Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil
This study delves into the agricultural landscape of Bahia, Brazil, employing the Mask R-CNN deep learning model with satellite imagery to detect three crop growth stages (early, mid-growth and maturity stage). This model is suited to the region’s complex terrain and diverse crop patterns, providing...
- Autores:
-
Camacho-De Angulo, Yineth Viviana
Arrechea-Castillo, Darwin Alexis
Cantero-Mosquera, Yessica Carolina
Solano-Correa, Yady Tatiana
Roisenberg, Mauro
- Tipo de recurso:
- Fecha de publicación:
- 2024
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12733
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12733
- Palabra clave:
- Crops Growth
Deep Learning
Image Instance Segmentation
Remote Sensing
Mask R-CNN
LEMB
- Rights
- closedAccess
- License
- http://purl.org/coar/access_right/c_14cb
| id |
UTB2_3147b205ef8147cfeb27ebefe237c842 |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12733 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| title |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| spellingShingle |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil Crops Growth Deep Learning Image Instance Segmentation Remote Sensing Mask R-CNN LEMB |
| title_short |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| title_full |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| title_fullStr |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| title_full_unstemmed |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| title_sort |
Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil |
| dc.creator.fl_str_mv |
Camacho-De Angulo, Yineth Viviana Arrechea-Castillo, Darwin Alexis Cantero-Mosquera, Yessica Carolina Solano-Correa, Yady Tatiana Roisenberg, Mauro |
| dc.contributor.author.none.fl_str_mv |
Camacho-De Angulo, Yineth Viviana Arrechea-Castillo, Darwin Alexis Cantero-Mosquera, Yessica Carolina Solano-Correa, Yady Tatiana Roisenberg, Mauro |
| dc.subject.keywords.spa.fl_str_mv |
Crops Growth Deep Learning Image Instance Segmentation Remote Sensing Mask R-CNN |
| topic |
Crops Growth Deep Learning Image Instance Segmentation Remote Sensing Mask R-CNN LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
This study delves into the agricultural landscape of Bahia, Brazil, employing the Mask R-CNN deep learning model with satellite imagery to detect three crop growth stages (early, mid-growth and maturity stage). This model is suited to the region’s complex terrain and diverse crop patterns, providing accurate instance segmentation crucial for monitoring crop development. Remarkable results have been achieved with a limited dataset of just 54 images for training, underscoring the model’s efficiency in scenarios where extensive data collection is challenging. The validation metric chosen for this study is the Intersection over Union (IoU), preferred for its ability to quantify the pixel-wise overlap between the predicted and actual segmentations, offering a clear measure of accuracy in spatial contexts. An IoU of 90% was obtained, demonstrating Mask R-CNN’s robustness and potential for precision agriculture in challenging environments. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-09-12T14:02:50Z |
| dc.date.available.none.fl_str_mv |
2024-09-12T14:02:50Z |
| dc.date.issued.none.fl_str_mv |
2024-07-12 |
| dc.date.submitted.none.fl_str_mv |
2024-09-11 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_8544 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/lecture |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_c94f |
| status_str |
publishedVersion |
| dc.identifier.citation.spa.fl_str_mv |
Y. V. Camacho-De Angulo; D.A. Arrechea-Castillo; Y. C. Cantero-Mosquera; Y. T. Solano-Correa; M. Roisenberg, "Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil," in 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Athens, Greece, Jul. 2024. DOI: 10.1109/IGARSS53475.2024.10642298. |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12733 |
| dc.identifier.doi.none.fl_str_mv |
10.1109/IGARSS53475.2024.10642298 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
Y. V. Camacho-De Angulo; D.A. Arrechea-Castillo; Y. C. Cantero-Mosquera; Y. T. Solano-Correa; M. Roisenberg, "Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil," in 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Athens, Greece, Jul. 2024. DOI: 10.1109/IGARSS53475.2024.10642298. 10.1109/IGARSS53475.2024.10642298 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12733 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/closedAccess |
| eu_rights_str_mv |
closedAccess |
| rights_invalid_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.format.extent.none.fl_str_mv |
4 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.publisher.faculty.spa.fl_str_mv |
Ciencias Básicas |
| dc.source.spa.fl_str_mv |
EEE International Geoscience and Remote Sensing Symposium (IGARSS) |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/1/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/2/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/3/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/4/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf.jpg |
| bitstream.checksum.fl_str_mv |
997be1652b87e78e87e4d21e2f918c33 e20ad307a1c5f3f25af9304a7a7c86b6 2284ad630c1c5ec892e075e049505a0e 40cd080675789292306797dd93c32367 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021773521321984 |
| spelling |
Camacho-De Angulo, Yineth Vivianadf97ad9f-47e5-45c8-922c-d1e2b12c9708Arrechea-Castillo, Darwin Alexis93ac81fe-17eb-4bd1-a2fc-f39f13cc9af2Cantero-Mosquera, Yessica Carolinae09375ab-1dbb-4de9-8570-abe851be1ceeSolano-Correa, Yady Tatiana64432ee7-11fa-4bfb-b643-143125ef82c1Roisenberg, Maurob82483b1-1b24-4356-8b2f-305190e1ae822024-09-12T14:02:50Z2024-09-12T14:02:50Z2024-07-122024-09-11Y. V. Camacho-De Angulo; D.A. Arrechea-Castillo; Y. C. Cantero-Mosquera; Y. T. Solano-Correa; M. Roisenberg, "Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil," in 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Athens, Greece, Jul. 2024. DOI: 10.1109/IGARSS53475.2024.10642298.https://hdl.handle.net/20.500.12585/1273310.1109/IGARSS53475.2024.10642298Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarThis study delves into the agricultural landscape of Bahia, Brazil, employing the Mask R-CNN deep learning model with satellite imagery to detect three crop growth stages (early, mid-growth and maturity stage). This model is suited to the region’s complex terrain and diverse crop patterns, providing accurate instance segmentation crucial for monitoring crop development. Remarkable results have been achieved with a limited dataset of just 54 images for training, underscoring the model’s efficiency in scenarios where extensive data collection is challenging. The validation metric chosen for this study is the Intersection over Union (IoU), preferred for its ability to quantify the pixel-wise overlap between the predicted and actual segmentations, offering a clear measure of accuracy in spatial contexts. An IoU of 90% was obtained, demonstrating Mask R-CNN’s robustness and potential for precision agriculture in challenging environments.4 páginasapplication/pdfengEEE International Geoscience and Remote Sensing Symposium (IGARSS)Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazilinfo:eu-repo/semantics/lectureinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_c94fhttp://purl.org/coar/version/c_970fb48d4fbd8a85http://purl.org/coar/resource_type/c_8544Crops GrowthDeep LearningImage Instance SegmentationRemote SensingMask R-CNNLEMBinfo:eu-repo/semantics/closedAccesshttp://purl.org/coar/access_right/c_14cbCartagena de IndiasCiencias BásicasInvestigadoresD. S. Bullock, M. Boerngen, H. Tao, B. Maxwell, J. D. Luck, L. Shiratsuchi, L. Puntel, and N. F. Martin, “The data-intensive farm management project: changing agronomic research through on-farm precision experimentation,” Agronomy journal, vol. 111, no. 6, pp. 2736–2746, 2019.K. Malhotra and M. Firdaus, “Application of artificial intelligence in iot security for crop yield prediction,” ResearchBerg Review of Science and Technology, vol. 2, no. 1, pp. 136–157, 2022.R. P. Sishodia, R. L. Ray, and S. K. Singh, “Applications of remote sensing in precision agriculture: A review,” Remote Sensing, vol. 12, no. 19, p. 3136, 2020.A. Robinson, Bahia: The Heart of Brazil’s Northeast. Bradt Travel Guides, 2010.E. Benami, Shaping the Producer’s Problem: Essays on Land-Use Zoning and Certification in the Sustainability of Brazilian Oil Palm and Coffee. Stanford University, 2018.K. G. Eng˚as, J. Z. Raja, and I. F. Neufang, “Decoding technological frames: An exploratory study of access to and meaningful engagement with digital technologies in agriculture,” Technological Forecasting and Social Change, vol. 190, p. 122405, 2023Y. T. Solano-Correa, K. Meshkini, F. Bovolo, and L. Bruzzone, “Automatic large-scale precise mapping and monitoring of agricultural fields at country level with sentinel-2 sits,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 3131–3145, 2022.Y. T. Solano-Correa, F. Bovolo, and L. Bruzzone, “A semi-supervised crop-type classification based on sentinel-2 ndvi satellite image time series and phenological parameters,” in IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, pp. 457–460, 2019.D.-C. Hsiou, F. Huang, F. J. Tey, T.-Y. Wu, and Y.-C. Lee, “An automated crop growth detection method using satellite imagery data,” Agriculture, vol. 12, no. 4, p. 504, 2022.CVAT.ai Corporation, “Computer Vision Annotation Tool (CVAT).”W. Abdulla, “Mask r-cnn for object detection and instance segmentation on keras and tensorflow.” https://github.com/matterport/MaskRCNN, 2017.T. N. Carlson and D. A. Ripley, “On the relation between NDVI, fractional vegetation cover, and leaf area index,” vol. 62, no. 3, pp. 241–252.http://purl.org/coar/resource_type/c_c94fORIGINAL2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdf2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdfapplication/pdf5950486https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/1/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf997be1652b87e78e87e4d21e2f918c33MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/2/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD52TEXT2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdf.txt2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdf.txtExtracted texttext/plain17323https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/3/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf.txt2284ad630c1c5ec892e075e049505a0eMD53THUMBNAIL2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdf.jpg2024-C-Detection of Different Crop Growth Stages by Applying Deep Learning Over Sentinel-2 Images of Bahía, Brazil.pdf.jpgGenerated Thumbnailimage/jpeg9474https://repositorio.utb.edu.co/bitstream/20.500.12585/12733/4/2024-C-Detection%20of%20Different%20Crop%20Growth%20Stages%20by%20Applying%20Deep%20Learning%20Over%20Sentinel-2%20Images%20of%20Bah%c3%ada%2c%20Brazil.pdf.jpg40cd080675789292306797dd93c32367MD5420.500.12585/12733oai:repositorio.utb.edu.co:20.500.12585/127332024-09-13 00:18:24.112Repositorio Institucional UTBrepositorioutb@utb.edu.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 |