Applying machine learning methods and analysis on remotely sensed color, multispectral, and thermal imageryhas been recognized as a potentially cost-effective approach for detecting the location of various weed speciesin-field. This detection approach has the potential to be an important first step for broader Site-Specific WeedManagement procedures (SSWM). The objective of this research was to create a method for automating thedetection of weeds in corn and soybean fields, at different stages of the growing season. Sensors based on anunmanned aerial vehicle were used to capture imagery used for this research. We focused on identifying fourcommon weed types present in Midwestern fields. This research involved: 1) collecting color, multispectral, andthermal imagery from UAV based sensors in corn and soybean fields throughout the 2018 growing season, 2)creating individual normalized differential vegetation index (NDVI) images from the near-infrared (NIR) andred multispectral bands 3) applying image thresholding and smoothing techniques on the NDVI imagery , 4)manually drawing bounding boxes and hand labelling vegetation blobs from the processed imagery using colorimages as the ground truth, 5) developing a training set of these processed, labeled images that represent weedsat different crop growth stages. Preliminary results of these methods show promise in creating an affordable firststep to target herbicide application.
展开▼
