Web service with machine learning model for airspace monitoring

Objective. The goal is to develop a web service for detecting aerial objects that detects a flying object, highlights it in an image and classifies it as a threat, since modern aerial object detection systems do not always cope with the task of detecting unmanned aerial vehicles due to their small size, low flight altitude and the use of materials that are barely noticeable to radar stations. Unmanned aerial vehicles that operate without operator control make it difficult to detect by radio signals. To detect UAVs, it is proposed to use a system based on optical scanning of the sky around protected objects. The system should be capable of autonomous operation and include aerial object detectors created on the basis of computer vision and artificial intelligence technologies. Method. The research and development of the airspace monitoring web service are based on the methods of system analysis, synthesis, and deduction. Result. The visual part of the web interface has been designed and developed; a dataset has been formed from open sources for the correct detection of flying objects; a neural network detector has been developed for classifying flying objects that pose a danger; a software module has been developed that allows for the automatic detection of identification flags of dangerous air objects with subsequent provision of reports in txt files in yolo format (coordinates are normalized). Conclusion. Separation of the visual part of the service will allow for distributed deployment of the server part, increasing flexibility and scalability. Development of the administrator control panel will allow for effective control of the service, management of settings and users. As a result, the web service will be able to: monitor the sky around protected objects, automatically detecting and classifying air objects and identifying air objects by threat level, providing information for taking necessary measures.

1. Unmanned aerial vehicles: bibliographic index. Compiled by O. V. Davydenko; edited by N. N. Astapova. - Kemerovo: IIO Kuzbass State Agricultural Academy, 2021; 23. (In Russ)

2. Astakhova N. L., Lukashov V. A. Drones and their piloting. Where to start. St. Petersburg: BHVPetersburg, 2021; 224l. (In Russ)

3. Dudkin A. A., Ganchenko V. V., Inyutin A. V., Marushko E. E. Identification and classification of objects in images obtained using UAV and orbital-based survey equipment. Systems analysis and applied informatics. 2022; 4.: 30–37. (In Russ)

4. Bubenshchikov A.A., Kastyrin M.I., Potaenkov G.O. Development of a hardware and software module for detecting and identifying UAVs with a ban on their access to a protected area based on the substitution of control signals. In the collection: Technology and safety of penal system facilities. collection of materials of the International scientific and practical conference. Ivanovo, 2022; 186–189. (In Russ)

5. Creation and deployment of computer vision models//https://roboflow.com/ (date of access 01.06.2024).

6. Strukov S.A., Pechenkin A.Yu., Belosludtsev V.N. Implementation of the principles of determining the distance to objects based on an artificial neural network. In the collection: Instrument making in the 21st century – 2022. integration of science, education and production. Collection of materials of the XVIII AllRussian scientific and technical conference. Izhevsk, 2023;56–60. (In Russ)

7. Tsurikhin O.I.,Sokolnikov V.V.The process of creating a sample for training a neural network using Roboflow. Information technologies in construction, social and economic systems. 2024;1–2(31–32):58–61. (In Russ)

8. Ochkov V.F., Tikhonov A.I., Stevens A. Jupyter notebook, Jupyterlab-integrated environment for stem education. 2022 6th International Conference on Information Technologies in Engineering Education, Inforino 2022 - Proceedings. 6. 2022.

9. Ilyichev V.Yu. Application of the OpenCV library of the Python language for object pattern recognition // System administrator. 2021;7-8 (224-225):130-132. (In Russ)

10. Practical application of YOLO and ResNet models for detecting unwanted objects in photographs // URL: https://habr.com/ru/articles/761200/ (date of access 01.06.2024) (In Russ)

11. Chae M.S., Lee H.M., Lee K. A. Performance comparison of Linux containers and virtual machines using Docker and Kvm. Cluster Computing. 2019; 22(l. 1):1765–1775.

12. Zakharchenko V.F., Bizyuk A.N. Containerization and deployment of applications using Docker and Docker-compose. In the collection: Proceedings of the 56th international scientific and technical conference of teachers and students. in two volumes. Vitebsk; 2023:80–82.