Files in this item

FilesDescriptionFormat

application/pdf

application/pdfSP20-ECE499-Thesis-Varghese, Joshua.pdf (8MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Weed visualization
Author(s):Varghese, Joshua
Contributor(s):Chowdhary, Girish
Subject(s):Agriculture
Deep learning
Computer vision
Abstract:Herbicide resistant weeds are becoming a problem in agriculture, causing millions of dollars’ worth of losses each year. A possible approach to mechanical control of weeds would be a team of small robots that are able to weed a given field in an algorithmic fashion. This research provides a suitable simulation environment to model weed growth and a way to count weeds in video frames collected by RGB cameras onboard the robots to estimate weed density, both of which will help develop a data driven predictor that can estimate weed growth in a field given an initial seed bank density, in the interest of creating a coordinated weeding policy.
Issue Date:2020-05
Genre:Other
Type:Text
Language:English
URI:http://hdl.handle.net/2142/107271
Date Available in IDEALS:2020-06-12


This item appears in the following Collection(s)

Item Statistics