Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning
Plastic shopping bags are often discarded as litter and can be carried away from roadsides and become tangled on cotton plants in farm fields. This rubbish plastic can end up in the cotton at the gin if not removed before harvest. These bags may not only cause problems in the ginning process but mig...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Agriculture |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0472/13/7/1365 |
_version_ | 1797590720690782208 |
---|---|
author | Pappu Kumar Yadav J. Alex Thomasson Robert Hardin Stephen W. Searcy Ulisses Braga-Neto Sorin C. Popescu Roberto Rodriguez Daniel E. Martin Juan Enciso Karem Meza Emma L. White |
author_facet | Pappu Kumar Yadav J. Alex Thomasson Robert Hardin Stephen W. Searcy Ulisses Braga-Neto Sorin C. Popescu Roberto Rodriguez Daniel E. Martin Juan Enciso Karem Meza Emma L. White |
author_sort | Pappu Kumar Yadav |
collection | DOAJ |
description | Plastic shopping bags are often discarded as litter and can be carried away from roadsides and become tangled on cotton plants in farm fields. This rubbish plastic can end up in the cotton at the gin if not removed before harvest. These bags may not only cause problems in the ginning process but might also become embedded in cotton fibers, reducing the quality and marketable value. Therefore, detecting, locating, and removing the bags before the cotton is harvested is required. Manually detecting and locating these bags in cotton fields is a tedious, time-consuming, and costly process. To solve this, this paper shows the application of YOLOv5 to detect white and brown colored plastic bags tangled at three different heights in cotton plants (bottom, middle, top) using Unmanned Aircraft Systems (UAS)-acquired Red, Green, Blue (RGB) images. It was found that an average white and brown bag could be detected at 92.35% and 77.87% accuracies and a mean average precision (mAP) of 87.68%. Similarly, the trained YOLOv5 model, on average, could detect 94.25% of the top, 49.58% of the middle, and only 5% of the bottom bags. It was also found that both the color of the bags (<i>p</i> < 0.001) and their height on cotton plants (<i>p</i> < 0.0001) had a significant effect on detection accuracy. The findings reported in this paper can help in the autonomous detection of plastic contaminants in cotton fields and potentially speed up the mitigation efforts, thereby reducing the amount of contaminants in cotton gins. |
first_indexed | 2024-03-11T01:24:32Z |
format | Article |
id | doaj.art-76d96b3219b944bf9f995936c8ec783b |
institution | Directory Open Access Journal |
issn | 2077-0472 |
language | English |
last_indexed | 2024-03-11T01:24:32Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Agriculture |
spelling | doaj.art-76d96b3219b944bf9f995936c8ec783b2023-11-18T17:52:47ZengMDPI AGAgriculture2077-04722023-07-01137136510.3390/agriculture13071365Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep LearningPappu Kumar Yadav0J. Alex Thomasson1Robert Hardin2Stephen W. Searcy3Ulisses Braga-Neto4Sorin C. Popescu5Roberto Rodriguez6Daniel E. Martin7Juan Enciso8Karem Meza9Emma L. White10Department of Biological & Agricultural Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Agricultural & Biological Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Biological & Agricultural Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Biological & Agricultural Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Ecology & Conservation Biology, Texas A&M University, College Station, TX 77843, USASpatial Data Analysis and Visualization Laboratory, University of Hawaii at Hilo, Hilo, HI 96720, USAAerial Application Technology Research, U.S.D.A. Agriculture Research Service, College Station, TX 77845, USADepartment of Biological & Agricultural Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Civil & Environmental Engineering, Utah State University, Logan, UT 84322, USADepartment of Biological & Agricultural Engineering, Texas A&M University, College Station, TX 77843, USAPlastic shopping bags are often discarded as litter and can be carried away from roadsides and become tangled on cotton plants in farm fields. This rubbish plastic can end up in the cotton at the gin if not removed before harvest. These bags may not only cause problems in the ginning process but might also become embedded in cotton fibers, reducing the quality and marketable value. Therefore, detecting, locating, and removing the bags before the cotton is harvested is required. Manually detecting and locating these bags in cotton fields is a tedious, time-consuming, and costly process. To solve this, this paper shows the application of YOLOv5 to detect white and brown colored plastic bags tangled at three different heights in cotton plants (bottom, middle, top) using Unmanned Aircraft Systems (UAS)-acquired Red, Green, Blue (RGB) images. It was found that an average white and brown bag could be detected at 92.35% and 77.87% accuracies and a mean average precision (mAP) of 87.68%. Similarly, the trained YOLOv5 model, on average, could detect 94.25% of the top, 49.58% of the middle, and only 5% of the bottom bags. It was also found that both the color of the bags (<i>p</i> < 0.001) and their height on cotton plants (<i>p</i> < 0.0001) had a significant effect on detection accuracy. The findings reported in this paper can help in the autonomous detection of plastic contaminants in cotton fields and potentially speed up the mitigation efforts, thereby reducing the amount of contaminants in cotton gins.https://www.mdpi.com/2077-0472/13/7/1365plastic contaminationcotton fieldYOLOv5unmanned aircraft systems (UAS) |
spellingShingle | Pappu Kumar Yadav J. Alex Thomasson Robert Hardin Stephen W. Searcy Ulisses Braga-Neto Sorin C. Popescu Roberto Rodriguez Daniel E. Martin Juan Enciso Karem Meza Emma L. White Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning Agriculture plastic contamination cotton field YOLOv5 unmanned aircraft systems (UAS) |
title | Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning |
title_full | Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning |
title_fullStr | Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning |
title_full_unstemmed | Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning |
title_short | Plastic Contaminant Detection in Aerial Imagery of Cotton Fields Using Deep Learning |
title_sort | plastic contaminant detection in aerial imagery of cotton fields using deep learning |
topic | plastic contamination cotton field YOLOv5 unmanned aircraft systems (UAS) |
url | https://www.mdpi.com/2077-0472/13/7/1365 |
work_keys_str_mv | AT pappukumaryadav plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT jalexthomasson plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT roberthardin plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT stephenwsearcy plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT ulissesbraganeto plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT sorincpopescu plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT robertorodriguez plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT danielemartin plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT juanenciso plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT karemmeza plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning AT emmalwhite plasticcontaminantdetectioninaerialimageryofcottonfieldsusingdeeplearning |