TY - CONF AU - Juhász, Attila TI - Hadtörténelmi és katonai objektumok rekonstruálása térinformatika és távérzékelés segítségével T2 - 17. Építőmérnöki Tudományos Tanácskozás közleményei SN - 9789634493495 PY - 2024 SP - 7 EP - 18 PG - 12 UR - https://m2.mtmt.hu/api/publication/34779013 ID - 34779013 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Dowajy, Mohammad AU - Somogyi, József Árpád AU - Barsi, Árpád AU - Lovas, Tamás TI - An Automatic Road Surface Segmentation in Non-Urban Environments: A 3D Point Cloud Approach with Grid Structure and Shallow Neural Networks JF - IEEE ACCESS J2 - IEEE ACCESS VL - 12 PY - 2024 SP - 33035 EP - 33044 PG - 10 SN - 2169-3536 DO - 10.1109/ACCESS.2024.3372431 UR - https://m2.mtmt.hu/api/publication/34742506 ID - 34742506 N1 - Export Date: 18 March 2024 AB - Automatic road segmentation from three-dimensional point cloud data has gained increasing interest recently. However, it is still challenging to do this task automatically due to the wide variations of roads and complex environments, especially in non-urban areas. This research proposed a comprehensive approach for using shallow neural networks to segment non-urban road point clouds to support autonomous driving applications. The proposed approach involves converting raw point cloud data into a regular grid of cells or partial clouds. Initially, a shallow neural network based on cells’ properties (cell plane fitting error, cell average intensity, cell elevation range, and cell weighted density) was employed to extract road cells from raw point cloud data. The road cells were refined and segmented into inside-road and road border point clouds based on morphologic operations. A point-wise shallow neural network was used to extract road points from the border point clouds based on intensity and geometric features (roughness, curvature, and change rate of the normal). A precise road surface point cloud is obtained by merging the inside-road and filtered border point clouds. The method performance was evaluated for two datasets captured using a mobile laser scanner (MLS). In the first dataset, the road points were extracted at average completeness, correctness, quality, and overall accuracy of 98.40%, 99.13%, 97.56%, and 98.47%, respectively. Similarly, the method achieved high scores for the second dataset with 97.22% completeness, 99.02% correctness, 96.29% quality, and 98.71% overall accuracy. The method performance demonstrates an advancement when compared to various state-of-the-art methods and also confirms its adaptability to different road environments. Authors LA - English DB - MTMT ER - TY - JOUR AU - Kugler, Zsófia AU - Nghiem, S. AU - Brakenridge, G.R. TI - SMAP Passive Microwave Radiometer for Global River Flow Monitoring JF - IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING J2 - IEEE T GEOSCI REMOTE VL - 62 PY - 2024 SP - 1 EP - 14 PG - 14 SN - 0196-2892 DO - 10.1109/TGRS.2024.3359515 UR - https://m2.mtmt.hu/api/publication/34628211 ID - 34628211 N1 - Export Date: 19 February 2024 CODEN: IGRSD AB - River flow is a fundamental observable in hydrology but there is no consistent global ground measurement network. Various types of orbital remote sensing are therefore well positioned to meet an important observational need, including for hydrological modeling and for understanding trends through time. In previous studies, we showed that passive microwave radiometry (PMR) can measure streamflow over selected locations around the globe with a high correlation to co-located in situ discharge observations. This paper demonstrates the potential of low-frequency, L-band NASA Soil Moisture Active and Passive (SMAP) satellite observations for streamflow measurement: an unanticipated but exceptionally valuable use of this sensor. Utilizing the fully polarimetric capability of SMAP with full Stokes parameters, we optimize the polarization combinations of the observations to retrieve accurate river hydrographs from space. Flow measurements over 150 satellite gauging reaches (SGR) are retrieved over different continents, and 14 SGRs provide comparisons to available in situ river gauging data. Results from linear correlation calculations provide coefficients of determination r2 of approximately 0.75 for SMAP-based discharge measurements when compared to in situ streamflow observations. SMAP river observations thereby improve river gauging results compared to ESA’s Soil Moisture Ocean Salinity (SMOS) satellite L-band PMR as the analysis indicates typically lower r2 values of approximately 0.68 for SMOS. IEEE LA - English DB - MTMT ER - TY - JOUR AU - Breunig, M. AU - Kuper, P. AU - Reitze, F. AU - Landgraf, S. AU - Al-Doori, M. AU - Stefanakis, E. AU - Abdulmuttalib, H. AU - Kugler, Zsófia TI - IMPROVING DATA QUALITY AND MANAGEMENT FOR REMOTE SENSING ANALYSIS: USE-CASES AND EMERGING RESEARCH QUESTIONS JF - ISPRS ANNALS OF THE PHOTOGRAMMETRY REMOTE SENSING AND SPATIAL INFORMATION SCIENCES J2 - ANN PHOTOGRAMMETRY REM SENS SPAT INF SCI VL - 10 PY - 2023 IS - 1-W1-2023 SP - 41 EP - 49 PG - 9 SN - 2194-9042 DO - 10.5194/isprs-annals-X-1-W1-2023-41-2023 UR - https://m2.mtmt.hu/api/publication/34554382 ID - 34554382 N1 - This contribution has been peer-reviewed. The double-blind peer-review was conducted on the basis of the full paper. Geodetic Institute, Karlsruhe Institute of Technology, Germany University of Science & Technology of Fujairah, College of Engineering and Technology, United Arab Emirates Department of Geomatics Engineering, University of Calgary, Canada GIS Department, Dubai Municipality, United Arab Emirates Dept. of Photogramm. and Geoinformatics, Budapest Univ. of Technology and Economics, Hungary Export Date: 18 March 2024 Correspondence Address: Kuper, P.; Geodetic Institute, Germany; email: paul.kuper@kit.edu AB - During the last decades satellite remote sensing has become an emerging technology producing big data for various application fields every day. However, data quality checking as well as the long-time management of data and models are still issues to be improved. They are indispensable to guarantee smooth data integration and the reproducibility of data analysis such as carried out by machine learning models. In this paper we clarify the emerging need of improving data quality and the management of data and models in a geospatial database management system before and during data analysis. In different use cases various processes of data preparation and quality checking, integration of data across different scales and references systems, efficient data and model management, and advanced data analysis are presented in detail. Motivated by these use cases we then discuss emerging research questions concerning data preparation and data quality checking, data management, model management and data integration. Finally conclusions drawn from the paper are presented and an outlook on future research work is given. © Author(s) 2023. CC BY 4.0 License. LA - English DB - MTMT ER - TY - JOUR AU - Fawzy, Mohamed AU - Szabó, György AU - Barsi, Árpád TI - A Shallow Neural Network Model for Urban Land Cover Classification Using VHR Satellite Image Features JF - ISPRS ANNALS OF THE PHOTOGRAMMETRY REMOTE SENSING AND SPATIAL INFORMATION SCIENCES J2 - ANN PHOTOGRAMMETRY REM SENS SPAT INF SCI VL - 10 PY - 2023 IS - 1-W1-2023 SP - 57 EP - 64 PG - 8 SN - 2194-9042 DO - 10.5194/isprs-annals-X-1-W1-2023-57-2023 UR - https://m2.mtmt.hu/api/publication/34554380 ID - 34554380 N1 - This contribution has been peer-reviewed. The double-blind peer-review was conducted on the basis of the full paper. Funding details: Nemzeti Kutatási, Fejlesztési és Innovaciós Alap, NKFIA Funding details: South Valley University, SVU Funding text 1: The research reported in this paper is part of project no. BMENVA-02, implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the TKP2021 funding scheme. Civil Eng. Dept., Faculty of Engineering, South Valley University, Qena, Egypt is gratefully acknowledged for providing the WorldView-2 satellite image of Qena City. Funding text 2: The research reported in this paper is part of project no. BME-NVA-02, implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the TKP2021 funding scheme. Civil Eng. Dept., Faculty of Engineering, South Valley University, Qena, Egypt is gratefully acknowledged for providing the WorldView-2 satellite image of Qena City. Export Date: 18 March 2024 Correspondence Address: Fawzy, M.; Department of Photogrammetry and Geoinformatics, 3 Műegyetem rkp., K Building First Floor 31., Hungary; email: Mohamedfawzyramadanmahmoud@edu.bme.hu AB - Recently, image classification techniques using neural networks have received considerable attention in sustainable urban development, since their applications have an extreme effect on building distribution, infrastructural networks, and water resource management. In this research, a back-propagation shallow neural network model is presented for very high resolution satellite image classification in urban environments. Workflow procedures consider selecting and collecting data, preparing required study areas, extracting distinctive features, and applying the classification process. Visual interpretation is performed to identify observed land cover classes and detect distinctive features in the urban environment. Pre-processing techniques are implemented to present the used images in a more suited form for the classification techniques. A shallow neural network model (supported by MathWorks MATLAB environment) is successfully applied and results are evaluated. The proposed model is tested for classifying both WorldView-2 and WorldView-3 multispectral images with different spatial and spectral characteristics to check the model's applicability to various kinds of satellite imagery and different study areas. Model outcomes are compared to two well-known classification methods; the Nearest Neighbour object-based method and the Maximum Likelihood pixel-based classifier, to validate and check the model stability. The overall accuracy achieved by the proposed model is 86.25% and 83.25%, while the nearest neighbour approach has obtained 84.50% and 82.75%, and the maximum likelihood classifier has accomplished 82.50% and 80.25% for study area 1 and study area 2 respectively. Obtained results indicate that the developed shallow neural network model achieves a promising accuracy for urban land cover classification in comparison with the standard techniques. © Author(s) 2023. CC BY 4.0 License. LA - English DB - MTMT ER - TY - JOUR AU - Lógó, János Máté AU - Barsi, Árpád TI - LINE AND POLYGON TOPOLOGY IN OPENDRIVE MODELLING JF - INTERNATIONAL ARCHIVES OF PHOTOGRAMMETRY AND REMOTE SENSING (2002-) J2 - ISPRS (2002-) VL - 48 PY - 2023 IS - 1/W2-2023 SP - 835 EP - 840 PG - 6 SN - 1682-1750 DO - 10.5194/isprs-archives-XLVIII-1-W2-2023-835-2023 UR - https://m2.mtmt.hu/api/publication/34554379 ID - 34554379 N1 - This contribution has been peer-reviewed. Export Date: 18 March 2024 Correspondence Address: Lógó, J.M.; Dept. Photogrammetry and Geoinformatics, Hungary; email: logo.janos.mate@emk.bme.hu AB - The paper discusses the importance of efficient methods in the automotive industry for the development of self-driving vehicles and advanced vehicle assistants, focusing on the use of high-definition (HD) maps. The integration of computer simulation and HD maps in the OpenDRIVE format is emphasized. A paradigm shift in map topology is highlighted, requiring a new map creation and usage approach. The article presents a methodology that addresses both geometric and topological aspects in creating accurate HD map models. The method focuses on the connection of linear and arc road elements and eliminating continuity/connectivity errors in lane descriptions. Real-world tests validate the implemented methodology and demonstrate the successful generation of topologically correct HD map models. The results show the potential of these models for various automotive applications, particularly in the development and testing of self-driving vehicles and advanced vehicle assistants. The methodology contributes to the advancement of HD map creation, providing valuable insights for researchers and map makers in the automotive industry. © Author(s) 2023. LA - English DB - MTMT ER - TY - JOUR AU - Horváth, Viktor Győző AU - Barsi, Árpád TI - COST-EFFICIENT METHODS OF DERIVING SLOPE INFORMATION FOR ROAD SEGMENTS IN DRIVER-ASSISTANCE APPLICATIONS JF - INTERNATIONAL ARCHIVES OF PHOTOGRAMMETRY AND REMOTE SENSING (2002-) J2 - ISPRS (2002-) VL - 48 PY - 2023 IS - 1/W2-2023 SP - 895 EP - 900 PG - 6 SN - 1682-1750 DO - 10.5194/isprs-archives-XLVIII-1-W2-2023-895-2023 UR - https://m2.mtmt.hu/api/publication/34554377 ID - 34554377 N1 - This contribution has been peer-reviewed Funding details: European Commission, EC Funding details: European Social Fund Plus, ESF, EFOP-3.6.3-VEKOP-16-2017-00001 Funding details: Nemzeti Kutatási Fejlesztési és Innovációs Hivatal, NKFI Funding details: Nemzeti Kutatási, Fejlesztési és Innovaciós Alap, NKFIA Funding details: Innovációs és Technológiai Minisztérium Funding text 1: The research reported in this paper and carried out at the Budapest University of Technology and Economics has been supported by the National Research Development and Innovation Fund (TKP2020 Institution Excellence Subprogram, Grant No. BME-IE-MIFM) based on the charter of bolster issued by the National Research Development and Innovation Office under the auspices of the Ministry for Innovation and Technology. The project has been supported by the European Union, co-financed by the European Social Fund. EFOP-3.6.3-VEKOP-16-2017-00001. The authors are grateful to the Lechner Knowledge Center for the topography data provided for the research. Export Date: 18 March 2024 Correspondence Address: Horváth, V.; Dept. Photogrammetry and Geoinformatics, Hungary; email: horvath.viktor.gyozo@emk.bme.hu AB - An advanced driver-assistance system (ADAS) is any of a group of technologies that assist drivers in driving and parking functions. Through a safe human-machine interface, ADAS increase car and road safety. These Advanced driver-assistance systems rely on special maps with extended geometry and attribute information. This extra information includes slope, curvature, and speed limit. ADAS-enabled maps are usually rather expensive in the industry. This paper is focused on finding cost-efficient alternatives for generating the slope aspect of ADAS maps. Slope and height information is not only used in ADAS but is a critical aspect of calculating electronic vehicle (EV) ranges, and truck fuel-efficiency calculations as well. ADAS slope information usually requires high-accuracy surveys. This paper researches the possible generation of slope information for road segments with the use of digital elevation models (DEM) or crowdsourcing with low-cost sensors and Kalman filtering. The first approach is based on globally available DEMs with interpolation and filtering with road geometry. DEMs have variable accuracy depending on the type of technology used in producing them. Such technologies include photogrammetry, aerial and terrestrial laser scanning (ALS, TLS), or aerial or space radar measurements. The other method is by using low-cost GPS and IMU sensors for generating altitude profiles. These produced altitude profiles are compared with a profile generated from a high-accuracy survey using large-resolution DEMs produced by aerial photogrammetry or aerial laser scanning. This paper proposes metrics with which these datasets can be compared, one is using the height differences, and the other compares the slope values at discrete common points. In the conclusion, the paper tries to find use cases for the low-accuracy data. © Author(s) 2023. LA - English DB - MTMT ER - TY - JOUR AU - Kugler, Zsófia AU - Horváth, Viktor Győző TI - A comparison of river streamflow measurement from optical and passive microwave radiometry JF - IDŐJÁRÁS / QUARTERLY JOURNAL OF THE HUNGARIAN METEOROLOGICAL SERVICE J2 - IDŐJÁRÁS VL - 127 PY - 2023 IS - 4 SP - 473 EP - 484 PG - 12 SN - 0324-6329 DO - 10.28974/idojaras.2023.4.4 UR - https://m2.mtmt.hu/api/publication/34417883 ID - 34417883 N1 - Export Date: 21 December 2023 Correspondence Address: Kugler, Z.; Department of Photogrammetry and Geoinformatics, Műegyetem rkp. 3, Hungary; email: kugler.zsofia@emk.bme.hu Funding Agency and Grant Number: European Union [RRF-2.3.1-21-2022-00004]; Ministry of Innovation and Technology NRDI Office within the framework of the Artificial Intelligence National Laboratory Program; European Union within the framework of the Artificial Intelligence National Laboratory [RRF-2.3.1-21-2022-00004]; National Research and Innovation Office; National Research, Development and Innovation Fund of Hungary [TKP2021-NKTA-32] 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.The authors would like to thank Dr. Kalman Kovacs and the Data Supply Department of the Hungarian Meteorological Service for sharing the extensive local and medical meteorological and accident databases for the purpose of the research presented in this paper. The research presented here was supported by the the European Union project RRF-2.3.1-21-2022-00004 within the framework of the Artificial Intelligence National Laboratory.Part of the work presented was supported by the National Research and Innovation Office.Project no. TKP2021-NKTA-32 has been implemented with the support provided from the National Research, Development and Innovation Fund of Hungary, financed under the TKP2021-NKTA funding scheme. AB - Climate change has a crucial impact on the global energy and water cycle. The hydrological cycle can be studied both from ground and satellite measurements on a global scale. Yet a comprehensive overview is challenging to establish given the spatial and temporal limitations related to various Earth Observation satellite sensors or maintenance of in-situ gauges. Optical remote sensing of visible light can not overcome the substantial obstacle from cloud cover that vastly limits its capability in daily global monitoring. Active satellite sensors like SAR or altimetry are not capable to provide global coverage on a daily basis, therefore, they can be geographically limited. Passive microwave radiometry (PMR) can acquire both daily and global scales that enables the temporally frequent and spatially extensive observations of continental river gauge. Previous studies demonstrated the use of PMR measurements for global daily river gauge benefiting from its high sensitivity of microwave radiation to water presence. This study aims at comparing the methodology of PMR to optical river gauge measurements based on the assumption that at selected locations along the river channel, increase in streamflow is related to increase in the floodplain water surface inundation. Comparison showed a significant obstacle of cloud cover over tropical regions, where PMR has the potential to measure river streamflow. Yet over regions with less clouds both optical and PMR can be good alternative to in-situ streamflow ground measurements. LA - English DB - MTMT ER - TY - JOUR AU - Horváth, Viktor Győző AU - Barsi, Árpád TI - Járműfedélzeti kamerák helymeghatározása Kálmán-szűréssel JF - GEODÉZIA ÉS KARTOGRÁFIA J2 - GEODÉZIA ÉS KARTOGRÁFIA VL - 75 PY - 2023 IS - 4 SP - 15 EP - 20 PG - 6 SN - 0016-7118 DO - 10.30921/GK.75.2023.4.2 UR - https://m2.mtmt.hu/api/publication/34342469 ID - 34342469 N1 - Export Date: 16 November 2023 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Kugler, Zsófia AU - Nghiem, Son V. AU - Brakenridge, G. Robert AU - Podkowa, Anna ED - Sidharth, Misra ED - Shannon, Brown ED - Javier, Bosch-Lluis TI - River Flow Monitoring with Passive Microwave Radiometry and Potential Synergy with Swot T2 - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium PB - IEEE CY - Piscataway (NJ) SN - 9798350320107 PY - 2023 SP - 2711 EP - 2714 PG - 4 DO - 10.1109/IGARSS52108.2023.10282796 UR - https://m2.mtmt.hu/api/publication/34212329 ID - 34212329 N1 - Export Date: 14 December 2023 CODEN: IGRSE Correspondence Address: Kugler, Z.; Budapest University of Technology and Economics, 1111 Budapest, Muegyetem rkp. 3-9, Hungary; email: Kugler.Zsofia@emk.bme.hu LA - English DB - MTMT ER -