Vegetation Detection for Mobile Robot Navigation

Described is the development and testing of a robust vegetation detector for mobile robot navigation. A multispectral sensor was created out of a near-infrared and a visible light video camera. Vegetation was then detected by subtracting each pixel in the red channel of the visible-light image from the corresponding pixel in the near-infrared image and thresholding the result. This computationally-efficient technique has been verified to be a robust chlorophyll detector in natural environments. This work was sponsored by DARPA, under contract ”Perception for Off-Road Mobility (PerceptOR)” (contract number MDA972-01-9-0016). The views and conclusions contained in this document are those of the authors and should not be interpreted as representing official policies or endorsements, expressed or implied, of the U.S. Government.