A survey of moment-based techniques for unoccluded object representation and recognition
CVGIP: Graphical Models and Image Processing
An active vision architecture based on iconic representations
Artificial Intelligence - Special volume on computer vision
Graphics Gems
Proceedings of the 39th SIGCSE technical symposium on Computer science education
An inexpensive hand-eye system for undergraduate robotics instruction
Proceedings of the 40th ACM technical symposium on Computer science education
Preparing computer science students for the robotics revolution
Communications of the ACM
Seven big ideas in robotics, and how to teach them
Proceedings of the 43rd ACM technical symposium on Computer Science Education
Hi-index | 0.02 |
We describe complementary iconic and symbolic representations for parsing the visual world. The iconic pixmap representation is operated on by an extensible set of "visual routines" (Ullman, 1984; Forbus et al., 2001). A symbolic representation, in terms of lines, ellipses, blobs, etc., is extracted from the iconic encoding, manipulated algebraically, and re-rendered iconically. The two representations are therefore duals, and iconic operations can be freely intermixed with symbolic ones. The dual-coding approach offers robot programmers a versatile collection of primitives from which to construct application-specific vision software. We describe some sample applications implemented on the Sony AIBO.