TY - CONF AU - Bugár-Mészáros, Barnabás AU - Majdik, András AU - Rózsa, Zoltán AU - Szirányi, Tamás TI - Radiation Plan Optimization for UV-C Disinfection Robots T2 - Proceedings of KEPAF 2023: Képfeldolgozók és Alakfelismerők társaságának 14. konferenciája PY - 2023 SP - 1 EP - 4 PG - 4 UR - https://m2.mtmt.hu/api/publication/34504666 ID - 34504666 LA - English DB - MTMT ER - TY - CONF AU - Rózsa, Zoltán AU - Szirányi, Tamás TI - LIDAR mérések időbeli felskálázása mono kamera alapján T2 - Proceedings of KEPAF 2023: Képfeldolgozók és Alakfelismerők társaságának 14. konferenciája PY - 2023 SP - 1 EP - 13 PG - 13 UR - https://m2.mtmt.hu/api/publication/34504606 ID - 34504606 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Rózsa, Zoltán AU - Szirányi, Tamás TI - Optical Flow and Expansion Based Deep Temporal Up-Sampling of LIDAR Point Clouds JF - REMOTE SENSING J2 - REMOTE SENS-BASEL VL - 15 PY - 2023 IS - 10 PG - 19 SN - 2072-4292 DO - 10.3390/rs15102487 UR - https://m2.mtmt.hu/api/publication/33822096 ID - 33822096 N1 - Export Date: 15 June 2023 Correspondence Address: Rozsa, Z.; Department of Material Handling and Logistics Systems, Muegyetem rkp. 3, Hungary; email: zoltan.rozsa@logisztika.bme.hu AB - This paper proposes a framework that enables the online generation of virtual point clouds relying only on previous camera and point clouds and current camera measurements. The continuous usage of the pipeline generating virtual LIDAR measurements makes the temporal up-sampling of point clouds possible. The only requirement of the system is a camera with a higher frame rate than the LIDAR equipped to the same vehicle, which is usually provided. The pipeline first utilizes optical flow estimations from the available camera frames. Next, optical expansion is used to upgrade it to 3D scene flow. Following that, ground plane fitting is made on the previous LIDAR point cloud. Finally, the estimated scene flow is applied to the previously measured object points to generate the new point cloud. The framework’s efficiency is proved as state-of-the-art performance is achieved on the KITTI dataset. LA - English DB - MTMT ER - TY - CHAP AU - Golarits, Marcell AU - Rózsa, Zoltán AU - Szirányi, Tamás ED - Szirmay-Kalos, L ED - Renner, Gábor TI - Környező járművek mozgásának meghatározása irány becslésre és kép-párok közötti epipoláris geometriára építve T2 - X. Magyar Számítógépes Grafika és Geometria Konferencia PB - Neumann János Számítógép-tudományi Társaság CY - Budapest SN - 9789634218715 PY - 2022 SP - 122 EP - 127 PG - 6 UR - https://m2.mtmt.hu/api/publication/33592095 ID - 33592095 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Rózsa, Zoltán AU - Golarits, Marcell AU - Szirányi, Tamás TI - Immediate Vehicle Movement Estimation and 3D Reconstruction for Mono Cameras by Utilizing Epipolar Geometry and Direction Prior JF - IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS J2 - IEEE T INTELL TRANSP VL - 23 PY - 2022 IS - 12 SP - 23548 EP - 23558 PG - 11 SN - 1524-9050 DO - 10.1109/TITS.2022.3199046 UR - https://m2.mtmt.hu/api/publication/33078836 ID - 33078836 N1 - Funding Agency and Grant Number: European Union [RRF-2.3.1-21-2022-00002]; Hungarian Scientific Research Fund (NKFIH OTKA) [K 139485] Funding text: This work was supported in part by the European Union within the framework of the National Laboratory for Autonomous Systems under Grant RRF-2.3.1-21-2022-00002 and in part by the Hungarian Scientific Research Fund (NKFIH OTKA) under Grant K 139485. The Associate Editor for this article was S. E. Li. LA - English DB - MTMT ER - TY - JOUR AU - Rózsa, Zoltán AU - Szirányi, Tamás TI - Temporal Up-Sampling of LIDAR Measurements Based on a Mono Camera JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 13232 PY - 2022 SP - 51 EP - 64 PG - 14 SN - 0302-9743 DO - 10.1007/978-3-031-06430-2_5 UR - https://m2.mtmt.hu/api/publication/32850291 ID - 32850291 N1 - Export Date: 7 June 2022 Correspondence Address: Rozsa, Z.; Machine Perception Research Laboratory of Institute for Computer Science and Control (SZTAKI), Kende u. 13-17, Hungary; email: zoltan.rozsa@sztaki.hu Funding Agency and Grant Number: Ministry of Innovation and Technology NRDI Office within the framework of the Autonomous Systems National Laboratory Program; Hungarian National Science Fundation (NKFIH OTKA) [K139485] Funding text: The research was supported by the Ministry of Innovation and Technology NRDI Office within the framework of the Autonomous Systems National Laboratory Program and by the Hungarian National Science Fundation (NKFIH OTKA) No. K139485. AB - Most of the 3D LIDAR sensors used in autonomous driving have significantly lower frame rates than modern cameras equipped to the same vehicle. This paper proposes a solution to virtually increase the frame rate of the LIDARs utilizing a mono camera, making possible the monitoring of dynamic objects with fast movement in the environment. First, dynamic object candidates are detected and tracked in the camera frames. Next, LIDAR points corresponding to these objects are identified. Then, virtual camera poses can be calculated by back projecting these points to the camera and tracking them. Finally, from the virtual camera poses, the object movement (transformation matrix transforming the object between frames) can be calculated (knowing the real camera poses) to the time moment, which does not have a corresponding LIDAR measurement. Static objects (rigid with the scene) can also be transformed to this time movement if the real camera poses are known. The proposed method has been tested in the Argoverse dataset, and it has outperformed earlier methods with a similar purpose. LA - English DB - MTMT ER - TY - JOUR AU - Benedek, Csaba AU - Majdik, András AU - Nagy, Balázs AU - Rózsa, Zoltán AU - Szirányi, Tamás TI - Positioning and perception in LIDAR point clouds JF - DIGITAL SIGNAL PROCESSING J2 - DIGIT SIGNAL PROCESS VL - 119 PY - 2021 PG - 12 SN - 1051-2004 DO - 10.1016/j.dsp.2021.103193 UR - https://m2.mtmt.hu/api/publication/32122541 ID - 32122541 N1 - Export Date: 24 September 2021 CODEN: DSPRE Correspondence Address: Sziranyi, T.; Machine Perception Research Laboratory (MPLab), Kende u. 13-17, Hungary; email: sziranyi.tamas@sztaki.hu LA - English DB - MTMT ER - TY - CHAP AU - Bohács, Gábor AU - Rózsa, Zoltán AU - Bertalan, Balint ED - Huang, Anqiang ED - Shang, Xiaopu ED - Shi, Xianliang ED - Bohács, Gábor ED - Liu, Shifeng TI - Mono Camera Based Pallet Detection and Pose Estimation for Automated Guided Vehicles T2 - LISS 2020 PB - Springer-Verlag Singapore CY - Singapore SN - 9789813343580 PY - 2021 SP - 1 EP - 11 PG - 11 DO - 10.1007/978-981-33-4359-7_1 UR - https://m2.mtmt.hu/api/publication/32029863 ID - 32029863 LA - English DB - MTMT ER - TY - CHAP AU - Rózsa, Zoltán AU - Golarits, Marcell AU - Szirányi, Tamás ED - Berns, K ED - Helfert, M ED - Gusikhin, O TI - Water Hazard Depth Estimation for Safe Navigation of Intelligent Vehicles T2 - Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems PB - SciTePress CY - Setubal SN - 9789897585135 PY - 2021 SP - 90 EP - 99 PG - 10 DO - 10.5220/0010438100900099 UR - https://m2.mtmt.hu/api/publication/32016263 ID - 32016263 LA - English DB - MTMT ER - TY - JOUR AU - Rózsa, Zoltán AU - Golarits, Marcell AU - Szirányi, Tamás TI - Localization of Map Changes by Exploiting SLAM Residuals JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 12002 PY - 2020 SP - 312 EP - 324 PG - 13 SN - 0302-9743 DO - 10.1007/978-3-030-40605-9_27 UR - https://m2.mtmt.hu/api/publication/31207094 ID - 31207094 LA - English DB - MTMT ER -