{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:31:28Z","timestamp":1774121488227,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T00:00:00Z","timestamp":1625788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Agriculture and Horticulture Development Board","award":["11140054"],"award-info":[{"award-number":["11140054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In potato (Solanum tuberosum) production, the number of tubers harvested and their sizes are related to the plant population. Field maps of the spatial variation in plant density can therefore provide a decision support tool for spatially variable harvest timing to optimize tuber sizes by allowing densely populated management zones more tuber-bulking time. Computer vision has been proposed to enumerate plant numbers using images from unmanned aerial vehicles (UAV) but inaccurate predictions in images of merged canopies remains a challenge. Some research has been done on individual potato plant bounding box prediction but there is currently no information on the spatial structure of plant density that these models may reveal and its relationship with potato yield quality attributes. In this study, the Faster Region-based Convolutional Neural Network (FRCNN) framework was used to produce a plant detection model and estimate plant densities across a UAV orthomosaic. Using aerial images of 2 mm ground sampling distance (GSD) collected from potatoes at 40 days after planting, the FRCNN model was trained to an average precision (aP) of 0.78 on unseen testing data. The model was then used to generate predictions on quadrants imposed on orthorectified rasters captured at 14 and 18 days after emergence. After spatially interpolating the plant densities, the resultant surfaces were highly correlated to manually-determined plant density (R2 = 0.80). Further correlations were observed with tuber number (r = 0.54 at Butter Hill; r = 0.53 at Horse Foxhole), marketable tuber weight per plant (r = \u22120.57 at Buttery Hill; r = \u22120.56 at Horse Foxhole) and the normalized difference vegetation index (r = 0.61). These results show that accurate two-dimensional maps of plant density can be constructed from UAV imagery with high correlation to important yield components, despite the loss of accuracy of FRCNN models in partially merged canopies.<\/jats:p>","DOI":"10.3390\/rs13142705","type":"journal-article","created":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T10:50:38Z","timestamp":1625827838000},"page":"2705","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Mapping Potato Plant Density Variation Using Aerial Imagery and Deep Learning Techniques for Precision Agriculture"],"prefix":"10.3390","volume":"13","author":[{"given":"Joseph K.","family":"Mhango","sequence":"first","affiliation":[{"name":"Crops and Environment Research Centre, Harper Adams University, Edgmond, Shropshire TF10 8NB, UK"}]},{"given":"Edwin W.","family":"Harris","sequence":"additional","affiliation":[{"name":"Crops and Environment Research Centre, Harper Adams University, Edgmond, Shropshire TF10 8NB, UK"}]},{"given":"Richard","family":"Green","sequence":"additional","affiliation":[{"name":"Crops and Environment Research Centre, Harper Adams University, Edgmond, Shropshire TF10 8NB, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1784-4907","authenticated-orcid":false,"given":"James M.","family":"Monaghan","sequence":"additional","affiliation":[{"name":"Crops and Environment Research Centre, Harper Adams University, Edgmond, Shropshire TF10 8NB, UK"}]}],"member":"1968","published-online":{"date-parts":[[2021,7,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Allen, E.J., and Wurr, D.C.E. (1992). Plant density. Potato Crop, Springer.","DOI":"10.1007\/978-94-011-2340-2_7"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Arsenault, W.J., LeBlanc, D.A., Tai, G.C.C., and Boswall, P. (2001). Effects of nitrogen application and seedpiece spacing on yield and tuber size distribution in eight potato cultivars. Am. J. Potato Res.","DOI":"10.1007\/BF02875695"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Knowles, N.R., and Knowles, L.O. (2006). Manipulating stem number, tuber set, and yield relationships for northern- and southern-grown potato seed lots. Crop Sci.","DOI":"10.2135\/cropsci2005.05-0078"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Love, S.L., and Thompson-Johns, A. (1999). Seed piece spacing influences yield, tuber size distribution, stem and tuber density, and net returns of three processing potato cultivars. HortScience.","DOI":"10.21273\/HORTSCI.34.4.629"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1007\/s12230-011-9213-4","article-title":"Potato Seed Piece Size, Spacing, and Seeding Rate Effects on Yield, Quality and Economic Return","volume":"88","author":"Bohl","year":"2011","journal-title":"Am. J. Potato Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1007\/s12230-017-9604-2","article-title":"High-Resolution Aerial Imaging Based Estimation of Crop Emergence in Potatoes","volume":"94","author":"Sankaran","year":"2017","journal-title":"Am. J. Potato Res."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gates, D.M., Keegan, H.J., Schleter, J.C., and Weidner, V.R. (1965). Spectral Properties of Plants. Appl. Opt.","DOI":"10.1364\/AO.4.000011"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6401","DOI":"10.1109\/JSTARS.2020.3034193","article-title":"Determining the Leaf Area Index and Percentage of Area Covered by Coffee Crops Using UAV RGB Images","volume":"13","author":"Diotto","year":"2020","journal-title":"IEEE J. Sel. Top Appl. Earth Obs. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s13007-020-00613-5","article-title":"Non-destructive estimation of field maize biomass using terrestrial lidar: An evaluation from plot level to individual leaf level","volume":"16","author":"Jin","year":"2020","journal-title":"Plant Methods"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Franceschini, M.H.D., Bartholomeus, H., van Apeldoorn, D.F., Suomalainen, J., and Kooistra, L. (2019). Feasibility of Unmanned Aerial Vehicle Optical Imagery for Early Detection and Severity Assessment of Late Blight in Potato. Remote Sens., 11.","DOI":"10.3390\/rs11030224"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1111\/tpj.14799","article-title":"Automatic wheat ear counting using machine learning based on RGB UAV imagery","volume":"103","author":"Lootens","year":"2020","journal-title":"Plant J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.3389\/fpls.2018.01362","article-title":"Rapeseed Seedling Stand Counting and Seeding Performance Evaluation at Two Early Growth Stages Based on Unmanned Aerial Vehicle Imagery","volume":"9","author":"Zhao","year":"2018","journal-title":"Front. Plant Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13007-019-0399-7","article-title":"The estimation of crop emergence in potatoes by UAV RGB imagery","volume":"15","author":"Li","year":"2019","journal-title":"Plant Methods"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Machefer, M., Lemarchand, F., Bonnefond, V., Hitchins, A., and Sidiropoulos, P. (2020). Mask R-CNN Refitting Strategy for Plant Counting and Sizing in UAV Imagery. Remote Sens., 12.","DOI":"10.3390\/rs12183015"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.aasri.2012.11.074","article-title":"An Improved Median-based Otsu Image Thresholding Algorithm","volume":"3","author":"Yang","year":"2012","journal-title":"AASRI Procedia"},{"key":"ref_16","unstructured":"Brefeld, U. (2019). CentroidNet: A Deep Neural Network for Joint Object Localization and Counting. Machine Learning and Knowledge Discovery in Databases, Springer. ECML PKDD 2018. Lecture Notes in Computer Science."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1111\/j.1744-7348.1991.tb04879.x","article-title":"A key for the stages of development of potato (Solatium tuberosum)","volume":"119","author":"Jefferies","year":"1991","journal-title":"Ann. Appl. Biol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1007\/BF02872222","article-title":"Effect of planting depth and hilling practices on total, U.S. No. 1, and field greening tuber yields","volume":"82","author":"Bohl","year":"2005","journal-title":"Am. J. Potato Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Taylor, J.A., Chen, H., Smallwood, M., and Marshall, B. (2018). Investigations into the opportunity for spatial management of the quality and quantity of production in UK potato systems. Field Crop Res.","DOI":"10.1016\/j.fcr.2018.10.002"},{"key":"ref_20","unstructured":"MATLAB (2020). version 9.8.0 (R2020a), The MathWorks Inc.. Available online: https:\/\/www.mathworks.com\/products\/get-matlab.html."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_22","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015\u2014Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_23","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_24","unstructured":"(2020, July 13). Pix4dmapper Pro. Available online: https:\/\/pix4d.com\/product\/pix4dmapper\/."},{"key":"ref_25","unstructured":"ESRI (2020). ArcGIS Pro (Version 2.5.2), Environmental Systems Research Institute. Available online: https:\/\/www.esri.com\/en-us\/arcgis\/products\/arcgis-pro\/overview."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/0034-4257(88)90106-X","article-title":"A soil-adjusted vegetation index (SAVI)","volume":"25","author":"Huete","year":"1988","journal-title":"Remote Sens. Environ."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bussan, A.J., Mitchell, P.D., Copas, M.E., and Drilias, M.J. (2007). Evaluation of the effect of density on potato yield and tuber size distribution. Crop Sci.","DOI":"10.2135\/cropsci2007.01.0026"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1093\/oxfordjournals.aob.a088084","article-title":"A Mathematical Function for Crop Growth Based on Light Interception and Leaf Area Expansion","volume":"66","author":"Goudriaan","year":"1990","journal-title":"Ann. Bot."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Haverkort, A.J., and MacKerron, D.K.L. (1995). Potato Ecology and Modelling of Crops under Conditions Limiting Growth, Springer.","DOI":"10.1007\/978-94-011-0051-9"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/14\/2705\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:28:17Z","timestamp":1760164097000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/14\/2705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,9]]},"references-count":29,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["rs13142705"],"URL":"https:\/\/doi.org\/10.3390\/rs13142705","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,9]]}}}