{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T13:40:29Z","timestamp":1777729229452,"version":"3.51.4"},"reference-count":23,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2017,12,17]],"date-time":"2017-12-17T00:00:00Z","timestamp":1513468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Green Development and Demonstration Programme (GUDP)","award":["34009-16- 1088"],"award-info":[{"award-number":["34009-16- 1088"]}]},{"DOI":"10.13039\/100012774","name":"Innovation Fund Denmark","doi-asserted-by":"publisher","award":["6159-00001B"],"award-info":[{"award-number":["6159-00001B"]}],"id":[{"id":"10.13039\/100012774","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Optimal fertilization of clover-grass fields relies on knowledge of the clover and grass fractions. This study shows how knowledge can be obtained by analyzing images collected in fields automatically. A fully convolutional neural network was trained to create a pixel-wise classification of clover, grass, and weeds in red, green, and blue (RGB) images of clover-grass mixtures. The estimated clover fractions of the dry matter from the images were found to be highly correlated with the real clover fractions of the dry matter, making this a cheap and non-destructive way of monitoring clover-grass fields. The network was trained solely on simulated top-down images of clover-grass fields. This enables the network to distinguish clover, grass, and weed pixels in real images. The use of simulated images for training reduces the manual labor to a few hours, as compared to more than 3000 h when all the real images are annotated for training. The network was tested on images with varied clover\/grass ratios and achieved an overall pixel classification accuracy of 83.4%, while estimating the dry matter clover fraction with a standard deviation of 7.8%.<\/jats:p>","DOI":"10.3390\/s17122930","type":"journal-article","created":{"date-parts":[[2017,12,19]],"date-time":"2017-12-19T03:54:32Z","timestamp":1513655672000},"page":"2930","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Estimation of the Botanical Composition of Clover-Grass Leys from RGB Images Using Data Simulation and Fully Convolutional Neural Networks"],"prefix":"10.3390","volume":"17","author":[{"given":"S\u00f8ren","family":"Skovsen","sequence":"first","affiliation":[{"name":"Department of Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark"}]},{"given":"Mads","family":"Dyrmann","sequence":"additional","affiliation":[{"name":"Department of Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark"}]},{"given":"Anders","family":"Mortensen","sequence":"additional","affiliation":[{"name":"Department of Agroecology, Aarhus University, Fors\u00f8gsvej 1, 4200 Slagelse, Denmark"}]},{"given":"Kim","family":"Steen","sequence":"additional","affiliation":[{"name":"Agro Intelligence ApS, Agro Food Park 13, 8200 Aarhus N, Denmark"}]},{"given":"Ole","family":"Green","sequence":"additional","affiliation":[{"name":"Agro Intelligence ApS, Agro Food Park 13, 8200 Aarhus N, Denmark"}]},{"given":"J\u00f8rgen","family":"Eriksen","sequence":"additional","affiliation":[{"name":"Department of Agroecology, Aarhus University, Blichers All\u00e9 20, 8830 Tjele, Denmark"}]},{"given":"Ren\u00e9","family":"Gislum","sequence":"additional","affiliation":[{"name":"Department of Agroecology, Aarhus University, Fors\u00f8gsvej 1, 4200 Slagelse, Denmark"}]},{"given":"Rasmus","family":"J\u00f8rgensen","sequence":"additional","affiliation":[{"name":"Department of Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark"}]},{"given":"Henrik","family":"Karstoft","sequence":"additional","affiliation":[{"name":"Department of Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark"}]}],"member":"1968","published-online":{"date-parts":[[2017,12,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1111\/gfs.12025","article-title":"Complementary effects of red clover inclusion in ryegrass-white clover swards for grazing and cutting","volume":"69","author":"Eriksen","year":"2014","journal-title":"Grass Forage Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1111\/j.1365-2494.2009.00689.x","article-title":"Yield and stability of yield of single- and multi-clover grass-clover swards in two contrasting temperate environments","volume":"64","author":"Halling","year":"2009","journal-title":"Grass Forage Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1080\/07352689.2014.898455","article-title":"Forage Legumes for Grazing and Conserving in Ruminant Production Systems","volume":"34","author":"Phelan","year":"2015","journal-title":"Crit. Rev. Plant Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1111\/j.1365-2664.2009.01653.x","article-title":"Strong mixture effects among four species in fertilized agricultural grassland led to persistent and consistent transgressive overyielding","volume":"46","author":"Nyfeler","year":"2009","journal-title":"J. Appl. Ecol."},{"key":"ref_5","first-page":"139","article-title":"Nitrogen fertilization of grass\/clover swards under cutting or grazing by dairy cows","volume":"59","author":"Egaard","year":"2009","journal-title":"Acta Agric. Scand. Sect. B\u2014Soil Plant Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2424","DOI":"10.1111\/gcb.12880","article-title":"Nitrogen yield advantage from grass-legume mixtures is robust over a wide range of legume proportions and environmental conditions","volume":"21","author":"Suter","year":"2015","journal-title":"Glob. Chang. Biol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1111\/j.1365-2745.2007.01225.x","article-title":"Evenness drives consistent diversity effects in intensive grassland systems across 28 European sites","volume":"95","author":"Kirwan","year":"2007","journal-title":"J. Ecol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.agee.2010.11.022","article-title":"Grass-legume mixtures can yield more nitrogen than legume pure stands due to mutual stimulation of nitrogen uptake from symbiotic and non-symbiotic sources","volume":"140","author":"Nyfeler","year":"2011","journal-title":"Agric. Ecosyst. Environ."},{"key":"ref_9","unstructured":"Landbrug & F\u00f8devarer, Planteproduktion (2014). Oversigt Over Landsfors\u00f8gene 2014, Videncentret for Landbrug."},{"key":"ref_10","unstructured":"Williams, A., Audsley, E., and Sandars, D. (2017, September 15). Determining the Environmental Burdens and Resource Use in the Production of Agricultural and Horticultural Commodities, Available online: http:\/\/randd.defra.gov.uk\/Default.aspx."},{"key":"ref_11","first-page":"76","article-title":"Evaluating an image analysis system for mapping white clover pastures","volume":"54","author":"Bonesmo","year":"2004","journal-title":"Acta Agric. Scand. Sect. B\u2014Soil Plant Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1910","DOI":"10.2135\/cropsci2008.11.0636","article-title":"Determining the contribution of legumes in legume-grass mixtures using digital image analysis","volume":"49","author":"Himstedt","year":"2009","journal-title":"Crop Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2186","DOI":"10.2135\/cropsci2009.10.0592","article-title":"The relationship between coverage and dry matter contribution of forage legumes in binary legume-grass mixtures","volume":"50","author":"Himstedt","year":"2010","journal-title":"Crop Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"943","DOI":"10.2135\/cropsci2011.04.0189","article-title":"The benefit of color information in digital image analysis for the estimation of legume contribution in legume-grass mixtures","volume":"52","author":"Himstedt","year":"2012","journal-title":"Crop Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rayburn, E.B. (2014). Measuring legume content in pastures using digital photographs. Forage Grazinglands, 12.","DOI":"10.2134\/FG-2011-0143-MG"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.compag.2016.02.015","article-title":"Application of local binary patterns in digital images to estimate botanical composition in mixed alfalfa-grass fields","volume":"123","author":"McRoberts","year":"2016","journal-title":"Comput. Electron. Agric."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_18","unstructured":"Dyrmann, M., Mortensen, A.K., Midtiby, H.S., and J\u00f8rgensen, R.N. (2016, January 26\u201329). Pixel-wise classification of weeds and crops in images by using a fully convolutional neural network. Proceedings of the International Conference on Agricultural Engineering, Aarhus, Denmark."},{"key":"ref_19","unstructured":"Mortensen, A.K., Dyrmann, M., Karstoft, H., J\u00f8rgensen, R.N., and Gislum, R. (2016, January 26\u201329). Semantic segmentation of mixed crops using deep convolutional neural network. Proceedings of the International Conference on Agricultural Engineering, Aarhus, Denmark."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., and Sivic, J. (2014, January 23\u201328). Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref_21","unstructured":"Pereira, F., Burges, C.J.C., Bottou, L., and Weinberger, K.Q. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25, Curran Associates, Inc."},{"key":"ref_22","unstructured":"Simonyan, K., and Zisserman, A. (arXiv, 2014). Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1046\/j.1365-2494.1999.00150.x","article-title":"Prediction of the clover content of red clover- and white clover-grass mixtures by near-infrared reflectance spectroscopy","volume":"54","author":"Wachendorf","year":"1999","journal-title":"Grass Forage Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2930\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:54:19Z","timestamp":1760208859000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,17]]},"references-count":23,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2017,12]]}},"alternative-id":["s17122930"],"URL":"https:\/\/doi.org\/10.3390\/s17122930","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,17]]}}}