Automated Visual Information Processing Using Artificial Intelligence
Tóm tắt
The main provisions for solving the complex problem of efficiently processing visual information in an automated optronic ground-space monitoring system using artificial intelligence are presented. The basic relationships and statements of the formally developed body of mathematical tools for processing information in real-time mode are presented. This body of tools has been used for developing the corresponding efficient information and mathematical support for automated optronic systems. The experimental results are presented.
Tài liệu tham khảo
Vizilter, Yu.V. and Zheltov, S.Yu., Problems of technical vision in aviation systems, Mekh. Upr. Inf., 2011, no. 6, pp. 11–44.
Chigrinskii, V.V. and Matveev, I.A., Optimization of a tracking system based on a network of cameras, J. Comput. Syst. Sci. Int., 2020, vol. 59, no. 4, pp. 583–597. https://doi.org/10.1134/S1064230720040127
Smirnov, A.V., Levashova, T.V., and Ponomarev, A.V., Decision support based on human-computer collective intelligence: Methodologies analysis and ontology model, Iskusstv. Intellekt Prinyatie Reshenii, 2020, no. 3, pp. 48–60. https://doi.org/10.14357/20718594200305
Knyazev, V.V. and Lovtsov, D.A., Situational planning of protected measurement data processing in automatic control systems of testing complex dynamic objects, Autom. Remote Control, 1998, vol. 59, no. 9, pp. 1336–1346.
Gavrilov, D.A. and Pavlov, A.V., Streaming hardware based implementation of the SURF algorithm, Izv. Vyssh. Uchebn. Zaved., Electron., 2018, vol. 23, no. 5, pp. 502–511. https://doi.org/10.24151/1561-5405-2018-23-5-502-511
Gavrilov, D.A., Mestetskiy, L.M., and Semenov, A.B., A method for aircraft labeling in aerial and satellite images based on continuous morphological models, Program. Comput. Software, 2019, vol. 45, no. 6, pp. 303–310. https://doi.org/10.1134/S0361768819060021
Gavrilov, D.A., The computer system testing of algorithms for detection and localization of objects in video sequences, Nauchn. Priborostr., 2019, vol. 29, no. 1, pp. 149–156. https://doi.org/10.18358/np-29-1-i149156
Gavrilov, D.A., Neural network algorithm for automatic detection and tracking of an object of interest in a video signal, Shestnadtsataya natsional’naya konf. po iskusstvennomu intellektu s mezhdunarodnym uchastiem KII-2018 (16th National Conf. on Artificial Intelligence with International Participation KII-2018), 2018, Moscow, vol. 2, pp. 188–190.
Pun, A.B., Gavrilov, D.A., Shchelkunov, N.N., and Fortunatov, A.A., Algorithm of adaptive binarization of objects in a video sequence in real time, Usp. Sovrem. Radioelektron., 2018, no. 9, pp. 40–48. https://doi.org/10.18127/j20700784-201809-05
Gavrilov, D.A., Pavlov, A.V., and Shchelkunov, D.N., Hardware implementation for compressing dynamic range of digital images on programmable logical integral circuits XILINX, Zh. Radioelektron., 2018, no. 10. https://doi.org/10.30898/1684-1719.2018.10.6
Gavrilov, D.A. and Shchelkunov, N.N., Software for large format aerospace image marking and training samples preparation, Nauch. Priborostr., 2020, vol. 30, no. 2, pp. 67–75. https://doi.org/10.18358/np-30-2-i6775
Carvana Image Masking Challenge—1st place winner’s interview, Kaggle Winner’s Blog. http://blog.kaggle. com/2017/12/22/carvana-image-masking-first-place-interview/.
Ronneberger, O., Fischer, P., and Brox, T., U-net: Convolutional networks for biomedical image segmentation, Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Navab, N., Hornegger, J., Wells, W., and Frangi, A., Eds., Lecture Notes in Computer Science, vol. 9351, Cham: Springer, 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Lovtsov, D.A. and Gavrilov, D.A., Processing of visual information in the automated optoelectronic system of ground-space monitoring, Informatsionnye Tekhnologii i Nanotekhnologii (ITNT-2020) (Information Technologies and Nanotechnologies), Samara, 2020, pp. 271–276.
Sikorsky, O.S., Review of convolutional neural networks for the problem of image classification, Novye Inf. Tekhnol. Avtom. Sist., 2017, no. 20, pp. 37–42.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A., Inception-v4, inception-ResNet and the impact of residual connections on learning, Proc. Thirty-First AIAA Conf. on Artificial Intelligence, San Francisco, 2017, pp. 4278–4284.
AutoML. https://www.automl.org.
Zoph, B., Vasudevan, V., and Shlens, J., and Le, V.Q., Learning transferable architectures for scalable image recognition, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, pp. 8697–8710. https://doi.org/10.1109/CVPR.2018.00907
Krizhevsky, A., Nair, V., and Hinton, G., The CIFAR-10 dataset. https://www.cs.toronto.edu/~kriz/cifar.html.
Berg, A., Deng, J., and Fei-Fei, L., ImageNet large scale visual recognition challenge (ILSVRC). http://www.image-net.org/challenges/LSVRC/.
COCO: Common objects in context. https://cocodataset.org/#home.
Favreau, J.-D., Lafarge, F., Bousseau, A., and Auvolat, A., Extracting geometric structures in images with Delaunay point processes, IEEE Trans. Pattern Anal. Mach. Intell., 2020, vol. 42, no. 4, pp. 837–850. doi https://doi.org/10.1109/TPAMI.2018.2890586
Gavrilov, D.A., RF Patent 714182, Byull., 2020, No. 5.
Gavrilov, D.A., Quality assessment of object detection and localization in a video stream, Vestn. MGTU N. E. Baumana, Ser. Priborostr., 2018, no. 2, p. 40–55.
Google Earth. https://www.google.com/earth/.
SASGIS: Web-Cartography and Navigation. http://www.sasgis.org/.