TY - JOUR AU - Terbe, Dániel AU - Orzó, László AU - Bicsák, Barbara AU - Zarándy, Ákos TI - Hologram Noise Model for Data Augmentation and Deep Learning JF - SENSORS J2 - SENSORS-BASEL VL - 24 PY - 2024 IS - 3 PG - 14 SN - 1424-8220 DO - 10.3390/s24030948 UR - https://m2.mtmt.hu/api/publication/34551736 ID - 34551736 LA - English DB - MTMT ER - TY - JOUR AU - Jánoki, Imre Gergely AU - Nagy, Ádám AU - Földesy, Péter AU - Zarándy, Ákos AU - Siket, Máté AU - Varga, Judit AU - Szabó, Miklós TI - Neonatal Activity Monitoring by Camera-Based Multi-LSTM Network JF - ENGINEERING PROCEEDINGS J2 - ENGENG PROC VL - 55 PY - 2023 IS - 1 PG - 7 SN - 2673-4591 DO - 10.3390/engproc2023055016 UR - https://m2.mtmt.hu/api/publication/34426868 ID - 34426868 LA - English DB - MTMT ER - TY - JOUR AU - Bauer, Péter AU - Nagy, Mihály AU - Kuna, Gergely István AU - Kisari, A AU - Simonyi, Ernő AU - Hiba, Antal AU - Drotar, I TI - Stability focused evaluation and tuning of special ground vehicle tracking algorithms JF - IFAC PAPERSONLINE J2 - IFACOL VL - 56 PY - 2023 IS - 2 SP - 9282 EP - 9287 PG - 6 SN - 2405-8971 DO - 10.1016/j.ifacol.2023.10.212 UR - https://m2.mtmt.hu/api/publication/34399999 ID - 34399999 LA - English DB - MTMT ER - TY - CHAP AU - Hiba, Antal AU - Körtvélyesi, Viktor AU - Kiskároly, Albert AU - Bhoite, O AU - David, P AU - Majdik, András TI - Indoor vehicle-in-the-loop simulation of unmanned micro aerial vehicle with artificial companion T2 - 2023 International Conference on Unmanned Aircraft Systems (ICUAS) PB - IEEE CY - Piscataway (NJ) SN - 9798350310375 PY - 2023 SP - 137 EP - 143 PG - 7 DO - 10.1109/ICUAS57906.2023.10156429 UR - https://m2.mtmt.hu/api/publication/34107680 ID - 34107680 N1 - Computational Optical Sensing and Processing Laboratory, Institute for Computer Science and Control (SZTAKI), Elkh, Budapest, Hungary Machine Perception Research Laboratory Institute for Computer Science and Control (SZTAKI), Elkh, Budapest, Hungary Conference code: 190024 Export Date: 20 September 2023 Correspondence Address: Hiba, A.; Computational Optical Sensing and Processing Laboratory, Hungary; email: hiba.antal@sztaki.hu LA - English DB - MTMT ER - TY - JOUR AU - Siket, Máté AU - Jánoki, Imre Gergely AU - Nagy, Ádám AU - Földesy, Péter TI - Sample-in-the-Loop Laser Speckle Contrast Imaging Based on Optimization JF - ACTA POLYTECHNICA HUNGARICA J2 - ACTA POLYTECH HUNG VL - 20 PY - 2023 IS - 2 SP - 25 EP - 39 PG - 15 SN - 1785-8860 DO - 10.12700/APH.20.2.2023.20.2 UR - https://m2.mtmt.hu/api/publication/33854267 ID - 33854267 N1 - Institute for Computer Science and Control, Kende utca 13-17, Budapest, H-1111, Hungary Physiological Controls Research Center, Óbuda University, Bécsi út 96/b, Budapest, H-1034, Hungary Export Date: 4 October 2023 LA - English DB - MTMT ER - TY - JOUR AU - Bauer, Péter AU - Hiba, Antal AU - Nagy, Mihály AU - Simonyi, Ernő AU - Kuna, Gergely István AU - Kisari, Ádám AU - Drotár, István AU - Zarándy, Ákos TI - Encounter Risk Evaluation with a Forerunner UAV JF - REMOTE SENSING J2 - REMOTE SENS-BASEL VL - 15 PY - 2023 IS - 6 PG - 45 SN - 2072-4292 DO - 10.3390/rs15061512 UR - https://m2.mtmt.hu/api/publication/33698328 ID - 33698328 AB - Forerunner UAV refers to an unmanned aerial vehicle equipped with a downward-looking camera flying in front of the advancing emergency ground vehicles (EGV) to notify the driver about the hidden dangers (e.g., other vehicles). A feasibility demonstration in an urban environment having a multicopter as the forerunner UAV and two cars as the emergency and dangerous ground vehicles was done in ZalaZONE Proving Ground, Hungary. After the description of system hardware and software components, test scenarios, object detection and tracking, the main contribution of the paper is the development and evaluation of encounter risk decision methods. First, the basic collision risk evaluation applied in the demonstration is summarized, then the detailed development of an improved method is presented. It starts with the comparison of different velocity and acceleration estimation methods. Then, vehicle motion prediction is conducted, considering estimated data and its uncertainty. The prediction time horizon is determined based on actual EGV speed and so braking time. If the predicted trajectories intersect, then the EGV driver is notified about the danger. Some special relations between EGV and the other vehicle are also handled. Tuning and comparison of basic and improved methods is done based on real data from the demonstration. The improved method can notify the driver longer, identify special relations between the vehicles and it is adaptive considering actual EGV speed and EGV braking characteristics; therefore, it is selected for future application. LA - English DB - MTMT ER - TY - CHAP AU - Siket, Máté AU - Tóth, R AU - Szász, László AU - Novák, Kamilla AU - Eigner, György AU - Kovács, Levente TI - An application programming interface for the widely used academic version of the UVA/Padova Type 1 Diabetes Mellitus Metabolic Simulator T2 - IEEE 21st World Symposium on Applied Machine Intelligence and Informatics SAMI (2023) : Proceedings PB - IEEE CY - Herlany SN - 9798350319859 PY - 2023 SP - 287 EP - 292 PG - 6 DO - 10.1109/SAMI58000.2023.10044485 UR - https://m2.mtmt.hu/api/publication/33589068 ID - 33589068 LA - English DB - MTMT ER - TY - JOUR AU - Orzó, László AU - Kiss, Márton AU - Terbe, Dániel AU - Zarándy, Ákos TI - Fast High Resolution In-line Phase Retrieval of Sparse Off-Axis Holograms JF - OPTICS INFOBASE CONFERENCE PAPERS J2 - OPTICS INFOBASE CONF PAP VL - 2022 PY - 2022 PG - 2 SN - 2162-2701 DO - 10.1364/DH.2022.Tu4A.6 UR - https://m2.mtmt.hu/api/publication/33589603 ID - 33589603 N1 - Conference code: 183142 Export Date: 24 January 2023 Correspondence Address: Orzó, L.; Institute for Computer Science and Control, Kende street. 13-17, Hungary; email: orzo@sztaki.hu LA - English DB - MTMT ER - TY - JOUR AU - Dénes-Fazakas, Lehel AU - Siket, Máté AU - Szilágyi, László AU - Kovács, Levente AU - Eigner, György TI - Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals JF - SENSORS J2 - SENSORS-BASEL VL - 2022 PY - 2022 PG - 23 SN - 1424-8220 DO - 10.3390/s22218568 UR - https://m2.mtmt.hu/api/publication/33210448 ID - 33210448 LA - English DB - MTMT ER - TY - JOUR AU - Terbe, Dániel AU - Orzó, László AU - Zarándy, Ákos TI - Classification of Holograms with 3D-CNN JF - SENSORS J2 - SENSORS-BASEL VL - 22 PY - 2022 IS - 21 PG - 9 SN - 1424-8220 DO - 10.3390/s22218366 UR - https://m2.mtmt.hu/api/publication/33203271 ID - 33203271 N1 - Export Date: 10 February 2023 Correspondence Address: Zarándy, Á.; Institute for Computer Science and ControlHungary; email: zarandy@sztaki.hu AB - A hologram, measured by using appropriate coherent illumination, records all substantial volumetric information of the measured sample. It is encoded in its interference patterns and, from these, the image of the sample objects can be reconstructed in different depths by using standard techniques of digital holography. We claim that a 2D convolutional network (CNN) cannot be efficient in decoding this volumetric information spread across the whole image as it inherently operates on local spatial features. Therefore, we propose a method, where we extract the volumetric information of the hologram by mapping it to a volume—using a standard wavefield propagation algorithm—and then feed it to a 3D-CNN-based architecture. We apply this method to a challenging real-life classification problem and compare its performance with an equivalent 2D-CNN counterpart. Furthermore, we inspect the robustness of the methods to slightly defocused inputs and find that the 3D method is inherently more robust in such cases. Additionally, we introduce a hologram-specific augmentation technique, called hologram defocus augmentation, that improves the performance of both methods for slightly defocused inputs. The proposed 3D-model outperforms the standard 2D method in classification accuracy both for in-focus and defocused input samples. Our results confirm and support our fundamental hypothesis that a 2D-CNN-based architecture is limited in the extraction of volumetric information globally encoded in the reconstructed hologram image. LA - English DB - MTMT ER -