<p dir="ltr">Plant phenotyping is the process of characterization and quantification of physical traits<br>of plants such as height, leaf area, biomass, wilting degree, or flowering time. Many plants<br>become limp or droop through heat, loss of water, or disease. This is also known as wilting.<br>In this thesis, we propose multiple quantifiable wilting metrics that will be useful in studying<br>bacterial wilt and identifying resistance genes. In order to obtain the wilting metrics, we use<br>machine learning methods to identify the center of the stem. We also propose a fast ground<br>truthing method to speed up training data generation. We test our metrics on both tomato<br>plants and soybean plants with wilting caused by either bacteria or drought. We successfully<br>demonstrated that our metrics are effective at estimating wilting in plants.</p><p dir="ltr"><br>Field experiments often comprise thousands of plants. For many Unmanned Aerial Vehi-<br>cles (UAVs) image-based plant phenotyping analyses, we need to examine smaller groups of<br>plants known as ”plots”. We propose a method to extract plots from images acquired from<br>UAVs. In addition, we proposed a system that will allow us to combine our plot extraction<br>results with field data such as plant ID, plant genotype, and experiment type provided by<br>the planters. We also developed a method to generate synthetic plant center location data.</p>