TY - JOUR AU - Fridvalszky, András Máté AU - Tóth, Balázs György AU - Szécsi, László TI - Evaluating dehazing techniques on artificial and satellite land surface images JF - IDŐJÁRÁS / QUARTERLY JOURNAL OF THE HUNGARIAN METEOROLOGICAL SERVICE J2 - IDŐJÁRÁS VL - 127 PY - 2023 IS - 4 SP - 447 EP - 457 PG - 11 SN - 0324-6329 DO - 10.28974/idojaras.2023.4.2 UR - https://m2.mtmt.hu/api/publication/34417874 ID - 34417874 N1 - Export Date: 21 December 2023 Correspondence Address: Fridvalszky, A.; Department of Control Engineering and Information Technology, Műegyetem rkp. 3, Hungary; email: fridvalszky@iit.bme.hu Funding Agency and Grant Number: Ministry of Innovation and Technology NRDI Office Funding text: The authors would like to express their gratitude towards Dr. Kalman Kovacs, Dr. Daniel Kristof, and the Lechner Knowledge Center for providing advice and support with the acquisition of satellite images. The research was supported by the Ministry of Innovation and Technology NRDI Office within the framework of the Artificial Intelligence National Laboratory Program. The GPUs have been donated by NVIDIA. AB - Many image-based recognition tasks are highly susceptible to different types of natural phenomena like foggy weather, snow, or rain. The participating media will likely obscure important details necessary for these algorithms to work correctly. Still, these aspects could be recovered in certain situations with prior information about the underlying light interactions. This could be done with certain heuristics or with the nowadays popular deep-learning based methods. In this paper, we review and compare the results of two approaches to remove or scale down the effects of foggy weather. We also examine how these results can be applied to high resolution satellite images of land surfaces. LA - English DB - MTMT ER - TY - CHAP AU - Fridvalszky, András Máté AU - Tóth, Márton József AU - Tóth, Balázs György ED - Kiss, Bálint ED - Szirmay-Kalos, László TI - Analysis of a deep learning based fog removal technique T2 - Proceedings of the Workshop on the Advances in Information Technology 2022 PB - OSZK CY - Budapest SN - 9789634218715 PY - 2022 SP - 29 EP - 33 PG - 5 UR - https://m2.mtmt.hu/api/publication/32850498 ID - 32850498 LA - English DB - MTMT ER - TY - JOUR AU - Szirmay-Kalos, László AU - Kacsó, Ágota Enikő AU - Magdics, Milán AU - Tóth, Balázs György TI - Robust Compartmental Model Fitting in Direct Emission Tomography Reconstruction JF - VISUAL COMPUTER J2 - VISUAL COMPUT VL - 38 PY - 2022 IS - 2 SP - 655 EP - 668 PG - 14 SN - 0178-2789 DO - 10.1007/s00371-020-02041-x UR - https://m2.mtmt.hu/api/publication/31836579 ID - 31836579 AB - Dynamic tomography reconstructs a time activity curve (TAC) for every voxel assuming that the algebraic form of the function is known a priori. The algebraic form derived from the analysis of compartmental models depends nonlinearly on the nonnegative parameters to be determined. Direct methods apply fitting in every iteration step. Because of the iterative nature of the maximum likelihood–expectation maximization (ML–EM) reconstruction, the fitting result of the previous step can serve as a good starting point in the current step; thus, after the first iteration we have a guess that is not far from the solution, which allows the use of gradient-based local optimization methods. However, finding good initial guesses for the first ML–EM iteration is a critical problem since gradient-based local optimization algorithms do not guarantee convergence to the global optimum if they are started at an inappropriate location. This paper examines the robust solution of the fitting problem both in the initial phase and during the ML–EM iteration. This solution is implemented on GPUs and is built into the 4D reconstruction module of the TeraTomo software. LA - English DB - MTMT ER - TY - CONF AU - Fridvalszky, András Máté AU - Tóth, Balázs György TI - Real-time ambient lighting with raytracing T2 - Képfeldolgozók és Alakfelismerők társaságának 13. konferenciája PB - Képfeldolgozók és Alakfelismerők Társasága C1 - Budapest PY - 2021 PG - 13 UR - https://m2.mtmt.hu/api/publication/32850668 ID - 32850668 LA - English DB - MTMT ER - TY - CONF AU - Fridvalszky, András Máté AU - Tóth, Balázs György TI - Optimizing multisample anti-aliasing for deferred renderers T2 - Proceedings of CESCG 2020: The 24th Central European Seminar on Computer Graphics PY - 2020 PG - 7 UR - https://m2.mtmt.hu/api/publication/33531572 ID - 33531572 LA - English DB - MTMT ER - TY - CHAP AU - Szirmay-Kalos, László AU - Varnyú, Dóra AU - Magdics, Milán AU - Tóth, Balázs György TI - Modeling of Depth of Interaction with Inter-crystal Scattering for PET Reconstruction T2 - 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) PB - IEEE CY - Piscataway (NJ) SN - 9781728176932 PY - 2020 SP - 1 EP - 6 PG - 6 DO - 10.1109/NSS/MIC42677.2020.9507795 UR - https://m2.mtmt.hu/api/publication/32252580 ID - 32252580 N1 - Export Date: 20 June 2022 LA - English DB - MTMT ER - TY - CHAP AU - Fridvalszky, András Máté AU - Tóth, Balázs György ED - Szirmay-Kalos, László ED - Kiss, Bálint TI - Többmintás élsimítás alkalmazása deferred shading esetében T2 - Proceedings of the Workshop on the Advances of Information Technology 2020 : WAIT 2020 PB - Budapesti Műszaki és Gazdaságtudományi Egyetem, Villamosmérnöki és Informatikai Kar CY - Budapest SN - 9789634218029 PY - 2020 SP - 117 UR - https://m2.mtmt.hu/api/publication/31998587 ID - 31998587 LA - Hungarian DB - MTMT ER - TY - BOOK AU - Tóth, Balázs György TI - Korszerű valós idejű 3D algoritmusok AR/VR alkalmazásokhoz PB - Nemzeti Közszolgálati Egyetem Közigazgatási Továbbképzési Intézet CY - Budapest PY - 2020 SP - 68 SN - 9789634981183 UR - https://m2.mtmt.hu/api/publication/31913818 ID - 31913818 LA - Hungarian DB - MTMT ER - TY - BOOK AU - Tóth, Balázs György AU - Jakab, László TI - Képmegjelenítés és animáció 3D rendszereken PB - Nemzeti Közszolgálati Egyetem Közigazgatási Továbbképzési Intézet CY - Budapest PY - 2020 SP - 85 SN - 9789634983910 UR - https://m2.mtmt.hu/api/publication/31913805 ID - 31913805 LA - Hungarian DB - MTMT ER - TY - CONF AU - Fridvalszky, András Máté AU - Tóth, Balázs György ED - Anders, Ynnerman TI - Multisample Anti-aliasing in Deferred Rendering T2 - Eurographics Short Papers PY - 2020 SP - 21 EP - 24 PG - 4 DO - 10.2312/egs.20201008 UR - https://m2.mtmt.hu/api/publication/31334325 ID - 31334325 LA - English DB - MTMT ER -