IMPROVING THE SYSTEM OF VISUAL DETECTION AND OVERCOMING OBSTACLES FOR UNMANNED AERIAL VEHICLE
DOI:
https://doi.org/10.26906/SUNZ.2023.1.040Keywords:
unmanned aerial vehicle, overcoming obstacles, visual planning, glare detection, atmospheric precipitation, image processingAbstract
Most critical tasks are performed by unmanned aerial vehicles (UAV) under the control of an operator. However, the interaction of a robot and an operator in modern conditions is no longer management in the traditional form. Modern UAV are equipped with technical vision systems, databases and knowledge, on the basis of which the aircraft can make decisions independently. The robot's knowledge base allows it to independently navigate the environment and make decisions regarding the completion of the assigned task. The functions of the human operator now consist of setting tasks for the robot in a problemoriented language, close to natural, and observing the actions of the robot. Visual planning is an extension of planning and obstacle avoidance methods for tasks in which the source of information about the environment is technical vision systems based on video cameras or scanning systems. The article provides an overview of visual planning methods. A large number of existing image processing methods and algorithms and their possible combinations make it possible to solve a wide variety of problems, to constantly improve existing algorithms and thereby increase the efficiency of image processing. But whatever method is used for visual planning, there are problems of obtaining quality input information related to meteorological conditions caused by precipitation and fog, and glare if the image is obtained using a video camera. It can be sun glare or glare from other lighting sources. The article proposes a technique for detecting and removing reflections from the image. Since the basic information about the environment that the robot analyzes depends on the quality of the image, appropriate methods that take atmospheric precipitation into account are needed. The article analyzes the methods of excluding various types of precipitation from the image and draws conclusions about the state of their development.Downloads
References
Burschka D., Geiman J., Hager G. Optimal landmark configuration for vision-based control of mobile robots [Text] // Proc. of 2003 IEEE ICRA, Taipei, Taiwan, Sept. 14–19, 2003. P. 3917–3922.
Hayet J.B., Lerasle F., Devy M. Visual Landmarks Detection and Recognition for Mobile Robot Navigation [Text] // Proc. of 2003 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR’2003). Madison, Wisconsin, USA, 2003. V. II. P.313–318.
Jurie F., Dhome M. Hyperplane Approximation for Template Matching [Text] // IEEE. Trans. on Pattern Analysis and Machine Intelligence. 2002. V. 24, №7. P. 996–1000.
Lourakis M. I.A., Orphanoudakis S. C. Visual Detection of Obstacles Assuming a Locally Planar Ground. [Text] // Technical Report FORTH-ICS, TR-207. 1997.
Lorigo L. M., Brooks R.A., Grimson W. E. L. Visually-Guided Obstacle Avoidance in Unstructured Environments [Text] // Proc. of IEEE Conf. on Intelligent Robots and Systems, 1997. Р. 373–379.
Santos-Victor J., Sandini G., Curotto F., Garibaldi S. Divergent stereo in autonomous navigation: from bees to robots [Text] // Intern. J. of Computer Vision. 1995. Р. 159–177.
Coombs D., Herman M., Hong T., Nashman M. Real-time Obstacle Avoidance Using Central Flow Divergence and Peripheral Flow [Text] // IEEE Transactions on Robotics and Automation. 1995. Р. 276–283.
Klein K., Sequeira V. View planning for the 3D modelling of Real World Scenes [Text] // 2000 IEEE/RSJ IROS. 2000. V. II. Р. 943–948.
Ганченко В.В., Дудкин А.А., Инютин А.В., Поденок Л.П. Моделирование оптико-электронной системы беспилотных летательных аппаратов [Текст] // «Штучний інтелект» № 3. – 2010. – С. 453-461.
Проценко М.М. Аналіз методів цифрової обробки відеозображень апаратурою безпілотного літального апарата [Текст] // Вісник ЖДТУ № 3(62). – 2012. – С. 67-72.
Толкунова Ю.М. Розробка системи подолання перешкод для безпілотного літального апарату [Текст] // Національний університет «Полтавська політехніка імені Юрія Кондратюка», Control, Navigation and Communication Systems № 2, – 2022. – С. 32-36.
Hossen, J. A. Modified Hybrid Fuzzy Controller for Real-Time Mobile Robot Navigation [Text] / J. Hossen, S. Sayeed, A.K.M. Parvez Iqbal // Procedia Computer Science. – 2015. – V.76. – P. 449-454.
Algabri, M. Comparative study of soft computing techniques for mobile robot navigation in an unknown environment [Text] / M. Algabri, H. Mathkour, H. Ramdane, M. Alsulaiman // Computers in Human Behavior. – 2015. – V.50. – P. 42-56.
Гонсалес Р. Цифровая обработка изображений [Текст] / Р. Гонсалес, Р. Вудс – М.: Техносфера, 2012. – 1104 с.
Jia Z., Wang H., Caballero R.E. et al. A two-step approach to see-through bad weather for surveillance video quality enhancement [Text] // Machine Vision and Applications. 2012. V. 23. No. 6. –P. 1059-1082.
Технології створення мультимедіа застосувань [Електронний ресурс] // Конспект лекцій для здобувачів вищої освіти першого (бакалаврського) рівня за освітньо-професійною програмою «Інженерія програмного забезпечення» / Укладач О. О. Шумейко. – Кам’янське: ДДТУ, 2019 – 169 с.
Гонсалес Р. Цифровая обработка изображений в среде MATLAB [Текст] / Р. Гонсалес, Р. Вудс, С. Эддинс – М.: Техносфера, 2006. – 616 с.
Garg K., Nayar S.K. Vision and rain [Text] // Intern. J. Computer Vision. 2007. V. 75. No. 1. P. 3–27.
Экземпляров Р. А. Устойчивые численные методы математического моделирования задачи восстановления искаженных изображений [Текст] : диссертация кандидата техн. наук : 05.13.18 / Экземпляров Роман Алексеевич. – СПб., 2018. – 125 с.
Zhang X., Li H., Qi Y., Leow W.K., Ng T.K.: Rain removal in video by combining temporal and chromatic properties [Text] // In: Proceedings of 2006 IEEE International Conference on Multimedia and Explosion, pp. 461–464 (2006).
Garg K., Nayar S.K. When does a camera see rain? [Text] // in Proc. ICCV 2005. V. 2. P. 1067–1074.
Garg K., Nayar S.K. Detection and removal of rain from videos [Text] // in Proc. CVPR 2004, V. 1. P. 528–535.
Kratz L., Nishino K. Factorizing scene albedo and depth from a single foggy image [Text] // In: Proceedings of 2009 IEEE 12th International Conference on Computer Vision, pp. 1701–1708.
Barnum P., Narasimhan S.G., Kanade T. Analysis of rain and snow in frequency space [Text] // International Journal of Computer Vision. 2010. V86. P. 256–274.
Zelnik-Manor L., Machline M., & Irani M. Multi-body factorization with uncertainty: Revisiting motion consistency [Text] // International Journal of Computer Vision. 2006. V68(1). P. 27–41.
