A New Procedure for Combining UAV-Based Imagery and Machine Learning in Precision Agriculture

• DOI: 10.3390/su15020998
• Publication Date: 2023-01-05T10:29:48Z
• Authors: Cristiano Fragassa; Giuliano Vitali; Luis Emmi; Marco Arru
• Keywords: Precision Agriculture

Drone images from an experimental field cropped with sugar beet a high diffusion of weeds taken different flying altitudes were used to develop and test machine learning method for vegetation patch identification. Georeferenced combined hue-based preprocessing analysis, digital transformation by image embedder, evaluation supervised learning. Specifically, six the most common algorithms applied (i.e., logistic regression, k-nearest neighbors, decision tree, random forest, neural network, support-vector machine). The proposed was able precisely recognize crops throughout wide cultivation field, training single partial images. information has been designed be easily integrated into autonomous weed management systems aim reducing use water, nutrients, herbicides precision agriculture.