Image Analysis for Weed Identification and Mapping

FORT Science

FORT Science Home

Science Features

Science Priorities

Current Research

Find FORT Science by

Research Staff

Bob Waltermire

Research Task: 8327CKX.3.0
Task Manager: Bob Waltermire

Farmers need distribution maps of weeds in their fields to reduce herbicide use by applying site-specific weed management (SSWM). Although remote sensing is key to successful weed mapping, methods of varying cost and complexity are needed for the widest adoption of SSWM. FORT staff are working with the USDA Agricultural Research Service, Water Management Research Unit, to develop a system for mapping weed cover in fallow dryland cropping that is low-cost, easy to use, and does not require expensive GIS, GPS, and image analysis software. The system includes a consumer digital camera and GPS unit, commercial software to map locations of images and view the image at each location, and image analysis and map viewing software that FORT developed. We use a pseudo-Normalized Difference Vegetation Index with a shadow adjustment to identify weed pixels. Weed cover is calculated as percent of pixels classified as green in an image. Locations are displayed using a color legend for percent weed cover and are linked for viewing original and analyzed images. Locations can also be mapped on aerial photographs, topographical maps, or shape files of information such as crop yield.

For more information contact Bob Waltermire