Available at: https://digitalcommons.calpoly.edu/theses/1858
Date of Award
MS in Electrical Engineering
Farmers require advance notice when a harvest is approaching, so they can allocate resources and hire workers as efficiently as possible. Existing methods are subjective and labor intensive, and require the expertise of a professional forecaster. Cal Poly’s EE department has been collaborating with the Cal Poly Strawberry Center to investigate the potential in using digital imaging processing to predict harvests more reliably. This paper shows the progress of that ongoing project, as well as what aspects could still be improved. Three main blocks comprise this system: data acquisition, which obtains and catalogues images of the strawberry plants; computer vision, which extracts information from the images and constructs a time-series model of the field as a whole; and prediction, which uses the field’s history to guess when the most likely harvest window will be. The best method of data acquisition is determined through a decision matrix to be a small autonomous rover. Several challenges specific to images captured via drone, such as fisheye distortion and dirt masking, are examined and mitigated. Using thresholding, the nRGB color space is shown to be the most promising for image segmentation of red strawberries. Data from field 25 at the Cal Poly Strawberry Center is tabulated, analyzed, and compared against industry trends across California. Ultimately, this work serves as a strong benchmark towards a full strawberry yield prediction system.