Registration errors between the physical world and computergenerated objects are a central problem in Augmented Reality (AR) systems. Some existing AR systems have demonstrated ho...
— A planning method for knotting/unknotting and tightening manipulation of deformable linear objects is proposed. It is important for linear object manipulation in industrial/med...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
This paper presents a new algorithm for video-object segmentation, which combines motion-based segmentation, high-level object-model detection, and spatial segmentation into a sin...
Dirk Farin, Peter H. N. de With, Wolfgang Effelsbe...
We propose a novel scheme for using supervised learning for function-based classification of objects in 3D images. During the learning process, a generic multi-level hierarchical ...