omparing the Segment Anything Model with Region Growing Algorithms in the detection of irrigated croplands
Article Sidebar
Main Article Content
Abstract
The advance of remote sensing and geotechnologies has helped to solve agricultural-related problems, especially
those connected to management practices such as irrigation. Image segmentation techniques, for example, bring the
possibility of identifying areas and borders of irrigated croplands, a factor that can enhance area and yield estimates. In this
research area, a recent innovation is the Segment Anything Model (SAM) algorithm. Thus, this study aimed to compare
SAM with two well-known remote sensing image segmentation algorithms, Region Growing and Baatz-Schape, to delineate
irrigated agricultural lands in the Brazilian semiarid region. The findings indicate that SAM has the potential to generate
homogeneous segments when examining such lands. However, it requires refinements in order to distinguish fields with
varying crops.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see "The Effect of Open Access").
References
ANGELOTTI, Francislene; HAMADA, Emília; MAGALHÃES, Edineide Elisa; GHINI, Raquel;
GARRIDO, Lucas da Ressureição; PEDRO, Mário José. Climate change and the occurrence of
downy mildew in Brazilian grapevines. Pesquisa Agropecuária Brasileira, SciELO Brasil,
v. 52, p. 426–434, 2017.
ARAUJO, Leandro Moscôso; TEIXEIRA, Antônio Heriberto de Castro; BASSOI, Luís Henrique.
Evapotranspiration and biomass modelling in the Pontal Sul Irrigation Scheme. International
Journal of Remote Sensing, Taylor & Francis, v. 41, n. 6, p. 2326–2338, 2020.
BARTH, R.; IJSSELMUIDEN, J.; HEMMING, J.; HENTEN, E.J. Van. Data synthesis methods
for semantic segmentation in agriculture: A Capsicum annuum dataset. Computers and
Electronics in Agriculture, v. 144, p. 284–296, 2018. ISSN 0168-1699. DOI: https://doi.org/
1016/j.compag.2017.12.001. Disponível em: <https://www.sciencedirect.com/science/
article/pii/S0168169917305689>.
BINS, Leonardo S.; FONSECA, Leila M. G.; ERTHAL, Guaraci J.; MITSUO, Fernando. Satellite
Imagery Segmentation: a region growing approach. In. Disponível em: <https://api.semanticsch
olar.org/CorpusID:2406096>.
BRASIL, Paulilo; MEDEIROS, Pedro. NeStRes–model for operation of Non-Strategic Reservoirs for
irrigation in drylands: model description and application to a semiarid basin. Water Resources
Management, v. 34, n. 1, p. 195–210, 2020.
CAI, Ximing; ROSEGRANT, Mark. Global water demand and supply projections: part 1. A modeling
approach. Water International, v. 27, n. 2, p. 159–169, 2002.
CÂMARA, Gilberto; SOUZA, Ricardo; FREITAS, Ubirajara; GARRIDO, Juan. SPRING: Integrating
remote sensing and GIS by object-oriented data modelling. Computers & Graphics, v. 20,
n. 3, p. 395–403, 1996.
COPERNICUS. Sentinel-2. [S. l.: s. n.], jan. 2023. https://dataspace.copernicus.eu/explore-data/datacollections/sentinel-data/sentinel-2.
DIAS, Lívia; PIMENTA, Fernando; SANTOS, Ana; COSTA, Marcos; LADLE, Richard. Patterns of
land use, extensification, and intensification of Brazilian agriculture. Global change biology,
v. 22, n. 8, p. 2887–2903, 2016.
HAGEL, Heinrich; RINCON, Daniela; DOLUSCHITZ, Reiner. Fruit Production in Brazil’s Desert
and Sustainability Aspects of Irrigated Family Farming Along the Lower-Middle Sao Francisco
River: A Case Study. In: WATER and Wastewater Management. [S. l.: s. n.], 2022. P. 269–281.
INPE, National Institute for Space Research. TerraView. [S. l.: s. n.], 2013.
KOTARIDIS, Ioannis; LAZARIDOU, Maria. Remote sensing image segmentation advances: A metaanalysis. ISPRS Journal of Photogrammetry and Remote Sensing, v. 173, p. 309–322,
NATIONS, United. The 17 Goals. [S. l.: s. n.], fev. 2024. https://sdgs.un.org/goals.
OSCO, Lucas; WU, Qiusheng; LEMOS, Eduardo; GONÇALVES, Wesley; RAMOS, Ana; LI, Jonathan;
JUNIOR, José. The segment anything model (sam) for remote sensing applications: From zero
to one shot. International Journal of Applied Earth Observation and Geoinformation,
v. 124, p. 103540, 2023.
OZDOGAN, Mutlu; YANG, Yang; ALLEZ, George; CERVANTES, Chelsea. Remote Sensing of
Irrigated Agriculture: Opportunities and Challenges. Remote Sensing, v. 2, n. 9, p. 2274–2304,
PETRONE, Felipe; SILVA, Darlan da; MAIA, Aluizio; SANCHES, Ieda; CHAVES, Michel; ADAMI,
Marcos; FONSECA, Leila. Detecting Irrigated Croplands: A Comparative Study with Segment
Anything Model and Region-Growing Algorithms. In: PROCEEDINGS of the 24º. Brazilian
Symposium on Geoinformatics, São José dos Campos, SP. [S. l.: s. n.], 2023.
POTAPOV, Peter; TURUBANOVA, Svetlana; HANSEN, Matthew; TYUKAVINA, Alexandra; ZALLES, Viviana; KHAN, Ahmad; SONG, Xiao-Peng; PICKENS, Amy; SHEN, Quan; CORTEZ,
Jocelyn. Global maps of cropland extent and change show accelerated cropland expansion in
the twenty-first century. Nature Food, v. 3, n. 1, p. 19–28, 2022.
RESENDE, Geraldo; YURI, Jony. Yield of watermelon cultivars in different spaces and planting times
at submiddle São Francisco Valley., 2021.
RODRIGUES, Geraldo Stachetti; IRIAS, Luiz José Maria. Considerações sobre os Impactos
Ambientais da Agricultura Irrigada. Jaguariúna, SP.: Embrapa, 2004. P. 1–7.
SAVENIJE, Hubert; VAN DER ZAAG, Pieter. Water as an economic good and demand management
paradigms with pitfalls. Water international, v. 27, n. 1, p. 98–104, 2002.
SHIMABUKURO, Yosio; NOVO, Evlyn; PONZONI, Flávio. Índice de vegetação e modelo linear de
mistura espectral no monitoramento da região do Pantanal. Pesquisa Agropecuária Brasileira,
v. 33, n. 13, p. 1729–1737, 1998.
SILVA, Bruno; RODRIGUES, Rodrigo; HEISKANEN, Janne; ABERA, Temesgen; GASPARETTO,
Suelen; BIASE, Adriele; BALLESTER, Maria; MOURA, Yhasmin; PIEDADE, Sônia; SILVA,
Andrezza et al. Evaluating the temporal patterns of land use and precipitation under desertification
in the semi-arid region of Brazil. Ecological Informatics, v. 77, p. 102192, 2023.
SUN, Xian; WANG, Bing; WANG, Zhirui; LI, Hao; LI, Hengchao; FU, Kun. Research progress on
few-shot learning for remote sensing image interpretation. IEEE Journal of Selected Topics
in Applied Earth Observations and Remote Sensing, v. 14, p. 2387–2402, 2021.
VENDRUSCOLO, Jhony; PEREZ-MARIN, Aldrin; FELIX, Evaldo; FERREIRA, Karoline; CAVALHEIRO, Wanderson; FERNANDES, Izaias. Monitoring desertification in semiarid Brazil:
using the Desertification Degree Index (DDI). Land Degradation & Development, v. 32, n. 2,
p. 684–698, 2021.
VIEIRA, Denis; SANCHES, Ieda; MONTIBELLER, Bruno; PRUDENTE, Victor; HANSEN, Matthew;
BAGGETT, Antoine; ADAMI, Marcos. Cropland expansion, intensification, and reduction
in Mato Grosso state, Brazil, between the crop years 2000/01 to 2017/18. Remote Sensing
Applications: Society and Environment, v. 28, p. 100841, 2022.
YU, Jiaqian; XU, Jingtao; CHEN, Yiwei; LI, Weiming; WANG, Qiang; YOO, Byungin; HAN, Jae-Joon.
Learning Generalized Intersection Over Union for Dense Pixelwise Prediction. In .
Proceedings of the 38th International Conference on Machine Learning. [S. l.]: PMLR, 18–
Jul 2021. v. 139. (Proceedings of Machine Learning Research), p. 12198–12207. Disponível