Artificial intelligence technologies in precision agriculture

• Autorzy: Pawłowski T. , Ganchenko V. , Doudkin A. , Petrovsky A.
• Języki publikacji: EN

Abstrakty

EN

Image processing, object classification and artificial neural network algorithms are considered in the paper applying to disease area recognition of agricultural field images. The images are presented as reduced normalized histograms. The classification is carried out for RGB-and HSV-space by using a multilayer perceptron.

Słowa kluczowe

EN

precision agriculture; perceptron; disease detection; object classification; training sample

• Wydawca: Sieć Badawcza Łukasiewicz - Poznański Instytut Technologiczny
• Czasopismo: Journal of Research and Applications in Agricultural Engineering
• Rocznik: 2013
• Tom: Vol. 58, nr 2
• Strony: 119--126
• Opis fizyczny: Bibliogr. 18 poz., rys., tab.

Twórcy

autor

Pawłowski T.

• Industrial Institute of Agricultural Engineering ul. Starołęcka 31; 60-963 Poznań, Poland

autor

Ganchenko V.

• United Institute of Informatics National Academy of Science, Minsk, Belarus

autor

Doudkin A.

• United Institute of Informatics National Academy of Science, Minsk, Belarus

autor

Petrovsky A.

• United Institute of Informatics National Academy of Science, Minsk, Belarus

Bibliografia

• [1] Aksoy S.: Automatic Mapping of Linear Woody Vegetation Features in Agricultural Landscapes Using Very High-Resolution Imagery / S. Aksoy, H.G. Akcay, T. Wassenaar // IEEE Transactions on Geoscience and Remote Sensing. – January 2010, No. 48 (1, 2), p. 511-522.
• [2] Belyaev B.I.: Optical remote sensing / B.I. Belyaev, L.V. Katkovsky. – Minsk: BSU, 2006, 455 p. [In russian].
• [3] Burks T.F.: Classification of weed species using color texture features and discriminant analysis / T.F. Burks, S.A. Shearer, F.A. Payne // Transactions of ASAE, 2000, Vol. 43(2), p. 441-448.
• [4] Carpenter G.A.: A neural network method for efficient vegetation mapping / G.A. Carpenter, S. Gopal, C.E. Woodcock // Remote Sensing Environment, 1999, Vol. 70, No. 9, p. 326-338.
• [5] Coleman G.B.: Image segmentation by clustering / G.B. Coleman, H.C. Andrews // Proc IEEE, 1979, Vol. 67. p. 773–785.
• [6] Ganchenko V.: Joint segmentation of Aerial Photographs with the Various Resolution / V. Ganchenko, A. Petrovsky, B. Sobkoviak // Proc. of the 5th Int Conf on Neural Networks and Artificial Intelligence ICNNAI 2008, May 27-30, Minsk, Belarus, p. 177-181.
• [7] Haykin S.: Neural networks: A Comprehensive Foundation, Second Edition. – Pearson Education, Inc, 2005, 823 pp.
• [8] Remote sensing of vegetation using modular neural networks / N. Kussul [et al.] // Proceedings of the III International Conferences on Neural Networks and Artificial Intelligence (ICNNAI'2003), November 12-14, Minsk, Belarus, 2003. Minsk: Publishing center of BSU, 2003, p. 232-234.
• [9] Qin Z.: Detection of rice sheath blight for in-season disease management using multispectral remote sensing / Zhihao Qin, Minghua Zhang // International Journal of Applied Earth Observation and Geoinformation, 2005. Vol. 7, Issue 2, p. 115-128.
• [10] Rubtsov S.A.: Aerospace equipment and technologies for precision farming / S.A. Rubtsov, I.N. Golovanev. A.N. Kashtanov. M., 2008, 330 p. [In russian].
• [11] Special Areas Detection on Agricultural Fields Images Using Evaluations of Local Brightness Variability / R. Sadykhov, A. Doudkin, V. Ganchenko, A. Petrovsky, T. Pawlowski// Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS'2011): Proceedings of The 6th IEEE International Conference (September 15-17, 2011, Prague, Czech Republic). Prague, 2011, p. 231-235.
• [12] Using high spatial resolution nniltispectral data to classify corn and soybean crops / G.B. Senay [et al.] // Photogrammetric engineering and remote sensing, 2000, Vol. 66, No. 3. p. 319-327.
• [13] Sofou A.: Soil image segmentation and texture analysis: a computer vision approach / A. Sofou. G. Evangelopoulos, P. Maragos // IEEE Geoscience and Remote Sensing Letters, 2005, Vol. 2, p. 394-398.
• [14] Torre M.: Agricultural field extraction on aerial images by region competition algorithm / M. Torre, P. Radeva // Int. Conf. on Pattern Recognition (ICPR'00), September 3-8, 2000, Barcelona, Spain, p. 137-139.
• [15] Tseng Y.H.: Automatic detecting rice fields by using multispectral satellite images, land-parcel data and domain knowledge / Y.H. Tseng, P.H. Hsu, Y.H. Chen // Proceedings of the 19th Asian Conference on Remote Sensing, Manila, Philippines, 16-20 November, 1998. Minsk. p. R–1–1~R–1–7.
• [16] Multi-sensor NDVI data continuity: Uncertainties and implications for vegetation monitoring applications / W.J.D. vanLeeuwen [et al.] // Remote Sensing of Environment, 2006, Vol. 3, p. 67-81.
• [17]Wu Lanlan.: Identification of weed/corn using BP network based on wavelet features and fractal dimension / Lanlan Wu, Youxian Wen, Xiaoyan Deng, Hui Peng // Scientific Research and Essay, November, 2009. Vol.4 (11). p. 1194-1200.
• [18] A neural network method for efficient vegetation mapping / C.C. Yang [et al.] // Recognition of Weeds with Image Processing and their use with Fuzzy Logic for Precision Farming. Canadian Agricultural Engineering, 2000, No. 42(4), p. 195-200.