Generic object recognition using form and function
Generic object recognition using form and function
Three-Dimensional Object Recognition from Range Images
Three-Dimensional Object Recognition from Range Images
Improved Appearance-Based 3-D Object Recognition Using Wavelets
VMV '01 Proceedings of the Vision Modeling and Visualization Conference 2001
Learning membership functions in a function-based object recognition system
Journal of Artificial Intelligence Research
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Model-based and learned semantic object labeling in 3D point cloud maps of kitchen environments
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Affordance-based human-robot interaction
Proceedings of the 2006 international conference on Towards affordance-based robot control
| Hi-index | 0.00 |
The visionary goal of an easy to use service robot impliessome key features like spatial cognition, speech understandingand object recognition. Therefore such a systemneeds techniques to identify objects in scenes, i.e. to assignthe natural category (e.g. "door", "chair", "table") tonew objects based on their prototypical geometry.Our approach uses 2{1 \over 2} D laser range data to recognizebasic objects like chairs or tables within an office environment.It is based on the concept of affordances; establishedon the work about form and function we identify certaingeometries that lead to certain functions and therefore allowtheir identification. Our approach currently is restrictedto basic objects but not limited to a special form. This isachieved by spatial abstraction where we assign the data tothree layers. In identifying components in these layers of altitude,we reconstruct the basic form of the object, concludeits function and finally determine the object.