Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition strategies for 3-D objects in occluded environments
Traditional and non-traditional robotic sensors
From Uncertainty to Visual Exploration
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Superquadrics for Segmenting and Modeling Range Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Segmentation and recovery of superquadrics: computational imaging and vision
Segmentation and recovery of superquadrics: computational imaging and vision
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
| Hi-index | 0.01 |
Fast robotic unloading of piled deformable box-like objects (e.g. box-like sacks), is undoubtedly of great importance to the industry. Existing systems although fast, can only deal with layered, neatly placed configurations of such objects. In this paper we discuss an approach which deals with both neatly placed and jumbled configurations of objects. We use a time of flight laser sensor mounted on the hand of a robot for data acquisition. Target objects are modeled with globally deformed superquadrics. Object vertices are detected and superquadric seeds are placed at these vertices. Seed refinement via region growing results in accurate object recovery. Our system exhibits a plethora of advantages the most important of which its speed. Experiments demonstrate that our system can be used for object unloading in real time, when a multi-processor computer is employed.