Gaussian Neural Network Training Method for Solving the Problem of Multispectral Satellite Images Recognition

The methods of Gaussian computer vision and machine learning used to process multispectral satellite images in the detection and recognition of research objects --- banana plantations in the area of El Porvenir on the coast of Ecuador --- are considered. Using computer vision and machine learning techniques, processing of multispectral satellite images and indirect raster data after calculating NDVI and NDWI vegetation indices, classification of vegetation and water objects was performed. The analysis of multispectral satellite image data is complicated by the presence of clouds and rasters that do not contain data other than the object of study. The machine learning method when labeling data with validation by vegetation indices is used in segmentation of classes that do not participate in the computer vision analysis in the detection and recognition of the research object. The probability of the given positive experimental results is ~ 96 %. The proposed methods of objects detection and recognition on multispectral satellite images can be implemented in agricultural systems to improve, analyze and assess the needs of crops, which are part of agriculture as the primary sector of the economy, to meet the needs of food and raw materials production. Thus, with the increased demand for agricultural products, it is necessary to introduce technologies that guarantee the quality and high productivity of agricultural machinery

References

[1] Lindeberg T. Scale selection properties of generalized scale-space interest point detectors. J. Math. Imaging Vis., 2013, vol. 46, no. 2, pp. 177--210. DOI: https://doi.org/10.1007/s10851-012-0378-3

[2] Lindeberg T. Feature detection with automatic scale selection. Int. J. Comput. Vis., 1998, vol. 30, no. 2, pp. 77--116. DOI: https://doi.org/10.1023/A:1008045108935

[3] Smirnov K.A., Volkov V.A. [Automated method for detection of arctic icebergs on satellite images]. 14 Vseros. otkrytaya konf. "Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa" [14th Russ. Open Conf. "Modern Issues of Earth Remote Sensing from Space"]. Moscow, IKI RAS Publ., 2016, p. 50 (in Russ.).

[4] Marr D., Hildreth E. Theory of edge detection. Proc. Royal Soc. Lond., 1980, vol. 207, no. 1167, pp. 187--217. DOI: https://doi.org/10.1098/rspb.1980.0020

[5] Lindeberg T. Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus-of-attention. Int. J. Comput. Vis., 1993, vol. 11, no. 3, pp. 283--318. DOI: https://doi.org/10.1007/BF01469346

[6] Olsen O.F. Multi-scale watershed segmentation. In: Gaussian scale-space theory. New York, Springer, 1997, pp. 191--200.

[7] Lindeberg T. On scale selection for differential operators. Proc. 8th SCIA, 1993, pp. 857--866.

[8] Lindeberg T. Edge detection and ridge detection with automatic scale selection. Int. J. Comput. Vis., 1998, vol. 30, no. 2, pp. 117--154. DOI: https://doi.org/10.1023/A:1008097225773

[9] Lindeberg T., Garding J. Shape from texture from a multi-scale perspective. Proc. ICCV, 1993, pp. 683--691. DOI: https://doi.org/10.1109/ICCV.1993.378146

[10] Swain M., Ballard D. Color indexing. Int. J. Comput. Vis., 1991, vol. 7, no. 1, pp. 11--32. DOI: https://doi.org/10.1007/BF00130487

[11] Lowe D. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 2004, vol. 60, no. 2, pp. 91--110. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94

[12] Slater D., Healey G. Combining colour and geometric information for illumination invariant recognition of 3D objects. Proc. ICCV, 1995, pp. 563--568. DOI: https://doi.org/10.1109/ICCV.1995.466889

[13] Gevers T., Smeulders A.W.M. Color-based object recognition. Pattern Recognit., 1999, vol. 32, no. 3, pp. 453--464. DOI: https://doi.org/10.1016/S0031-3203(98)00036-3

[14] Geusebroek J.M., van den Boomgaard R., Smeulders A.W.M., et al. Color invariance. IEEE Trans. Pattern Anal. Mach. Intell., 2001, vol. 23, no. 12, pp. 1338--1350. DOI: https://doi.org/10.1109/34.977559

[15] Hall D., de Verdiere V., Crowley J. Object recognition using coloured receptive fields. Proc. ECCV, pp. 164--177. DOI: https://doi.org/10.1007/3-540-45054-8_11

[16] Lindeberg T. A computational theory of visual receptive fields. Biol. Cybern., 2013, vol. 107, no. 6, pp. 589--635. DOI: https://doi.org/10.1007/s00422-013-0569-z

[17] Truong T., Dinh A., Wahid K. An IoT environmental data collection system for fungal detection in crop fields. Proc. IEEE 30th CCECE, 2017. DOI: https://doi.org/10.1109/CCECE.2017.7946787

[18] Wolfert S., Ge L., Verdouw C., et al. Big data in smart farming a review. Agric. Syst., 2017, vol. 153, pp. 69--80. DOI: https://doi.org/10.1016/j.agsy.2017.01.023

[19] Patil S.S., Thorat S.A. Early detection of grapes diseases using machine learning and IoT. Proc. 2nd Int. Conf. CCIP, 2016. DOI: https://doi.org/10.1109/CCIP.2016.7802887

[20] Pallavi S., Mallapur J.D., Bendigeri K.Y. Remote sensing and controlling of greenhouse agriculture parameters based on IoT. Proc. Int. Conf. BID, 2017, pp. 44--48. DOI: https://doi.org/10.1109/BID.2017.8336571

[21] Campbell J.B., Wynne R.H. Introduction to remote sensing. New York, The Guilford Press, 2011.

[22] Gao B. NDWI --- a normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens. Environ., 1996, vol. 58, no. 3, pp. 257--266. DOI: https://doi.org/10.1016/S0034-4257(96)00067-3

[23] Druki A.A., Spitsyn V.G., Bolotova Yu.A., et al. Semantic segmentation of Earth scanning images using neural network algorithms. Izvestiya TPU. Inzhiniring georesursov [Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering], 2018, vol. 329, no. 1, pp. 59--68 (in Russ.).