20.500.12556/RUL-152987 Sistem za sledenje stikov z uporabo analize videa Contact tracing system utilizing video analysis Pandemija COVID-19 je pokazala pomembnost sledenja stikov za omejitev širjenja okužb. Težava sistemov za sledenje, ki zahtevajo uporabo aplikacij in s tem obremenjujejo uporabnike, je, da se ne uporabljajo, ko pandemije ni. V tem magistrskem delu je predstavljen sistem za iskanje bližnjih stikov, ki predstavlja neinvazivno rešitev sledenja stikov v stavbah. Sistem je sestavljen iz dveh podsistemov. Podsistem za nadzor kamer nam omogoča, da upoštevanje varne razdalje med osebami spremljamo v živo in ga enostavno integriramo v obstoječe sisteme kamer. Podsistem za iskanje bližnjih stikov pa nam omogoča, da najdemo vse bližnje stike določene osebe, a le, ko je to zahtevano. S tem prihranimo vire in vzdržujemo zasebnost obiskovalcev. Za potrebe zaznave in identifikacije oseb je bil razvit učinkovit model Eff-SeqNet, ki se lahko izvaja in uči na grafičnih procesnih enotah, ki so dostopne končnim uporabnikom. S tem smo pokazali, da lahko s smiselno izbiro arhitekture modela dosežemo dober kompromis med natančnostjo in hitrostjo zaznave. Poleg učinkovitega modela smo predstavili cevovod iskanja stikov, ki izrablja informacije o lokaciji in povezavah med kamerami in s tem izboljša robustnost in učinkovitost sistema. The COVID-19 pandemic highlighted the importance of contact tracing to limit the spread of infections. The problem with tracing systems that require the use of apps and other approaches, which burden users, is that they often go unused outside of a pandemic. This master's thesis introduces a system for identifying close contacts, offering a non-invasive solution for contact tracing within buildings. The system comprises two parts: the camera surveillance system allows for real-time monitoring of social distancing between individuals and can be easily integrated into existing camera systems. The close-contact detection system enables us to identify all the close contacts of a specific person, but only when necessary. This conserves resources and maintains the privacy of visitors. For the purposes of detection and identification of individuals, an efficient model named Eff-SeqNet was developed, which can be used on graphical processing units available to end users. With this, we demonstrated that by making a thoughtful choice in model architecture, a good balance between detection accuracy and speed can be achieved. In addition to the new efficient model, we introduced a person search pipeline utilizing information about position and connections between cameras, which improves the robustness as well as the efficiency of our system. detekcija oseb ponovna identifikacija iskanje oseb sledenje stikov person detection person re-identification person search contact tracing true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2023-12-13 14:10:01 2023-12-13 14:10:08 2023-12-22 10:23:14 0000-00-00 00:00:00 2023 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 35425 178646019 Kastelec_Erik_-_Sistem_za_sledenje_stikov_z_uporabo_analize_videa.pdf Kastelec_Erik_-_Sistem_za_sledenje_stikov_z_uporabo_analize_videa.pdf 1 F99380C8EAEBFCD12695C55D8117CDE4 ad2aa1ba57bc7009bcbbc3eaa5834f9957ebb649ad8fcf83bb15cf44eb2f493d f0884264-99b8-11ee-9499-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=178755 Fakulteta za računalništvo in informatiko 0 0 0