János Máté Lógó

János Máté Lógó

Auto-generated profile, based on publicly available information

János Máté Lógó

Department of Photogrammetry and Geoinformatics, Faculty of Civil Engineering, Budapest University of Technology and Economics, 3 Műegyetem rkp., K building first floor 31. Budapest, H-1111, Hungary

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2023 in Periodica Polytechnica Civil Engineering
Verified
Journal Article
Open access
PDF file
MSMátyás Szántó
Mátyás Szántó
SKSándor Kobál
Sándor Kobál
LVLászló Vajta
László Vajta
VHViktor Győző Horváth
Viktor Győző Horváth
JLJános Máté Lógó
János Máté Lógó
ABArpad Barsi
Arpad Barsi
3-dimensional, accurate, and up-to-date maps are essential for vehicles with autonomous capabilities, whose functionality is made possible by machine learning-based algorithms. Since these solutions require a tremendous amount of data for parameter optimization, simulation-to-reality (Sim2Real) methods have been proven immensely useful for training data generation. For creating realistic models to be used for synthetic data generation, crowdsourcing techniques present a resource-efficient alternative. In this paper, we show that using the Carla simulation environment, a crowdsourcing model can be created that mimics a multi-agent data gathering and processing pipeline. We developed a solution that yields dense point clouds based on monocular images and location information gathered by individual data acquisition vehicles. Our method provides scene reconstructions using the robust Structure-from-Motion (SfM) solution of Colmap. Moreover, we introduce a solution for synthesizing dense ground truth point clouds originating from the Carla simulator using a simulated data acquisition pipeline. We compare the results of the Colmap reconstruction with the reference point cloud after aligning them using the iterative closest point algorithm. Our results show that a precise point cloud reconstruction was feasible with this crowdsourcing-based approach, with 54\% of the reconstructed points having an error under 0.05 m, and a weighted root mean square error of 0.0449 m for the entire point cloud.

1 January 2020 in Periodica Polytechnica Civil Engineering
Verified
Journal Article
Closed access
PDF file
ABArpad Barsi
Arpad Barsi
VPVivien Potó
Vivien Potó
JLJános Máté Lógó
János Máté Lógó
NKNikol Krausz
Nikol Krausz
The development of automotive technologies requires quite a significant amount of time and money. To accelerate this procedure, the technology of now is strongly based on computer simulations, where the whole vehicle or its parts can be analyzed in a virtual environment. The behavior of cars, especially equipped with new sensors or assistants, requires long testing, where the automotive simulators can play a cardinal role. The precise vehicular tests request accurate environmental models. These new kinds of models are still standardized; one of the pioneer de facto standards is OpenDRIVE. This standard was initially defined to be able to express all elements with all potential parameters required in high precision simulations. The actual research focused on creating a compliant virtual model based on mobile mapping measurements. A Leica Pegasus Two mobile mapping system was applied to capture field data about the selected pilot area, which is the campus of Budapest University of Technology and Economics (BME). The obtained Lidar point cloud was georeferenced; the merged point cloud is tailored to the driven trajectory, and then it has been evaluated manually. The acquired land use map is converted - similarly manually - into basic road geometry elements: straight lane and bended lane segments. These objects are finally compiled into an XML format, which is compliant with the OpenDRIVE standard. The achieved virtual model has been tested in Driving Scenario Designer of Mathworks Matlab; however, it is promptly ready for use in other widely applied automotive simulators.