stručni rad
Deep learning is widespread and thoroughly researched in autonomous vehicles, face recognition, and other similar domains. It is rare in land mine (LM) clearance and other explosive objects clearance domains in the non-military application. This text presents follow thru of previous research using the YOLO algorithm for UXO detection in thermal images by applying it to near real-time detection of annotated explosive objects in a thermal video sequence. The research was conducted on UXOTi_NPA dataset with 11 different explosive targets and original thermal video of very high ground sampling distance taken from an altitude of 3m. YOLO is a fast and accurate model that can achieve detections in more than 40 frames per second (FPS) thus giving viable solutions for 25FPS or 30 FPS thermal videos. Up to date, no automated solutions exist for surface UXO detection by using thermal video that enables large area survey and this research will be a step in that direction.
YOLO, UXO, video
Razvojem virtualizacijskih tehnologija raste kompleksnost IT sustava, dok korisnici istovremeno zahtijevaju brži pristup resursima, napredne integracije i jednostavnost korištenja. Jedno od ključnih rješenja za ove izazove primjena je…
Ovaj rad istražuje i uspoređuje mogućnosti prosljeđivanja grafičkih kartica na Hyper-V i KVM hipervizorima prema virtualnim strojevima, detaljno opisujući metode, postupke i razlike u arhitekturi koje utječu na…
The ever-growing usage and adaptation of HTTP/3 in web traffic leverages Quick UDP Internet Connections (QUIC) as a transport protocol. QUIC is widely recognized for reduced latency, enhanced…
