Pregled bibliografske jedinice broj: 1142951
Target detection for visual collision avoidance system
Target detection for visual collision avoidance system // Pedagogika-Pedagogy, 93 (2021), 7s; 159-166 doi:10.53656/ped21-7s.14targ (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1142951 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Target detection for visual collision avoidance
system
Autori
Petković, Miro ; Kezić, Danko ; Vujović, Igor ; Pavić, Ivan
Izvornik
Pedagogika-Pedagogy (0861-3982) 93
(2021), 7s;
159-166
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
collision avoidance ; MASS ; COLREGs ; YOLO ; kalman filter
Sažetak
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.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Tehnologija prometa i transport
POVEZANOST RADA
Projekti:
VLASTITA-SREDSTVA-pfst-2018-03 - Uspostava referalne baze za istraživanje utjecaja vremenskih prilika na video nadzor u pomorskom prometu (ERDBSIWCMVS) (Vujović, Igor, VLASTITA-SREDSTVA - Interni poziv ustanove) ( CroRIS)
Ustanove:
Pomorski fakultet, Split
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Emerging Sources Citation Index (ESCI)
Uključenost u ostale bibliografske baze podataka::
- Web of Science: JCR
- ERIH PLUS
- RSCI
- EBSCOhost