Date of Award:

12-2026

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Electrical and Computer Engineering

Committee Chair(s)

Calvin Coopmans

Committee

Calvin Coopmans

Committee

Mario Harper

Committee

Sierra Young

Committee

Alfonso Torres-Rua

Abstract

Grape growers rely on knowing how much leaf area their vines have, since canopy size affects how much water a vine needs, how healthy it is, and how much fruit it will produce. Measuring this by hand, plant by plant, across an entire vineyard takes enormous time and labor, so researchers have turned to cameras mounted on drones and satellites as a faster alternative. Drones capture very detailed images but only over small areas per flight, while satellites can photograph an entire farming region at once but cannot make out individual plants. 

This thesis builds a computer vision model, a program trained to interpret images the way a person would recognize objects in a photo, that automatically estimates leaf area from drone photographs of two California vineyards, using ordinary color images together with invisible near-infrared light and camera-based measurements of plant height. Two different ways of combining these image types were built and compared to find the more accurate approach. The resulting model was used to create complete leaf-area maps across whole vineyard fields, which were then compared against satellite images of the same fields to check how well the two agreed. The goal is a practical tool that could one day help growers monitor vineyard health across large areas without walking every row and measuring every vine by hand.

Checksum

0e3810496d43c6aa503c7df7abb4ce59

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .