Neural network technology adaptation to the small-size objects identification in satellite images of insufficient resolution within the graphic reference images database
A novel flowchart for small-size objects identification in satellite images of insufficient resolution within the graphic reference images database using neural network technology based on compromise contradiction, i.e. simultaneously the resolution enhancement of the object segment of input image and the resolution reduction of the reference image to joint resolution through the simulation of the imaging system has been proposed. This is necessary due to a significant discrepancy between the resolutions of the input image and the graphic reference images used for identification. The required level of resolution enhancement for satellite images, as a rule, is unattainable, and a significant coarsening of reference images is undesirable because of identification errors. Therefore, a certain intermediate spatial resolution is used for identification, which, on the one hand, can be obtained, and on the other the loss of information contained in the reference image is still acceptable. The intermediate resolution is determined by simulating the process of image acquisition with satellite imaging system. To facilitate such simulation, it is advisable to perform it in the frequency domain, where the advanced Fourier analysis is available and, as a rule, all the necessary transfer properties of the links of image formation chain are known. Three main functional elements are engaged for identification: an artificial neural network for the resolution enhancement of input images, a module of frequency-domain simulating of the graphical reference satellite imaging and an artificial neural network for comparing the enhanced object segment with the reference model images. The feasibility of the described approach is demonstrated by the example of successful identification of the sea vessel image in the SPOT-7 satellite image. Currently, the works are under way to compare the performance of a neural network platforms variety for small-size objects identification in satellite images aa well as to assess achievable accuracy.
Abramov, N. S., Makarov D. A., Talalaev A. A., Fralenko, V. P. (2018). Modern methods of intelligent processing of remote sensing data. Programmnye sistemy: teoriya i prilozheniya, 9 (4), 417–442. (in Russian)
Dong, C., Loy, C.C., He, K., & Tang, X. (2016). Image superresolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38 (2), 295– 307.
Elham, K., Kaveh, K., & Javadi, S. (2014). A survey on superresolution methods for image reconstruction. International Journal of Computer Applications, 90 (3), 32–39
Kaftannikov, I. L., Parasich, A.V. (2016). Problems of forming a training sample in machine learning tasks. Vestnik YuUrGU. Seriya Kompyuternye tekhnologii, upravlenie, radioelektronika, 16 (3), compact target samples in aerospace imagery visual interpretation support system. Abstracts of the ІІI Scientific Conference Aerospace Technologies in Ukraine: Problems and Prospects, 33–34. Kiev: NSFCTC.
Lavrinchuk, O.V., Hryniuk, S.V. & Rakushev, M.Yu. (2017). Analysis of the technology of space images decryption. Suchasni informacijni tekhnologhiji u sferi bezpeky ta oborony, 30 (3), 45-49. (in Ukrainian).
Lim, B., Son, S., Kim, H., Nah, S., & Lee, K.M. (2017). Enhanced deep residual networks for single image super-resolution. Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR 2017), 136-144. Honolulu: IEEE.
Maggiori, E., Charpiat, G., Tarabalka, Y. & Alliez, P. (2017). Recurrent neural networks to correct satellite image classification maps. IEEE Transactions on Geoscience and Remote Sensing, 55 (9), 4962-4971.
Markova, S.V. & Zhigalov, K.Yu. (2017). Neural network application for purposes of recognition of images. Fundamentalnye issledovaniya, 8 (1), 60-64. (in Russian).
Piestova, I., Stankevich, S., & Kostolny, J. (2017). Multispectral imagery superresolution with logical reallocation of spectra. Proceedings of the International Conference on Information and Digital Technologies (IDT 2017), 322–326. Žilina: IEEE.
Rawat, W. & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29 (9), 2352–2449.
Schachter, B.J. (2018). Automatic Target Recognition. Bellingham: SPIE Press.
Stankevich, S. A., Shklyar, S. V. (2005). Optimization of the parameters of the species aerial photography equipment under the condition of the maximum average probability of detection of objects in the image. Zbirnyk naukovykh pracj Derzhavnogho naukovo-doslidnogho instytutu aviaciji, 8 (2), 133–136. (in Ukrainian).
Stankevich, S.A. & Maslenko, O.V. (2019). Automated identification of compact target samples in aerospace imagery visual interpretation support system. Abstracts of the ІІI Scientific Conference “Aerospace Technologies in Ukraine: Problems and Prospects”, 33-34. Kiev: NSFCTC.
Tang, C., Zhu, Q., Wu, W., Huang, W., Hong, C. and Niu, X. (2020). PLANET: Improved convolutional neural networks with image enhancement for image classification. Mathematical Problems in Engineering, 20, 1245924.
Tatyankin, V. M. (2016). An approach to the formation of a neural network architecture for pattern recognition. Vestnik Yugorskogo gosudarstvennogo universiteta, 2 (41), 61–64. (in Russian).
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy, C.C. (2018). ESRGAN: enhanced super-resolution generative adversarial networks. Proceedings of the European Conference on Computer Vision (ECCV 2018), 63–79. Cham: Springer.