A.S. Molchanov1, V.A. Kolomoets2

1,2 V.P. Chkalov State Flight Test Center (Akhtubinsk, Russia)
1 andryoe@yandex.ru, 2 kolomw@yandex.ru

Intelligent systems and complexes are becoming increasingly relevant to improve the accuracy, efficiency and effectiveness of collecting and analyzing information about potential threats. To accept these systems for supply to interested organizations, it is necessary to test them, however, the methodological support used does not take into account the specifics of building, functioning and processing information using artificial intelligence, as well as the need to create a special test database of typical aerial reconnaissance facilities for a reliable assessment of the intellectual capabilities of aerial reconnaissance systems and complexes with integrated elements of artificial intelligence.. As a result, there is a contradiction between the timely commissioning of the latest aerial reconnaissance systems and complexes with artificial intelligence and the imperfection of existing methodological support, which makes it difficult to test them.

Objective – to consider the features of the construction and operation of intelligent systems and aerial reconnaissance complexes and to develop a methodology for forming a test database for evaluating intelligent systems and aerial reconnaissance complexes with integrated artificial intelligence.

The article considers the issues of testing intelligent systems and aerial reconnaissance complexes based on the use of test databases that allow performing procedures for collecting, preparing, separating and training convolutional neural networks. It presents a methodology for forming a test database based on the formation of reference digital portraits obtained in a combined manner using natural digital portraits, due to expert marking of objects in images and synthesized digital portraits, using digital polygons and digital twins of typical aerial reconnaissance objects obtained at different times, under various climatic conditions for various spatial configurations of objects in each degree of detail of information about them.

Testing intelligent systems using digital portraits allows accelerating the process of recognizing and classifying aerial reconnaissance objects, increasing the accuracy of analyzing visual information, and optimizing the operation of reconnaissance systems.

Molchanov A.S., Kolomoets V.A. Testing of intelligent systems and aerial reconnaissance complexes using digital portraits of typical aerial reconnaissance objects. Science Intensive Technologies. 2025. V. 26. № 3. P. 20−31. DOI: https://doi.org/ 10.18127/j19998465-202503-03 (in Russian)

1. Molchanov A.S., Kolomoec V.A. Cifrovye portrety tipovyh ob"ektov vozdushnoj razvedki. M.: Pero. 2025. 194 s. (in Russian).
2. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. preprint arXiv: 1409.1556. 2014.
3. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition, preprint arXiv: 1512.03385, 2015.
4. Russakovsky O., Jia Deng, Hao Su et al. Imagenet large scale visual recognitionchallenge. International journal of computer vision, preprint arXiv: 1409.0575. 2015.
5. Girshick R. Fast R-CNN. IEEE International Conference on Computer Vision (ICCV). preprint arXiv: 1504.08083. 2015.
6. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection, preprint arXiv: 1506.02640. 2015.
7. Liu W. et al. SSD: Single Shot MultiBox Detector. Lecture Notes in Computer Science, vol. 9905. Springer, Cham. Computer Vision – ECCV. preprint arXiv: 1512.02325, 2016.
8. Devis R., Terk M. Komp'yuternoe zrenie. Sovremennye metody i perspektivy razvitiya: Per. s angl. V.S. Yacenkova. M.: DMK Press. 2022. 690 s. (in Russian).
9. Chausov E.V., Molchanov A.S., Kolomoec V.A. i dr. Cifrovye optiko-elektronnye sistemy distancionnogo zondirovaniya Zemli. Osnovy postroeniya, ispytanij i kontrolya: uchebnoe posobie. Pod red. E.V. CHausova. M.: Pero. 2023. 108 s. (in Russian).
10. Molchanov A.S. Teoriya i praktika deshifrirovaniya ob"ektov aviacionnoj tekhniki ikonicheskih optiko-elektronnyh sistem. M: Pero. 2020. 173 s. (in Russian).
11. Rebrin Yu.K. Optiko-elektronnoe razvedyvatel'noe oborudovanie letatel'nyh apparatov. Kiev: KVVAIU. 1988. 450 s. (in Russian).
12. Gorodeckij V.I., Dmitriev A.K. Elementy teorii ispytanij i kontrolya tekhnicheskih sistem. L.: Energiya. 1978. 192 s. (in Russian).
13. Molchanov A.S. Teoriya postroeniya ikonicheskih sistem vozdushnoj razvedki. Volgograd: Panorama. 2017. 224 s. (in Russian).
14. Soldatov E.S., Bogomolov A.V., Larkin E.V., Soldatov A.S. Sensornye seti kontrolya sostoyaniya aviacionnoj tekhniki pri ispytaniyah i ekspluatacii. Aviakosmicheskoe priborostroenie. 2024. № 2. S. 61–68 (in Russian).
15. Chausov E.V., Molchanov A.S. Programmno-metodicheskij kompleks obrabotki izobrazhenij pri provedenii letnyh ispytanij ikonicheskih optiko-elektronnyh sistem. Geodeziya i kartografiya. 2020. T. 81. № 1. S. 26–33 (in Russian).