Abstract:
Fast and reliable non-destructive phenotyping of plants plays an important role in precision agriculture, as the information enables farmers to make real-time crop management decisions without affecting yield. To non-destructively phenotype crops, computer and stereo-vision based methods are commonly used, as they are low-cost and resolve finer details compared to other systems such as LiDAR. However, most approaches are targeted towards large and sparsely populated crops, where occlusions and sensor error pose less of a challenge.

In this thesis, we tackle the problem of using computer vision to non-destructively phenotype smaller crops by leveraging semantic information. First, we present a method for creating 3D models of Sorghum panicles by using seeds as semantic 3D landmarks. Next, we present a computer vision-based method to measure the sizes and growth rates of apple fruitlets using a hand-held stereo camera and an Attentional Graph Neural Network to associate
fruitlets across different days. Finally, we build upon our sizing pipeline by designing a robotic system that adopts a next-best-view planning approach targeted towards sizing smaller fruit to make the sizing process fully autonomous.

Committee:
George Kantor (advisor)
Michael Kaess
Daniel McGann