When trees are not green: Recent developments in an off-the-shelf system for robust color and multispectral based recognition and robot control

摘要

Mobile robots typically operate in environments where objects of interest are likely to appear as mixtures of colors and textures with complex outlines. To use color or multispectral imagery for identification and decision-making, systems that can quickly be trained by example to recognize such objects have distinct advantages. Two examples are shown of the use of WAY-2C, a system for color-based recognition that relies on a non-parametric statistical model to provide robust segmentation in the presence of real-world complexities. Recent enhancements to the system to increase the amount of information available for decision making are discussed as well as control interfaces.