20.500.12556/RUL-149405 Optimizacija obdelave oblaka točk za robotsko sledenje 3D površini Optimization of point cloud processing for robotic 3D surface tracking Zdravljenje s pomočjo medicinske robotike prinaša številne prednosti pri terapijah. Globinske 3D kamere omogočajo robotom vizualno zaznavanje okolice in s tem prilagajanje terapij v realnem času. Obdelava oblakov točk, zajetih z globinskimi kamerami, je računsko intenzivna, zato je pomembna dobra optimizacija algoritmov. V okviru diplomske naloge smo vzpostavili merilno mesto, analizirali delovanje programske kode in metode za obdelavo oblaka točk. S parametrizacijo smo poskusili optimizirati obdelavo oblaka točk. Izboljšave smo sproti testirali in jih vrednotili. Rezultati so pokazali, da sta algoritma za iskanje najbližje točke in redčenje oblaka točk najbolj računsko zahtevna. Medical robotics treatment brings many benefits in rehabilitation and therapy. 3D depth cameras allow robots to visually sense their surroundings and thus adapt therapies in real time. The processing of point clouds captured by depth cameras is computationally intensive, so good optimisation of algorithms is important. As part of the thesis, we set up a measurement site, analysed the performance of the software code and the methods for processing the point cloud. We tried to optimise the processing of the point cloud by parameterisation. Improvements were tested and evaluated on an ongoing basis. The results showed that the nearest point and point cloud thinning algorithms are the most computationally demanding. optimizacija programiranje 3D globinske kamere ROS PCL C ++ oblaki točk parametrizacija optimization programming 3D depth sensing cameras ROS PCL C ++ point clouds parameterisation true false false [J. Korošec] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2023-09-07 08:30:56 2023-09-07 08:30:57 2023-10-16 09:12:52 0000-00-00 00:00:00 2023 0 Ljubljana 0 XX, 45 str. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.4:007.52:681.772(043.2) 256021 168468995 29517.pdf 29517.pdf 1 56D1496D6F8D022F0CEF1B741D401261 25083713d2464fbbc32b8158595b1b55eb102e9d556c6359636fbeb887f5d83e 1a4fe0b4-4d48-11ee-9934-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=173846 Fakulteta za strojništvo 0 0 0