<i>Semi-Self-Supervised Segmentation of Oranges with Small Sample Sizes</i>

Kyle Volle; Prashant Ganesh; Thomas Francis Burks; Siddhartha S Mehta

doi:10.13031/aim.202001397

Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Semi-Self-Supervised Segmentation of Oranges with Small Sample Sizes

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2020 ASABE Annual International Virtual Meeting 2001397.(doi:10.13031/aim.202001397)
Authors:   Kyle Volle, Prashant Ganesh, Thomas Francis Burks, Siddhartha S Mehta
Keywords:   Deep-learning, Fruit Detection, Machine Learning, Orange Segmentation

Abstract. Visually detecting and masking fruit can be regarded as a vital first step in autonomous harvesting. Given the constrained domain, general purpose segmentation networks are overly computationally intensive. In this work, we train a generative segmentation network for semantic segmentation of oranges. The proposed method exploits the domain constraints to train a machine learning segmentation solution from scratch with only 110 labeled training images.

(Download PDF) (Export to EndNotes)

Authors, please use the Guide for Authors when creating your articles.

Public Access Information
= Public Access (PA)
Public Access Limited Time = PA Limited Time
= Open Access
= Contact Us For Purchase