Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data

Borzov, S. M.; Guryanov, Mark Aleksandrovich; Potaturkin, O. I.

doi:10.18287/2412-6179-2019-43-3-464-473

Cited by 13 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…С. А. Лебедева РАН, 119991, Россия, Москва, Ленинский проспект, д. 51, 2 Московский физико-технический институт (национальный исследовательский университет), 141701, Россия, Московская область, г. Долгопрудный, Институтский переулок, д.9…”

Section: исследование применимости сверточной нейронной сети U-netunclassified

Investigation of the applicability of the convolutional neural network U-Net to a problem of segmentation of aircraft images

Gavrilov¹

2021

Computer Optics

View full text Add to dashboard Cite

The paper investigates the applicability of the convolutional neural network "U-Net" to a problem of segmentation of aircraft images. The neural network image segmentation method is based on the "Carvana" implementation with the "U-Net" architecture. For orientation recognition, a neural network built in the Keras open neural network library based on the pretrained VGG16 neural network is used. The approach considered allows the image segmentation to be conducted. The results of the experiments have shown the possibility of a fairly accurate selection of the object of interest. The resulting binary masks make it possible to visually classify the aircraft in the image.

show abstract

Section: исследование применимости сверточной нейронной сети U-netunclassified

Investigation of the applicability of the convolutional neural network U-Net to a problem of segmentation of aircraft images

Gavrilov¹

2021

Computer Optics

View full text Add to dashboard Cite

show abstract

“…Thus, the randomness of the choice of pixels can provide continuous coverage with fewer standards. The same idea in solving other problems can be traced in [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Optimization of the Composition of Standards in Recognition and Compression Algorithms of Hyperspectral Images

Lebedev

2020

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2

View full text Add to dashboard Cite

The paper proposes a solution to the problem of minimizing the number of standards in order to increase both the compression coefficient of hyperspectral images (HSI) and the speed of correlation extreme compression methods (CEM). As modifications of the CEM, randomized and differential compression algorithms are offered. The randomized and difference algorithms are based on the hypothesis of spatial compactness of pixels located in local regions of the image matrix. This means that when a new template is formed based on an unrecognized pixel, there is a high probability of using a pixel that lies near the boundaries of the coverage areas of the existing templates, which leads to their increase. In order to reduce the influence of spatial compactness of pixels on the formation of standards, a methodology based on changing the sequence of recognized pixels is proposed. In a randomized algorithm, a row of the matrix is randomly determined for this, on the basis of which a sequence of recognized pixels is generated by a random column generator. In the difference algorithm of compression, the row number of the matrix is determined by the rule for finding the members of an arithmetic progression with a given difference. For the selected line a sequence of recognizable pixels is formed on the same principle. It should be noted that line-by-line pixel recognition in the self-learning mode allows compressing HSI of almost any volume. The effectiveness of the created algorithms is demonstrated on two fragments of real HSI. A comparative analysis of all three compression algorithms in terms of the quantitative composition of the obtained standards is presented.

show abstract

Analysis of the Ratio of the Standard Deviations of the Kernel Estimate of the Probability Density with Independent and Dependent Random Variables

Лапко

2021

Meas Tech

View full text Add to dashboard Cite

Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data

Cited by 13 publications

References 27 publications

Investigation of the applicability of the convolutional neural network U-Net to a problem of segmentation of aircraft images

Investigation of the applicability of the convolutional neural network U-Net to a problem of segmentation of aircraft images

Optimization of the Composition of Standards in Recognition and Compression Algorithms of Hyperspectral Images

Analysis of the Ratio of the Standard Deviations of the Kernel Estimate of the Probability Density with Independent and Dependent Random Variables

Contact Info

Product

Resources

About