20.500.12556/RUL-175562 Odstranjevanje senc z ortofoto slik Removing shadows from orthophoto images V magistrski nalogi obravnavamo problem odstranjevanja senc iz ortofoto slik, kar predstavlja izziv zaradi pomanjkanja ustreznih učnih podatkov. Za reševanje problema smo razvili inovativen pristop. Ta vključuje izdelavo lastne zbirke z generiranjem podatkov s pomočjo okolja Unity, kjer uporabimo ortofoto kot sloj terena in 3D modele stavb ter rastlinja za izris realističnih senc, ter učenje nevronske mreže U-Net. Model smo ovrednotili na različnih učnih zbirkah in nevronskih mrežah. Ugotovili smo, da je kakovost podatkov ključna za uspešnost učenja, pri čemer naša podatkovna zbirka ponuja konkurenčne rezultate. Glavna prispevka naloge sta obširna učna zbirka in naučen model odstranjevanja senc. In the master's thesis, we address the problem of shadow removal from orthophotography images, which presents a challenge due to the lack of suitable training data. To tackle this issue, we developed an innovative approach. This involves creating our own dataset by generating data using the Unity environment, where we use the orthophoto as a terrain layer and 3D models of buildings and vegetation to render realistic shadows, followed by training a U-Net neural network. We evaluated the model on various training datasets and neural networks. We found that data quality is crucial for successful learning, as evidenced by our dataset's competitive results. The main contributions of the thesis are a comprehensive training dataset and a trained shadow removal model. sence odstranjevanje senc strojno učenje ortofoto shadows shadow removal machine learning orthophoto true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2025-11-04 11:55:34 2025-11-04 11:55:40 2025-12-12 03:48:47 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 37930 257404163 Galjot_Luka_-_Odstranjevanje_senc_z_ortofoto_slik.pdf Galjot_Luka_-_Odstranjevanje_senc_z_ortofoto_slik.pdf 1 A6A6E970F5C67B7D1AA6B711984CD9A8 512dfdef741e449f532623b77d5f06297218d3ad6b7772ddbb7ffa7fbdd1fb73 7dd6b4f7-b96c-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=221318 Fakulteta za računalništvo in informatiko 0 0 0