Pregled bibliografske jedinice broj: 1146177
Vision-based system for a real-time detection and following of UAV
Vision-based system for a real-time detection and following of UAV // 2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)
London, Ujedinjeno Kraljevstvo: Institute of Electrical and Electronics Engineers (IEEE), 2019. str. 156-159 doi:10.1109/reduas47371.2019.8999675 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1146177 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Vision-based system for a real-time detection and following of UAV
Autori
Barisic, Antonella ; Car, Marko ; Bogdan, Stjepan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS)
/ - : Institute of Electrical and Electronics Engineers (IEEE), 2019, 156-159
Skup
Workshop on Research, Education and Development of Unmanned Aerial Systems (RED-UAS)
Mjesto i datum
London, Ujedinjeno Kraljevstvo, 25.11.2019. - 27.11.2019
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
object detection ; unmanned aerial vehicle ; target tracking
Sažetak
In this paper a vision-based system for detection, motion tracking and following of Unmanned Aerial Vehicle (UAV) with other UAV (follower) is presented. For detection of an airborne UAV we apply a convolutional neural network YOLO trained on a collected and processed dataset of 10, 000 images. The trained network is capable of detecting various multirotor UAVs in indoor, outdoor and simulation environments. Furthermore, detection results are improved with Kalman filter which ensures steady and reliable information about position and velocity of a target UAV. Preserving the target UAV in the field of view (FOV) and at required distance is accomplished by a simple nonlinear controller based on visual servoing strategy. The proposed system achieves a real-time performance on Neural Compute Stick 2 with a speed of 20 frames per second (FPS) for the detection of an UAV. Justification and efficiency of the developed vision-based system are confirmed in Gazebo simulation experiment where the target UAV is executing a 3D trajectory in a shape of number eight.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Projekti:
EK-H2020-810321 - Twinning koordinacijska akcija za širenje izvrsnosti i sudjelovanja u zračnoj robotici – AeRoTwin (AeRoTwin) (Bogdan, Stjepan, EK ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb