Abstract
In this study, six supervised classification algorithms were compared. The algorithms were based on cluster analysis, distance, deep learning, and object-based image analysis. Our objective was to determine which of these algorithms has the highest overall accuracy in both detection and automated estimation of agave cover in a given area to help growers manage their plantations. An orthomosaic with a spatial resolution of 2.5 cm was derived from 300 images obtained with a DJI Inspire 1 unmanned aerial system. Two training classes were defined: (1) sites where the presence of agaves was identified and (2) “absence” where there were no agaves but other plants were present. The object-oriented algorithm was found to have the highest overall accuracy (0.963), followed by the support-vector machine with 0.928 accuracy and the neural network with 0.914. The algorithms with statistical criteria for classification were the least accurate: Mahalanobis distance = 0.752 accuracy and minimum distance = 0.421. We further recommend that the object-oriented algorithm be used, because in addition to having the highest overall accuracy for the image segmentation process, it yields parameters that are useful for estimating the coverage area, size, and shapes, which can aid in better selection of agave individuals for harvest.
Similar content being viewed by others
Data availability
Not applicable.
References
Almaraz-Abarca N, Delgado-Alvarado EA, Hernández-Vargas V, Ortega-Chávez M, Orea-Lara G, León AC, Ávila-Reyes JA, Muñiz-Martínez R (2009) Profiling of phenolic compounds of somatic and reproductive tissues of Agave Durangensis gentry (Agavaceae). Am J Appl Sci 6:1076–1085. https://doi.org/10.3844/AJASSP.2009.1076.1085
Al-Najjar HAH, Kalantar B, Pradhan B, Saeidi V, Halin AA, Ueda N, Mansor S (2019) Land cover classification from fused DSM and UAV images using convolutional neural networks. Remote Sensing 11(12):1461. https://doi.org/10.3390/rs11121461
Atkinson PM, Tatnall AR (1997) Introduction neural networks in remote sensing. Int J Remote Sens 18(4):699709. https://doi.org/10.1080/014311697218700
Benediktsson JA, Swain PH, Ersoy OK (1993) Conjugate-gradient neural networks in classification of multisource and very-high-dimensional remote sensing data. Intl J Remote Sens 14(15):2883–2903. https://doi.org/10.1080/01431169308904316
Blaschke T (2010) Object based image analysis for remote sensing. Photogram Rem S 65(1):2–16. https://doi.org/10.1016/j.isprsjprs.2009.06.004
Braspenning PJ, Thuijsman F (1995) Artificial neural networks: an introduction to ANN theory and practice. Springer Science & Business Media, New York
Bunruang P, Kaewplang S (2021) Evaluation of sugarcane plant height using UAV remote sensing. Engineering Access 7(2):98–102. https://doi.org/10.14456/mijet.2021.15
Calvario G, Alarcón TE, Dalmau O, Sierra B, Hernandez C (2020) An agave counting methodology based on mathematical morphology and images acquired through unmanned aerial vehicles. Sensors 20(21):1–21. https://doi.org/10.3390/s20216247
Carrillo-Trueba LA (2007) Los destilados de agave en México y su denominación de origen. Ciencias 087. https://www.revistacienciasunam.com/es/. Accessed 15 Nov 2020
Carvalho-Júnior OA, Guimarães RF, Gillespie AR, Silva NC, Gomes RA (2011) A new approach to change vector analysis using distance and similarity measures. Rem Sens 3(11):2473–2493. https://doi.org/10.3390/rs3112473
Castro-Alvarado E (2019) UAV remote sensing: NDVI analysis in Danongdafu plantation. Dissertation, Universidad Pública de Navarra. España
Chang A, Jung J, Maeda MM, Landivar J (2017) Crop height monitoring with digital imagery from unmanned aerial system (UAS). Comput Electron Agric 141:232–237. https://doi.org/10.1016/j.compag.2017.07.008
Chen W, Xianju L, Lizhe W (2020) Fine land cover classification in an open pit mining area using optimized support vector machine and WorldView-3 imagery. Rem Sens 12(82):1–16. https://doi.org/10.3390/rs12010082
Chuvieco ES (2019) Teledetección Ambiental. La observación de la Tierra desde el Espacio. Ariel. España
Cloutis EA (1996) Review Article Hyperspectral geological remote sensing: evaluation of analytical techniques. Int J Remote Sens 17(12):2215–2242. https://doi.org/10.1080/01431169608948770
Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Rem Sens Environ 37(1):35–46. https://doi.org/10.1016/0034-4257(91)90048-B
Coria-Contreras JJ, Mora-Aguilera G, Yáñez-Morales MJ, Acevedo-Sánchez G, Santana-Peñaloza B, Mendoza-Ramos C, Jiménez-González L, Martínez-Bustamante VI, García-Martínez DC, Rubio-Cortés R (2019) Epidemiología regional aplicada a la caracterización inductiva y pronóstico de la mancha gris del agave azul (Cercospora agavicola) en Jalisco México. Revista mexicana de fitopatología 37(1):71–94. https://doi.org/10.18781/r.mex.fit.1809-4
Dimosthenis CT, Stamatia B, Panagiotis GS (2019) A review on UAV-based applications for precision agriculture. Information 10(11):2–26. https://doi.org/10.3390/info10110349
DOF, 1994. Diario Oficial de la Federancion. Norma Oficial Mexicana NOM-EM-007-SCFI-2000, Bebidas alcohólicas-Mezcal-Especificaciones. https://dof.gob.mx/nota_detalle. Acccesed 12 June 2020
Douglas DH, Peuker T (1973) Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica the international journal for geographic information and geovisualization. 10(2):112–122. https://doi.org/10.3138/FM57-6770-U75U-7727
Drake JM, Randin C, Guisan A (2006) Modelling ecological niches with support vector machines. J Appl Ecol 43(3):424–432. https://doi.org/10.1111/j.1365-2664.2006.01141.x
Duan T, Zheng B, Guo W, Ninomiya S, Guo Y, Chapman SC (2017) Comparison of ground cover estimates from experiment plots in cotton, sorghum and sugarcane based on images and ortho-mosaics captured by UAV. Funct Plant Biol 44:169–183. https://doi.org/10.1071/FP16123
Escobar-Flores JG, Lopez-Sanchez CA, Sandoval S, Marquez-Linares MA, Wehenkel C (2018) Predicting Pinus monophylla forest cover in the Baja California Desert by remote sensing. PeerJ 6:e4603. https://doi.org/10.7717/peerj.4603
Flores D, González-Hernández I, Lozano R, Vazquez-Nicolas JM, Hernandez-Toral JL (2021) Automated agave detection and counting using a convolutional neural network and unmanned aerial systems. Drones 5(1):1–17. https://doi.org/10.3390/drones5010004
García-Mendoza AJ, Franco-Martínez IS, Sandoval-Gutiérrez D (2019) Cuatro especies nuevas de Agave (Asparagaceae Agavoideae) del sur de México. Act Bot Mex 126:e1461. https://doi.org/10.21829/abm126.2019.1461
Goodchild MF (1994) Integrating GIS and remote sensing for vegetation analysis and modeling: methodological issues. J Veg Sci 5(5):615–626. https://doi.org/10.2307/3235878
Hepner G, Logan T, Ritter N, Bryant N (1990) Artificial neural network classification using a minimal training set Comparison to conventional supervised classification. Photogram Eng Rem S 56(4):469–473
Hossain MD, Chen D (2019) Segmentation for object-based image analysis (OBIA): a review of algorithms and challenges from remote sensing perspective. Photogram Eng Rem S 150:115–134. https://doi.org/10.1016/j.isprsjprs.2019.02.009
Hsu CW, Chang CC, Lin CJ (2010) A practical guide to support vector classification. National Taiwan University. https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf. Accessed Dec 2021
Huang C, Davis LS, Townshend JRG (2002) An assessment of support vector machines for land cover classification. Int J Remote Sens 23(4):725–749. https://doi.org/10.1080/01431160110040323
Immitzer M, Vuolo F, Atzberger C (2016) First experience with sentinel-2 data for crop and trees species classifications in Central Europe. Rem Sen 8(3):1–27. https://doi.org/10.3390/rs8030166
Jean-Philippe T, Marc-Olivier B, Macq Benoit MM, Jacques M (1994) Automatic recognition of cancerous cells using mathematical morphology. Proc. SPIE. Visualization in Biomedical Computing 2359:392–401. https://doi.org/10.1117/12.185200
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Lee H, Wang J, Leblon B (2020) Intra-field canopy nitrogen retrieval from unmanned aerial vehicle Imagery for wheat and corn fields. Can J Remote Sens 46(4):454–472. https://doi.org/10.1080/07038992.2020.1788384
López-García P, Intrigliolo DS, Moreno MA, Martínez-Moreno A, Ortega JF, Pérez-Álvarez EP, Ballesteros R (2021) Assessment of vineyard water status by multispectral and RGB imagery obtained from an unmanned aerial vehicle. Am J Enol Vitic 72(4):285–297. https://doi.org/10.5344/ajev.2021.20063
Martínez-Ramírez S, Trinidad A, Bautist G, Pedro EC (2013) Crecimiento de plántulas de dos especies de mezcal en función del tipo de suelo y nivel de fertilización. Rev Fitotec Mex 36(4):387–393
Modica G, De Luca G, Messina G, Praticò S (2021) Comparison and assessment of different object-based classifications using machine learning algorithms and UAVs multispectral imagery: a case study in a citrus orchard and an onion crop. Eur J Remote Sens 54(1):431–460. https://doi.org/10.1080/22797254.2021.1951623
Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens 66(3):247–259. https://doi.org/10.1016/j.isprsjprs.2010.11.001
Oh S, Chang A, Ashapure A, Jung J, Dube N, Maeda M, Gonzalez D, Landivar J (2020) Plant counting of cotton from UAS imagery using deep learning-based object detection framework. Rem Sens 12(18):2981. https://doi.org/10.3390/rs12182981
Okwuashi O, Ndehedehe CE (2020) Deep support vector machine for hyperspectral image classification. Pattern Recogn 103:1–10. https://doi.org/10.1016/j.patcog.2020.107298
Olofsson P, Foody GM, Herold M, Stehman SV, Woodcock CE, Wulder MA (2014) Good practices for estimating area and assessing accuracy of land change. Remote Sens Environ 148:42–57. https://doi.org/10.1016/j.rse.2014.02.015
Pathak AR, Pandey M, Rautaray S (2018a) Application of deep learning for object detection. Procedia Computer Science 132:1706–1717
Pathak AR, Pandey M, Rautaray S (2018b) Application of deep learning for object detection. Procedia Comput Sci 132:1706–1717. https://doi.org/10.1016/j.procs.2018.05.144
Perumal K, Bhaskaran R (2010) Supervised classification performance of multispectral images. Journal of Computing. 2(2): 124–129. https://sites.google.com/site/journalofcomputing. Accessed Dec 2010
Poenaru V, Baeda A, Mihai CS, Irimescu A (2015) Multi-temporal multi-spectral and radar remote sensing for agricultural monitoring in the Braila Plain. Agric Agric Sci Procedia 6:506–516. https://doi.org/10.1016/j.aaspro.2015.08.134
Poblete T, Ortega-Farías S, Ryu D (2018) Automatic coregistration algorithm to remove canopy shaded pixels in UAV-borne thermal images to improve the estimation of crop water stress index of a drip-irrigated Cabernet Sauvignon vineyard. Sensors 18(2):397. https://doi.org/10.3390/s18020397
Polat N, Kaya Y (2021) Investigation of the performance of different pixel-based classification methods in land use/land cover (LULC) determination. Türkiye İnsansız Hava Araçları Dergisi 3(1):01–06. https://doi.org/10.51534/tiha.829656
Rangel-Landa S, Casas A, Dávila P (2015) Facilitation of Agave potatorum: an ecological approach for assisted population recovery. For Ecol Manag 347:57–74. https://doi.org/10.1016/j.foreco.2015.03.003
Richards JA (1999) Remote Sensing Digital Image Analysis. Springer-Verlag, Berlin
Robinson DJ, Redding NJ, Crisp DJ (2002) Implementation of a fast algorithm for segmenting SAR imagery. Scientific and Techinical Report. Defense Science and Techonology Organization. Australia. https://apps.dtic.mil/sti/pdfs/ADA402611.pdf. Accesed 12 Febrary 2020
Souffer I, Sghiouar M, Sebari I, Zefri Y, Hajji H, Aniba G (2022) Automatic extraction of photovoltaic panels from UAV imagery with object-based image analysis and machine learning. S. Bennani, Y. Lakhrissi, G. Khaissidi, A. Mansouri, Y. Khamlichi (Eds.), WITS 2020. Lecture notes in electrical engineering, vol. 745, Springer, Singapore. https://doi.org/10.1007/978-981-33-6893-4_64
Srivastava S, Narayan S (2021) Mitta S (2021) A survey of deep learning techniques for vehicle detection from UAV images. J Syst Architect 117:102152. https://doi.org/10.1016/j.sysarc.2021.10215
Talukdar S, Singha P, Mahato S, Pal S, Liou YA, Rahman A (2020) Land-use land-cover classification by machine learning classifiers for satellite observations—a review. Rem Sens 12(7):1135. https://doi.org/10.3390/rs12071135
Tan SS, Smeins FE (1996) Predicting grassland community changes with an artificial neural network model. Ecol Modell 84(1–3):91–97. https://doi.org/10.1016/0304-3800(94)00131-6
Torres-Sánchez J, López-Granados F, Serrano N, Arquero O, Peña JM (2015) High-throughput 3-D monitoring of agricultural-tree plantations with unmanned aerial vehicle (UAV) technology. PLoS ONE 10(6):e0130479. https://doi.org/10.1007/s13593-016-0405-7
Valenzuela ZAG (2003) El Agave tequilero. Cultivo e industria de México. Mundiprensa, México
Verbeke LPC, Vancoillie FMB, De Wulf RR (2004) Reusing back-propagation artificial neural networks for land cover classification in tropical savannahs. Int J Remote Sens 25(14):2747–2771
Woo H, Acuna M, Madurapperuma B, Jung G, Woo C, Park J (2021) Application of maximum likelihood and spectral angle mapping classification techniques to evaluate forest fire severity from UAV multi-spectral images in South Korea. Sensors and Materials. 33(1):3745–3760. https://doi.org/10.18494/SAM.2021.3365
Xiang S, Nie F, Zhang C (2008) Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recogn 41(12):3600–3612. https://doi.org/10.1016/j.patcog.2008.05.018
Yang KT (2008) Artificial neural networks (ANNs): a new paradigm for thermal science and engineering. J Heat Transfer 130(9):093001. https://doi.org/10.1115/1.2944238
Yuba N, Kawamura K, Yasuda T, Lim J, Yoshitoshi R, Watanabe N, Kurokawa Y, Maeda T (2021) Discriminating Pennisetum alopecuoides plants in a grazed pasture from unmanned aerial vehicles using object-based image analysis and random forest classifier. Grassland Sci 67(1):73–82. https://doi.org/10.1111/grs.12288
Zakeri F, Mariethoz G (2021) A review of geostatistical simulation models applied to satellite remote sensing: Methods and applications. Remote Sens Environ 259:112381. https://doi.org/10.1016/j.rse.2021.112381
Acknowledgements
We would like to acknowledge Miss Gelvin Isela Gámiz Romero and Mr. Jose Cruz for allowing us to work on his property.
Funding
Access funding is provided by Instituto Politecnico Nacional, CIIDIR Unidad Durango, Project Number 20210008.
Author information
Authors and Affiliations
Contributions
JE and SS provide a substantial contribution to the conception and design of this mini-review. JE is the major contributor of literature search and data analysis for this mini-review. SS analyzed and interpreted the data for this mini-review article. JE analyzed and interpreted the data for this mini-review article. SS is the major contributor in drafting this mini-review. EG contributed to critically revising the article for important intellectual content. All the authors read and approved the final version of this mini-review and agree to approve for sending for publication in this esteemed journal.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Responsible Editor: Philippe Garrigues
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Escobar-Flores, J.G., Sandoval, S. & Gámiz-Romero, E. Unmanned aerial vehicle images in the machine learning for agave detection. Environ Sci Pollut Res 29, 61662–61673 (2022). https://doi.org/10.1007/s11356-022-18985-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-022-18985-7