An Approach for Weed Detection Using CNNs And Transfer Learning

Simple item page
dc.contributor.authorOfori, Martinson
dc.contributor.authorEl-Gayar, Omar
dc.date.accessioned2020-12-24T19:09:32Z
dc.date.available2020-12-24T19:09:32Z
dc.date.issued2021-01-05
dc.description.abstractTo prevent yield losses, it is critical to eliminate competition between food crops and weeds at the onset of plant growth. While uniform spraying of herbicides can be economically and environmentally inefficient, site-specific weed management (SSWM) counteracts this by reducing the amount of chemical application with localized spraying of weed species. Past research on weed detection in SSWM has used a large deep convolutional neural network (DCNN) for weed detection. These models are, however, computationally expensive and prone to overfitting on smaller datasets. In this paper, we propose an approach to detecting weeds amongst plant seedlings using transfer learning in a small network. Our approach combines the mobile-sized EfficientNet with transfer learning to achieve up to 95.44% classification accuracy on plant seedlings. Due to the robustness of transfer learning methods, this approach would be beneficial in improving both the classification accuracy and generalizability of current weed detection methods.
dc.format.extent8 pages
dc.identifier.doi10.24251/HICSS.2021.109
dc.identifier.isbn978-0-9981331-4-0
dc.identifier.urihttp://hdl.handle.net/10125/70721
dc.language.isoEnglish
dc.relation.ispartofProceedings of the 54th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectAnalytics and Decision Support for Green IS and Sustainability Applications
dc.subjectconvolutional neural network
dc.subjectdeep learning
dc.subjectefficientnet
dc.subjectplant seedling
dc.subjectprecision agriculture
dc.subjectsmart farming
dc.subjecttransfer learning
dc.subjectweed detection
dc.titleAn Approach for Weed Detection Using CNNs And Transfer Learning
prism.startingpage888

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0088.pdf
Size:
686.64 KB
Format:
Adobe Portable Document Format
Download

Collections

Analytics and Decision Support for Green IS and Sustainability Applications