No abstract

No abstract

Abstract. This paper proposes a technique for tracking a superquadricmodelled object over a monocular video sequences. The object is currently modelled with a single superquadric. Object's position and orientation in the first frame of the sequence are assumed known. A frame in a sequence is first processed to find object's contour. Contour is determined by extracting edges on the frame in the vicinity of model's contour from the previous frame. The model's relative translation and rotation parameters are then calculated by fitting model's contour to the frame's contour. This fitting is achieved by minimizing the cost function, which is based on model to image mapping.

This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using an interpretation tree, the presence of an object in the scene from the model database can be hypothesized. These hypotheses are verified by projecting and refitting the object model to the range image which at the same time enables a better localization of the object in the scene.

Abstract. This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using an interpretation tree, the presence of an object in the scene from the model database can be hypothesized. These hypotheses are verified by projecting and re-fitting the object model to the range image which at the same time enables a better localization of the object in the scene.