Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active learning for vision-based robot grasping
Machine Learning - Special issue on robot learning
Superquadrics for Segmenting and Modeling Range Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast and Globally Convergent Pose Estimation from Video Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic generation of GRBF networks for visual learning
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparison of Affine Region Detectors
International Journal of Computer Vision
Superquadrics and Angle-Preserving Transformations
IEEE Computer Graphics and Applications
| Hi-index | 0.00 |
Combining visual shape-capturing and vision-based object manipulation without intermediate manual interaction steps is important for autonomic robotic systems. In this work we introduce the concept of such a vision system closing the chain of shape-capturing, detecting and tracking. Therefore, we combine a laser range sensor for the first two steps and a monocular camera for the tracking step. Convex shaped objects in everyday cluttered and occluded scenes can automatically be re-detected and tracked, which is suitable for automated visual servoing or robotic grasping tasks. The separation of shape and appearance information allows different environmental and illumination conditions for shape-capturing and tracking. The paper describes the framework and its components of visual shape-capturing, fast 3D object detection and robust tracking. Experiments show the feasibility of the concept.