Hostname: page-component-7dd5485656-wlg5v Total loading time: 0 Render date: 2025-10-30T13:46:12.968Z Has data issue: false hasContentIssue false
  • English
  • Français

Detection of grassy weeds in bermudagrass with deep convolutional neural networks

Published online by Cambridge University Press:  08 June 2020

Jialin Yu Open the ORCID record for Jialin Yu [Opens in a new window] ,
Arnold W. Schumann ,
Shaun M. Sharpe ,
Xuehan Li  and
Nathan S. Boyd
Jialin Yu
Affiliation:
Professor, Co-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing, Jiangsu, China
Arnold W. Schumann
Affiliation:
Professor, Citrus Research and Education Center, University of Florida, Lake Alfred, Florida, USA
Shaun M. Sharpe
Affiliation:
Research Scientist, Saskatoon Research and Development Centre, Science and Technology Branch, Agriculture and Agri-Food Canada/Government of Canada, Saskatoon, Saskatchewan, Canada
Xuehan Li
Affiliation:
Student, Co-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing, Jiangsu, China
Nathan S. Boyd*
Affiliation:
Associate Professor, Gulf Coast Research and Education Center, University of Florida, Wimauma, FL, USA
*
Author for correspondence: Nathan S. Boyd, Gulf Coast Research and Education Center, University of Florida, 14625 County Road 672, Wimauma, FL33578. Email: nsboyd@ufl.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

Spot spraying POST herbicides is an effective approach to reduce herbicide input and weed control cost. Machine vision detection of grass or grass-like weeds in turfgrass systems is a challenging task due to the similarity in plant morphology. In this work, we explored the feasibility of using image classification with deep convolutional neural networks (DCNN), including AlexNet, GoogLeNet, and VGGNet, for detection of crabgrass species (Digitaria spp.), doveweed [Murdannia nudiflora (L.) Brenan], dallisgrass (Paspalum dilatatum Poir.), and tropical signalgrass [Urochloa distachya (L.) T.Q. Nguyen] in bermudagrass [Cynodon dactylon (L.) Pers.]. VGGNet generally outperformed AlexNet and GoogLeNet in detecting selected grassy weeds. For detection of P. dilatatum, VGGNet achieved high F1 scores (≥0.97) and recall values (≥0.99). A single VGGNet model exhibited high F1 scores (≥0.93) and recall values (1.00) that reliably detected Digitaria spp., M. nudiflora, P. dilatatum, and U. distachya. Low weed density reduced the recall values of AlexNet at detecting all weed species and GoogLeNet at detecting Digitaria spp. In comparison, VGGNet achieved excellent performances (overall accuracy = 1.00) at detecting all weed species in both high and low weed-density scenarios. These results demonstrate the feasibility of using DCNN for detection of grass or grass-like weeds in turfgrass systems.

Keywords

Artificial intelligencecomputer visionmachine visionprecision herbicide applicationweed recognition

Information

Type
Research Article
Information
Weed Science , Volume 68 , Issue 5 , September 2020 , pp. 545 - 552
Copyright
© The Author(s), 2020. Published by Cambridge University Press on behalf of Weed Science Society of America

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Footnotes

Associate Editor: Ramon G. Leon, North Carolina State University

References

Balogh, JC, Walker, WJ (1992) Golf Course Management & Construction: Environmental Issues. Boca Raton, FL: CRC Press. Pp 1–39Google Scholar
Busey, P (2004) Goosegrass (Eleusine indica) control with foramsulfuron in bermudagrass (Cynodon spp.) turf. Weed Technol 18:634–640CrossRefGoogle Scholar
Chaki, J, Parekh, R, Bhattacharya, S (2015) Plant leaf recognition using texture and shape features with neural classifiers. Pattern Recogn Lett 58:61–68CrossRefGoogle Scholar
Chism, WJ, Bingham, SW (1991) Postemergence control of large crabgrass (Digitaria sanguinalis) with herbicides. Weed Sci 39:62–66CrossRefGoogle Scholar
Collobert, R, Weston, J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. Pages 160–167 in Proceedings of the 25th International Conference on Machine Learning. New York: ACMCrossRefGoogle Scholar
Collobert, R, Weston, J, Bottou, L, Karlen, M, Kavukcuoglu, K, Kuksa, P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537Google Scholar
Cross, RB, McCarty, LB, Estes, AG (2016) Postemergence tropical signalgrass (Urochloa subquadripara) control with nonorganic arsenical herbicides. Weed Technol 30:815–821CrossRefGoogle Scholar
Dayan, FE, Trindade, ML, Velini, ED (2009) Amicarbazone, a new photosystem II inhibitor. Weed Sci 57:579–583CrossRefGoogle Scholar
Dekker, J (1997) Weed diversity and weed management. Weed Sci 45:357–363CrossRefGoogle Scholar
dos Santos Ferreira, A, Freitas, DM, da Silva, GG, Pistori, H, Folhes, MT (2017) Weed detection in soybean crops using ConvNets. Comput Electron Agric 143:314–324CrossRefGoogle Scholar
Dyrmann, M, Karstoft, H, Midtiby, HS (2016) Plant species classification using deep convolutional neural network. Biosyst Eng 151:72–80CrossRefGoogle Scholar
[EPA] Environmental Protection Agency (2018) Atrazine—Background and Updates. https://www.epa.gov/ingredients-used-pesticide-products/atrazine-background-and-updates. Accessed: June 3, 2019Google Scholar
Farooq, MH, Zaman, QU, Boyd, NS, White, SN (2019) Evaluation of broadcast and spot herbicide applications for narrowleaf goldenrod [Euthamia graminifolia (L.) Nutt.] management in lowbush blueberry. Weed Technol 33:739–747CrossRefGoogle Scholar
Fennimore, SA, Slaughter, DC, Siemens, MC, Leon, RG, Saber, MN (2016) Technology for automation of weed control in specialty crops. Weed Technol 30:823–837CrossRefGoogle Scholar
Ferentinos, KP (2018) Deep learning models for plant disease detection and diagnosis. Comp Electron Agric 145:311–318CrossRefGoogle Scholar
Fernández-Quintanilla, C, Peña, J, Andújar, D, Dorado, J, Ribeiro, A, López-Granados, F (2018) Is the current state of the art of weed monitoring suitable for site-specific weed management in arable crops? Weed Res 58:259–272CrossRefGoogle Scholar
Fidanza, M, Dernoeden, P, Zhang, M (1996) Degree-days for predicting smooth crabgrass emergence in cool-season turfgrasses. Crop Sci 36:990–996CrossRefGoogle Scholar
Ghosal, S, Blystone, D, Singh, AK, Ganapathysubramanian, B, Singh, A, Sarkar, S (2018) An explainable deep machine vision framework for plant stress phenotyping. Proc Natl Acad Sci USA 115:4613–4618CrossRefGoogle ScholarPubMed
Graves, A, Mohamed, AR, Hinton, G (2013) Speech recognition with deep recurrent neural networks. Pages 6645–6649 in Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Vancouver, Canada: IEEE Computer SocietyCrossRefGoogle Scholar
Grinblat, GL, Uzal, LC, Larese, MG, Granitto, PM (2016) Deep learning for plant identification using vein morphological patterns. Comput Electron Agric 127:418–424CrossRefGoogle Scholar
Hamada, Y, Stow, DA, Coulter, LL, Jafolla, JC, Hendricks, LW (2007) Detecting Tamarisk species (Tamarix spp.) in riparian habitats of southern California using high spatial resolution hyperspectral imagery. Remote Sens Environ 109:237–248CrossRefGoogle Scholar
Haug, S, Michaels, A, Biber, P, Ostermann, J (2014) Plant classification system for crop/weed discrimination without segmentation. Pages 1142–1149 in Proceedings of the 2014 IEEE Winter Conference on Applications of Computer Vision (WACV). Steamboat Springs, CO: IEEE Computer SocietyCrossRefGoogle Scholar
Havaei, M, Davy, A, Warde-Farley, D, Biard, A, Courville, A, Bengio, Y, Pal, C, Jodoin, PM, Larochelle, H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31CrossRefGoogle ScholarPubMed
Henry, GM, Yelverton, FH, Burton, MG (2007) Dallisgrass (Paspalum dilatatum) control with foramsulfuron in bermudagrass turf. Weed Technol 21:759–762CrossRefGoogle Scholar
Hinton, G, Deng, L, Yu, D, Dahl, GE, Mohamed, AR, Jaitly, N, Senior, A, Vanhoucke, V, Nguyen, P, Sainath, TN (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Proc Mag 29:82–97CrossRefGoogle Scholar
Hoiem, D, Chodpathumwan, Y, Dai, Q (2012) Diagnosing error in object detectors. Pages 340–353in Fitzgibbon, A, Lazebnik, S, Perona, P, Sato, Y, Schmid, C, eds.). Berlin: SpringerCrossRefGoogle Scholar
Jia, Y, Shelhamer, E, Donahue, J, Karayev, S, Long, J, Girshick, R, Guadarrama, S, Darrell, T (2014) Caffe: convolutional architecture for fast feature embedding. Pages 675–678 in Proceedings of the 22nd ACM International Conference on Multimedia. New York: ACMCrossRefGoogle Scholar
Johnson, B (1976) Turfgrass tolerance and weed control with methazole and metribuzin. Weed Sci 24:512–517CrossRefGoogle Scholar
Johnson, BJ (1993) Sequential herbicide treatments for large crabgrass (Digitaria sanguinalis) and goosegrass (Eleusine indica) control in bermudagrass (Cynodon dactylon) turf. Weed Technol 7:674–680CrossRefGoogle Scholar
Johnson, BJ (1996) Reduced rates of preemergence and postemergence herbicides for large crabgrass (Digitaria sanguinalis) and goosegrass (Eleusine indica) control in bermudagrass (Cynodon dactylon). Weed Sci 44:585–590CrossRefGoogle Scholar
Jordan, MI, Mitchell, TM (2015) Machine learning: trends, perspectives, and prospects. Science 349:255–260CrossRefGoogle ScholarPubMed
Kerr, RA, Zhebentyayeva, T, Saski, C, McCarty, LB (2019) Comprehensive phenotypic characterization and genetic distinction of distinct goosegrass (Eleusine indica L. Gaertn.) ecotypes. J Plant Sci Phytopathol 3:95–100CrossRefGoogle Scholar
Krizhevsky, A, Sutskever, I, Hinton, GE (2012) Imagenet classification with deep convolutional neural networks. Pages 1097–1105 in Proceedings of the Advances in Neural Information Processing Systems. 10.1145/3065386Google Scholar
Kurtulmuş, F, Kavdir, I (2014) Detecting corn tassels using computer vision and support vector machines. Expert Syst Appl 41:7390–7397CrossRefGoogle Scholar
Larese, MG, Granitto, PM (2016) Finding local leaf vein patterns for legume characterization and classification. Mach Vision Appl 27:709–720CrossRefGoogle Scholar
Larese, MG, Namías, R, Craviotto, RM, Arango, MR, Gallo, C, Granitto, PM (2014) Automatic classification of legumes using leaf vein image features. Pattern Recog 47:158–168CrossRefGoogle Scholar
Lass, LW, Thill, DC, Shafii, B, Prather, TS (2002) Detecting spotted knapweed (Centaurea maculosa) with hyperspectral remote sensing technology. Weed Technol 16:426–432CrossRefGoogle Scholar
LeCun, Y, Bengio, Y, Hinton, G (2015) Deep learning. Nature 521:436CrossRefGoogle ScholarPubMed
Liu, W, Anguelov, D, Erhan, D, Szegedy, C, Reed, S, Fu, CY, Berg, AC (2016) SSD: Single Shot MultiBox Detector. Pages 21–37 in Proceedings of the European Conference on Computer Vision. Berlin: SpringerCrossRefGoogle Scholar
Lycan, DW, Hart, SE (2005) Cool-season turfgrass response to bispyribac-sodium. HortScience 40:1552–1555CrossRefGoogle Scholar
McCarty, LB (1996) Selective control of common bermudagrass in St. Augustinegrass. Crop Sci 36:694–698CrossRefGoogle Scholar
McCarty, LB, Miller, LC, Colvin, DL (1991) Bermudagrass (Cynodon spp.) cultivar response to diclofop, MSMA and metribuzin. Weed Technol 5:27–32CrossRefGoogle Scholar
McCullough, PE, de Barreda, DG, Sidhu, S, Yu, J (2014) Dithiopyr behavior in smooth crabgrass (Digitaria ischaemum) as influenced by growth stage and temperature. Weed Sci 62:11–21CrossRefGoogle Scholar
Milesi, C, Elvidge, C, Dietz, J, Tuttle, B, Nemani, R, Running, S (2005) A strategy for mapping and modeling the ecological effects of U.S. lawns. J Turfgrass Manag 1:83–97Google Scholar
Milioto, A, Lottes, P, Stachniss, C (2018) Real-time semantic segmentation of crop and weed for precision agriculture robots leveraging background knowledge in CNNs. Pages 2229–2235 in Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA). Brisbane, Australia: IEEE Computer SocietyCrossRefGoogle Scholar
Mohanty, SP, Hughes, DP, Salathé, M (2016) Using deep learning for image-based plant disease detection. Front Plant Sci 7:1419CrossRefGoogle ScholarPubMed
Pearsaul, DG, Leon, RG, Sellers, BA, Silveira, ML, Odero, DC (2018) Evaluation of verticutting and herbicides for tropical signalgrass (Urochloa subquadripara) control in turf. Weed Technol 32:392–397CrossRefGoogle Scholar
Pimentel, D (2005) Environmental and economic costs of the application of pesticides primarily in the United States. Environ Dev Sustain 7:229–252CrossRefGoogle Scholar
Redmon, J, Divvala, S, Girshick, R, and Farhadi, A (2016) You only look once: unified, real-time object detection. Pages 779–788 in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE Computer SocietyCrossRefGoogle Scholar
Reed, TV, Yu, J, McCullough, PE (2013) Aminocyclopyrachlor efficacy for controlling Virginia buttonweed (Diodia virginiana) and smooth crabgrass (Digitaria ischaemum) in tall fescue. Weed Technol 27:488–491CrossRefGoogle Scholar
Saidi, N, Kadir, J, Hong, LW (2016) Genetic diversity and morphological variations of goosegrass [Eleusine indica (L.) Gaertn] ecotypes in Malaysia. Weed Turfgrass Sci 5:144–154CrossRefGoogle Scholar
Schmidhuber, J (2015) Deep learning in neural networks: an overview. Neural Net 61:85–117CrossRefGoogle ScholarPubMed
Shaner, D (2014) Herbicide Handbook. 10th ed. Lawrence, KS: Weed Science Society of AmericaGoogle Scholar
Sharpe, SM, Schumann, AW, Boyd, NS (2019) Detection of Carolina geranium (Geranium carolinianum) growing in competition with strawberry using convolutional neural networks. Weed Sci 67:239–245CrossRefGoogle Scholar
Simonyan, K, Zisserman, A (2014) Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1409.1556. Accessed: May 28, 2019Google Scholar
Singh, AK, Ganapathysubramanian, B, Sarkar, S, Singh, A (2018) Deep learning for plant stress phenotyping: trends and future perspectives. Trend Plant Sci 23:883–898CrossRefGoogle ScholarPubMed
Sokolova, M, Lapalme, G (2009) A systematic analysis of performance measures for classification tasks. Inform Process Manag 45:427–437CrossRefGoogle Scholar
Szegedy, C, Liu, W, Jia, Y, Sermanet, P, Reed, S, Anguelov, D, Erhan, D, Vanhoucke, V, Rabinovich, A (2015) Going deeper with convolutions. Pages 1–9 in IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA: IEEE Computer SocietyCrossRefGoogle Scholar
Tao, A, Barker, J, Sarathy, S (2016) Detectnet: Deep Neural Network for Object Detection in Digits. https://devblogs.nvidia.com/detectnet-deep-neural-network-object-detection-digits. Accessed: October 1, 2018Google Scholar
Tillett, N, Hague, T, Grundy, A, Dedousis, A (2008) Mechanical within-row weed control for transplanted crops using computer vision. Biosyst Eng 99:171–178CrossRefGoogle Scholar
Tillett, N, Hague, T, Miles, S (2001) A field assessment of a potential method for weed and crop mapping on the basis of crop planting geometry. Comp Electron Agric 32:229–246CrossRefGoogle Scholar
[USDA-NRCS] U.S. Department of Agriculture–Natural Resources Conservation Service (2019) Plants Database. https://plants.sc.egov.usda.gov. Accessed: July 13, 2019Google Scholar
Vithu, P, Moses, J (2016) Machine vision system for food grain quality evaluation: a review. Trend Food Sci Technol 56:13–20CrossRefGoogle Scholar
Wang, Y, Yu, J, Zhou, B, Sapkota, S, Wei, F, Wang, Z (2018) Atrazine and mesotrione-induced oxidative stress and impact on antioxidant enzymes and chlorophyll contents in bermudagrass. Planta Daninha. 10.1590/s0100-83582018360100146CrossRefGoogle Scholar
Wang, A, Zhang, W, Wei, X (2019) A review on weed detection using ground-based machine vision and image processing techniques. Comp Electron Agric 158:226–240CrossRefGoogle Scholar
Welch, AH, Westjohn, D, Helsel, DR, Wanty, RB (2000) Arsenic in ground water of the United States: occurrence and geochemistry. Groundwater 38:589–604CrossRefGoogle Scholar
Wu, Q, Zhou, C, Wang, C (2006) Feature extraction and automatic recognition of plant leaf using artificial neural network. Adv Art Intellig 3:5–12Google Scholar
Xu, R, Li, C, Paterson, AH, Jiang, Y, Sun, S, Robertson, JS (2018) Aerial images and convolutional neural network for cotton bloom detection. Front Plant Sci 8:2235CrossRefGoogle ScholarPubMed
Yang, C, Prasher, SO, Landry, J, DiTommaso, A (2000) Application of artificial neural networks in image recognition and classification of crop and weeds. Can Agric Eng 42:147–152Google Scholar
Yu, J, Cao, Z, Sharpe, SM, Schumann, AW, Boyd, NS (2019a) Deep learning for broadleaf weed detection in perennial ryegrass. Front Plant Sci 10:1422CrossRefGoogle Scholar
Yu, J, McCullough, PE (2016) Efficacy and fate of atrazine and simazine in doveweed (Murdannia nudiflora). Weed Sci 64:379–388CrossRefGoogle Scholar
Yu, J, McCullough, PE, Czarnota, MA (2017) Selectivity and fate of monosodium methylarsenate in bermudagrass, centipedegrass, and seashore paspalum. Crop Sci 57:S-322–S-330CrossRefGoogle Scholar
Yu, J, Sharpe, SM, Schumann, AW, Boyd, NS (2019b) Deep learning for image-based weed detection in turfgrass. Eur J Agron 104:78–84CrossRefGoogle Scholar
Yu, J, Sharpe, SM, Schumann, AW, Boyd, NS (2019c) Detection of broadleaf weeds growing in turfgrass with convolutional neural networks. Pest Manag Sci 75:2211–2218CrossRefGoogle ScholarPubMed
Zaman, QU, Esau, TJ, Schumann, AW, Percival, DC, Chang, YK, Read, SM, Farooque, AA (2011) Development of prototype automated variable rate sprayer for real-time spot-application of agrochemicals in wild blueberry fields. Comp Electron Agric 76:175–182CrossRefGoogle Scholar