Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning
The presence of Kochia weed is harmful to crop production. It can grow well in harsh conditions and is resistant to common herbicides like glyphosate. It causes stress to crops and spreads quickly, forming large patches. Early detection of Kochia is crucial for its effective control. However, it is...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10230234/ |
_version_ | 1797692137846865920 |
---|---|
author | Muhammad Hamza Asad Sajid Saleem Abdul Bais |
author_facet | Muhammad Hamza Asad Sajid Saleem Abdul Bais |
author_sort | Muhammad Hamza Asad |
collection | DOAJ |
description | The presence of Kochia weed is harmful to crop production. It can grow well in harsh conditions and is resistant to common herbicides like glyphosate. It causes stress to crops and spreads quickly, forming large patches. Early detection of Kochia is crucial for its effective control. However, it is challenging to detect Kochia due to its close resemblance with early-stage crops. As Kochia seeds are water and air-borne, these can also spread in the field from neighbouring farms. Therefore, Kochia needs to be managed both at the field as well as regional levels. Currently, object-based detection methods are used for Kochia detection at the field level, but there is still a lack of literature on mapping Kochia at a regional level. Our research proposes a methodology for accurately detecting, localizing and quantifying Kochia plants in fields using high-resolution RGB imagery. We also explore the potential of detecting Kochia patches at a regional level using satellite imagery. Our approach uses semantic segmentation techniques to process geotagged RGB images, allowing us to identify and quantify individual Kochia plants in the field. To ensure accurate detection, we have established a minimum Kochia density threshold based on the density of Kochia in RGB images. This threshold enables us to distinguish the spectral signature of satellite imagery pixels containing a high density of Kochia. We label the satellite imagery based on the geo-locations where Kochia density exceeds the threshold value. Our method has a 99% accuracy rate in detecting Kochia patches using multi-spectral satellite imagery with a density threshold of 40%. The semantic segmentation model trained on RGB imagery for in-field mapping has a mean intersection over union value of up to 0.8606. These results suggest pixel-level Kochia segmentation of satellite imagery can be performed more accurately if a pixel has more than 40% Kochia mix. Our study highlights the potential of using high-resolution RGB imagery and satellite data at the farm and regional levels for effective Kochia management. Detecting Kochia early and accurately can help prevent crop damage and ensure successful crop production. |
first_indexed | 2024-03-12T02:24:15Z |
format | Article |
id | doaj.art-987086e840c94344b830c905ec83c2d4 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-12T02:24:15Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-987086e840c94344b830c905ec83c2d42023-09-05T23:01:48ZengIEEEIEEE Access2169-35362023-01-0111922989231110.1109/ACCESS.2023.330890910230234Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine LearningMuhammad Hamza Asad0https://orcid.org/0000-0002-1663-7837Sajid Saleem1Abdul Bais2https://orcid.org/0000-0003-2190-348XElectronic Systems Engineering, Faculty of Engineering and Applied Science, University of Regina, Regina, CanadaDepartment of Computer Science, National University of Modern Languages, Lalazar, Rawalpindi, PakistanElectronic Systems Engineering, Faculty of Engineering and Applied Science, University of Regina, Regina, CanadaThe presence of Kochia weed is harmful to crop production. It can grow well in harsh conditions and is resistant to common herbicides like glyphosate. It causes stress to crops and spreads quickly, forming large patches. Early detection of Kochia is crucial for its effective control. However, it is challenging to detect Kochia due to its close resemblance with early-stage crops. As Kochia seeds are water and air-borne, these can also spread in the field from neighbouring farms. Therefore, Kochia needs to be managed both at the field as well as regional levels. Currently, object-based detection methods are used for Kochia detection at the field level, but there is still a lack of literature on mapping Kochia at a regional level. Our research proposes a methodology for accurately detecting, localizing and quantifying Kochia plants in fields using high-resolution RGB imagery. We also explore the potential of detecting Kochia patches at a regional level using satellite imagery. Our approach uses semantic segmentation techniques to process geotagged RGB images, allowing us to identify and quantify individual Kochia plants in the field. To ensure accurate detection, we have established a minimum Kochia density threshold based on the density of Kochia in RGB images. This threshold enables us to distinguish the spectral signature of satellite imagery pixels containing a high density of Kochia. We label the satellite imagery based on the geo-locations where Kochia density exceeds the threshold value. Our method has a 99% accuracy rate in detecting Kochia patches using multi-spectral satellite imagery with a density threshold of 40%. The semantic segmentation model trained on RGB imagery for in-field mapping has a mean intersection over union value of up to 0.8606. These results suggest pixel-level Kochia segmentation of satellite imagery can be performed more accurately if a pixel has more than 40% Kochia mix. Our study highlights the potential of using high-resolution RGB imagery and satellite data at the farm and regional levels for effective Kochia management. Detecting Kochia early and accurately can help prevent crop damage and ensure successful crop production.https://ieeexplore.ieee.org/document/10230234/Kochia patch detectionmachine learningremote sensingsemantic segmentation |
spellingShingle | Muhammad Hamza Asad Sajid Saleem Abdul Bais Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning IEEE Access Kochia patch detection machine learning remote sensing semantic segmentation |
title | Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning |
title_full | Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning |
title_fullStr | Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning |
title_full_unstemmed | Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning |
title_short | Detection and Mapping of Kochia Plants and Patches Using High-Resolution Ground Imagery and Satellite Data: Application of Machine Learning |
title_sort | detection and mapping of kochia plants and patches using high resolution ground imagery and satellite data application of machine learning |
topic | Kochia patch detection machine learning remote sensing semantic segmentation |
url | https://ieeexplore.ieee.org/document/10230234/ |
work_keys_str_mv | AT muhammadhamzaasad detectionandmappingofkochiaplantsandpatchesusinghighresolutiongroundimageryandsatellitedataapplicationofmachinelearning AT sajidsaleem detectionandmappingofkochiaplantsandpatchesusinghighresolutiongroundimageryandsatellitedataapplicationofmachinelearning AT abdulbais detectionandmappingofkochiaplantsandpatchesusinghighresolutiongroundimageryandsatellitedataapplicationofmachinelearning |