Local Quadrics Surface Approximation for Real-Time Tracking of Textureless 3D Rigid Curved Objects

This paper addresses the problem of tracking textureless rigid curved objects. A common approach uses polygonal meshes to represent curved objects and use them inside an edge-based tracking system. However, in order to accurately recover their shape, high quality meshes are required, creating a trade-off between computational efficiency and tracking accuracy. To solve this issue, we suggest the use of quadrics for each patch in the mesh to give local approximations of the object shape. The novelty of our research lies in using curves that represent the quadrics projection in the current viewpoint for distance evaluation instead of using the standard method which compares edges from mesh and detected edges in the video image. This representation allows to considerably reduce the level of detail of the polygonal mesh and led us to the development of a novel method for evaluating the distance between projected and detected features. The experiments results show the comparison between our approach and the traditional method using sparse and dense meshes. They are presented using both synthetic and real image data.