The society of mind
Repairing learned knowledge using experience
Artificial intelligence at MIT expanding frontiers
Robotic grasping of unknown objects: a knowledge-based approach
International Journal of Robotics Research
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Control of selective perception using Bayes nets and decision theory
International Journal of Computer Vision - Special issue on active vision II
Functional and physical object characteristics and object recognition in improvisation
Computer Vision and Image Understanding - Special issue of funtion-based vision
Recognition by functional parts
Computer Vision and Image Understanding - Special issue of funtion-based vision
Generic recognition of articulated objects through reasoning about potential function
Computer Vision and Image Understanding - Special issue of funtion-based vision
Interactive recognition and representation of functionality
Computer Vision and Image Understanding - Special issue of funtion-based vision
Computer Vision and Image Understanding - Special issue of funtion-based vision
Computer Vision and Image Understanding - Special issue of funtion-based vision
Generic object recognition using form and function
Generic object recognition using form and function
Feature Detection with Automatic Scale Selection
International Journal of Computer Vision
Attentional scene segmentation: integrating depth and motion
Computer Vision and Image Understanding
Scale-Space Theory in Computer Vision
Scale-Space Theory in Computer Vision
Computer Vision
Active Perception
3D object recognition: Representation and matching
Statistics and Computing
Occlusions as a Guide for Planning the Next View
IEEE Transactions on Pattern Analysis and Machine Intelligence
Egomotion estimation of a range camera using the space envelope
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Active vision in robotic systems: A survey of recent developments
International Journal of Robotics Research
| Hi-index | 0.00 |
Function-based object recognition provides the framework to represent and reason about object functionality as a means to recognize novel objects and produce plans for interaction with the world. When function can be perceived visually, function-based computer vision is consistent with Gibson's theory of affordances. Objects are recognized by their functional attributes. These attributes can be segmented out of the scene and given symbolic labels which can then be used to guide the search space for additional functional attributes. An example of such affordance-driven scene segmentation would be the process of attaching symbolic labels to the areas that afford sitting (functional seats) and using these areas to guide parameter selection for deriving nearby surfaces that potentially afford back support. The Generic Recognition Using Form and Function (GRUFF) object recognition system reasons about and generates plans for understanding 3-D scenes of objects by performing such a functional attribute-based labelling process. An avenue explored here is based on a novel approach of autonomously directing image acquisition and range segmentation by determining the extent to which surfaces in the scene meet specified functional requirements, or provide affordances associated with a generic category of objects.