Miro Petković, Danko Kezić,
Igor Vujović, Ivan Pavić
University of Split (Croatia)
https://doi.org/10.53656/ped21-7s.14targ
Abstract. Automatic Identification Systems (AIS) and Automatic Radar Plotting Aids (ARPA) are commonly used to detect targets for collision avoidance. However, AIS cannot detect targets without AIS transmitters and ARPA has limitations due to blind sector and small targets may not be detected. Advances in computer performance and video-based detection generated much interest in developing intelligent video surveillance systems to achieve autonomous navigation. To develop a reliable collision avoidance system, we propose the use of a visual camera for real-time object detection and target tracking. Moreover, the system should follow the International Regulations for Preventing Collisions at Sea (COLREGs) to avoid catastrophic accidents. In this paper only a part of the system is presented. For real-time object detection, the You Only Look Once (YOLO) ver. 3 convolutional neural network is used, and the target tracking filter based on a Kalman filter with built-in estimated relative position and velocity.
Keywords: collision avoidance; MASS COLREGs; YOLO; kalman filter
Свързани статии:
DIDACTIC MODEL FOR GENERATING A SYSTEM
OF PROBLEMS BASED ON THE TECHNOLOGICAL APPROACH
Centralisation And Decentralisation In Higher Education: A Comparative Study Of Hungary And Germany
Категориални и некатегориални значения на рода, числото и падежа при личните местоимения (руско-български паралели)
Научен проект „България в италианските и във ватиканските архиви“: първи резултати от анализ на ватиканския вестник „Осерваторе Романо“
