracted from range images, and parameterized volumetric models. The domain of the geomet- ric shapes explored is that of complex curved objects with articulated parts, and a great deal of similarity between some of the parts. In model-based object recognition three main issues constrain the design of a complete solution: representation, feature extraction, and interpretation. We have developed an integrated approach that addresses these three issues in the context of the above mentioned domain of objects. The so- lution is presented here describing the main modules and how they relate to each other. Results are shown for a variety of real image data acquired in our lab.