Artificial intelligence

Scientific journal

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Search by:

Year of publication
Author name
Paper title

Convolutional neural networks in tasks of agricultural vegetation state monitoring on aerial images

Ganchenko V.1, Doudkin A.2
1 United Institute of Informatics Problems of the National Academy of Sciences of Belarus
2 United Institute of Informatics Problems of the National Academy of Sciences of Belarus

Full text (PDF)

UDC: 004.93'1
Publication Language: Russian
Stuc. intelekt. 2018; 23(3):103-110

Abstract: In the article a recognition task of agricultural vegetation using aerial images of different spatial resolution is considered. An image classifier is proposed that allows classifying image segments into three classes: “healthy vegeta-tion”, “diseased vegetation” and “soil”. This classifier is implemented by two convolution neural networks that previ-ously form two classes of vegetation state: “healthy vegetation”-“diseased vegetation” and “vegetation”-“soil”.

Keywords:

References:

  1. Belyayev, B.I. (2006) Opticheskoye distantsionnoyezondirovaniye. Minsk: BGU. 455 s.
  2. Shovengerdt, R.A. (2013) Distantsionnoyezondirovaniye. Modeli i metody obrabotki izobrazheniy. M.: Tekhnosfera. 592 s.
  3. Chao, К. (2002) Machine vision technology foragricultural applications. Elsevier sciencetransactions on computers and electronics inagriculture. Vol. 36. P. 173-191.
  4. Kumar, N. (2004) Do leaf surface' characteristicsaffect agrobaсterium infection in tea [camelliasinensis (1)]. Vol. 29, № 3. P. 309-317.
  5. Wu, L. (2009) Identification of weed, corn usingBP network based on wavelet features and fractaldimension. Scientific Research and Essay.November, 2009. – Vol. 4 (11). – P. 1194-1400.
  6. Qin, Zh. (2005) Detection of rice sheath blight forin-season disease management using multispectralremote sensing. International Journal of AppliedEarth Observation and Geoinformation. Vol. 7.P. 115-148.
  7. Aksoy, S. (2010) Automatic mapping of linearwoody vegetation features in agriculturallandscapes using very high-resolution imagery.IEEE Transactions on Geoscience and RemoteSensing. № 48 (1, 2). P. 511-522.
  8. Abdullahi, H.S. (2017) Advances of imageprocessing in Precision Agriculture: Using deeplearning convolution neural network for soil nutrientclassification. Journal of MultidisciplinaryEngineering Science and Technology (JMEST).Vol. 4, Issue 8. P. 7981-7987.
  9. Wright, D., Rasmussen, V., Ramsey, R., Baker, D.,Ellsworth, J. (2004) Canopy Reflectance Estimationof Wheat Nitrogen Content for Grain ProteinManagement. GIScience Remote Sens. Vol. 41,No. 4. P. 287–300.
  10. Mate, K.A., Pooja, G., Kavita, S.R. (2016)Feature Extraction Algorithm for Estimation ofAgriculture Acreage from Remote SensingImages. P. 5–9.
  11. Huang, H., Deng, J., Lan, Y., Yang, A., Deng, X.,Zhang, L. (2018) A fully convolutional networkfor weed mapping of unmanned aerial vehicle(UAV) imagery. PLoS ONE 13(4): e0196302.
  12. Sa, I. (2018) WeedNet: Dense Semantic WeedClassification Using Multispectral Images andMAV for Smart Farming. IEEE Robotics andAutomation Letters. Vol. 3(1). P. 588-595.
  13. Potena, C., Nardi, D., Pretto, A. (2017) Fast andAccurate Crop and Weed Identification withSummarized Train Sets for Precision Agriculture:Intelligent Autonomous Systems. P. 105-121.
  14. Yao, C., Zhang, Y., Zhang, Y., Liu, H. (2017)Application of convolutional neural network inclassification of high resolution agricultural remotesensing images, Int. Arch. Photogramm. RemoteSens. Spatial Inf. Sci., XLII-2/W7. P. 989-992.
  15. Atole, R.R., Park, D. (2018) A Multiclass DeepConvolutional Neural Network Classifier forDetection of Common Rice Plant Anomalies.IJACSA: International Journal of AdvancedComputer Science and Applications. Vol. 9,No. 1. P. 67-70.
  16. Rajmohan, R., Pajany, M., Rajesh, R.,Raman, D.R., Prabu, U. (2018) Smart paddy cropdisease identification and management using deepconvolution neural network and SVM classifier.International Journal of Pure and AppliedMathematics. Vol. 118, No. 15. P. 255-264.
  17. Athanikar, G., Badar, P. (2016) Potato LeafDiseases Detection and Classification System.International Journal of Computer Science andMobile Computing. Vol. 5 Issue, 2. P. 76-88.
  18. Sladojevic, S., Arsenovic, M., Anderla, A.,Culibrk, D., Stefanovic, D. (2016) Deep NeuralNetworks Based Recognition of Plant Diseases byLeaf Image Classification. ComputationalIntelligence and Neuroscience. 11 p.
  19. Sobkowiak, B. (2006) Zastosowanie technikanalizy obrazu do wczesnego wykrywaniapatogenow ziemniaka. Praca nie publicowana.Poznan: PIMR.
  20. Sobkowiak, B. (2007) Zastosowanie technikanalizy obrazu do wczesnego wykrywania zarazyziemnechanej w warynkach polowych. Praca niepublicowana. Poznan: PIMR.
  21. Nikolenko, S., Kadurin, A., Arkhangel'skaya, Ye.(2018) Glubokoye obucheniye. SPb.: Piter. 480 s.
  22. Tensorflow API documentation. Available from:https://www.tensorflow.org/api_docs/python/tf/nn/softmax_cross_entropy_with_logits_v2

View full text (PDF)