GARGOYLE: an environment for real-time, context-sensitive active vision

Abstract

Researchers in robot vision have access to several excellent image processing packages (e.g., Khoros, Vista, Susan, MIL, and XVision to name only a few) as a base for any new vision software needed in most navigation and recognition tasks. Our work in automonous robot control and human-robot interaction, however, has demanded a new level of run-time flexibility and performance: on-the-fly configuration of visual routines that exploit up-to-the-second context from the task, image, and environment. The result is Gargoyle: an extendible, on-board, realtime vision software package that allows a robot to configure, parameterize, and execute imageprocessing pipelines at run-time. Each operator in a pipeline works at a level of resolution and over regions of interest that are computed by upstream operators or set by the robot according to task constraints. Pipeline configurations and operator parameters can be stored as a library of visual methods appropriate for different sensing tasks and e...