Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kacper Podbucki has a total of 14 co-authors. Here are the top co-authors by number of shared publications:

  • Jakub Suder

    Division of Signal Processing and Electronic Systems, Institute of Automatic Control and Robotics, Faculty of Automatic Control, Robotics and Electrical Engineering, Poznan University of Technology, ul. Jana Pawla II 24, 60-965 Poznan, Poland

    15 shared publications
  • Tomasz Marciniak

    10 shared publications
  • Tomasz Marciniak

    Division of Electronic Systems and Signal Processing, Institute of Automatic Control and Robotics, Poznan University of Technology, 60-965 Poznan, Poland

    9 shared publications
  • Adam Dąbrowski

    Poznan University of Technology, Faculty of Control, Robotics & Electrical Engineering, Institute of Automatic Control and Robotics, ul. Piotrowo 3a, 60-965 Poznan, Poland

    5 shared publications
  • Adam Dabrowski

    Poznan University of Technology, Robotics, and Electrical Engineering, Institute of Automatic Control and Robotics,Faculty of Automatic Control, Division of Electronic Systems and Signal Processing,Pozna,Poland,60-965

    4 shared publications
  • Adam Dąbrowski

    3 shared publications

Latest Publications

  • Open Access

    Cost-Effective Edge AI: Hailo-8 Powered Raspberry Pi vs. NVIDIA Jetson AGX Orin in Airport Infrastructure Monitoring

    by Kacper Podbucki, Bartłomiej Szalwach

    The automatic inspection of airport infrastructure, specifically horizontal surface markings and Airfield Ground Lighting (AGL), is a critical task for maintaining aviation safety and operational efficiency. As the aviation industry shifts from manual surveys to automated visual inspections utilizing unmanned aerial vehicles (UAVs) and smart service vehicles, the demand for robust, real-time computer vision systems has surged. However, deploying computationally intensive deep learning models in the field introduces severe Size, Weight, and Power (SWaP) constraints. This paper presents a comprehensive framework for the semantic segmentation of runway/taxiway markings and the point-localization of AGL lamps, specifically focusing on the deployment paradigm shift from the expensive, GPU-accelerated heterogeneous system on chip (SoC) to highly efficient, dedicated Neural Processing Units (NPUs). We evaluate the performance of U-Net, LinkNet, U-Net-Point and HRNet-Lite-Point architectures trained on a custom dataset from the Poznań-Ławica Airport. Crucially, this study conducts a rigorous comparative hardware analysis between the flagship NVIDIA Jetson AGX Orin and a highly cost-effective heterogeneous setup comprising a Raspberry Pi 5 augmented with an NPU Hailo-8 AI accelerator. Experimental results demonstrate that while both platforms achieve real-time inference, the Hailo-8 integration fundamentally disrupts the traditional cost-to-performance ratio. Furthermore, the Hailo-8 configuration consumed less electrical power and memory footprint required by the Jetson, proving that dedicated NPUs are vastly superior for continuous, battery-operated edge deployment in autonomous airport maintenance systems. Specifically, the Raspberry Pi setup with the Hailo-8 accelerator demonstrated superior energy efficiency, requiring a significantly lower energy consumption per processed video frame compared to the Jetson platform.


  • Comparison of GNSS Modules in Application for Localization in Restricted Areas

    by Kacper Podbucki

    This paper investigates the positioning accuracy of four standalone GNSS modules: Teseo-LIV4F, Teseo-LIV3F, NEO-6M, and SIM28 in restricted environments where differential correction methods such as RTK and DGPS are not available. The research aims to evaluate the feasibility of reliable localization using only raw GNSS data, with a specific focus on accuracy under satellite visibility and HDOP conditions. Two experimental approaches were employed: static tests, where modules were placed at a fixed, known position, and dynamic tests, conducted along a defined trajectory. Position estimates for each module were recorded over time and compared with a reference dataset. The analysis considered the influence of environmental conditions, HDOP values, and the number of visible satellites on the overall positioning error. The results show notable differences in accuracy between the modules tested, and Teseo-LIV4F generally outperforms others in both static and dynamic scenarios. The study highlights the impact of GNSS hardware design, satellite geometry, and firmware algorithms on the reliability of GNSS alone. These findings offer practical insights for developers and researchers designing navigation systems for constrained applications in which precise localization is required without access to correction services.

  • Technical Acoustics Laboratory Course Series

    by Kacper Podbucki, Szymon Drgas

    The article presents an overview of laboratory exercises in the subject of Technical Acoustics at the academic level. They include issues related to the study of the characteristics of audio equipment such as amplifiers, microphones and loudspeakers, both in terms of electronics and acoustic characteristics. Exercises for the analysis of acoustic features of rooms through simulation and real measurements and the use of adaptive filtering methods for sound denoising are also proposed. Students are also introduced to methods of speech feature analysis and classification of audio files based on them. Issues related to psychoacoustics are also discussed, such as frequency discrimination or binaural masking level differences.

    • 9 July 2025

    Wsparcie bezpieczeństwa operacji lotniczych za pomocą zintegrowanych systemów wizyjnych i multisensorycznych

    by Jakub Suder, Kacper Podbucki, Tomasz Marciniak, Adam Dąbrowski

  • Performance analysis of vision AGL light spots detection using embedded devices

    by Kacper Podbucki, Tomasz Marciniak

    The article presents an analysis of the issue concerning the use of embedded devices for the task of detecting the light points of airport AGL lamps. This type of detection is an important preliminary stage of the measuring process for testing the photometric parameters of in-pavement AGL lamps. The algorithm developed during previous studies was tested in two versions: supporting calculations on the CPU and using CUDA technology and performing calculations on the GPU. An experiment was conducted that involved the processing of video sequences from airport areas for the detection of in-pavement AGL lamps in various weather conditions and times of day. The efficiency of the programs was checked by analyzing the average number of frames per second achieved by the program. The software was compared on single-board microcomputers of the Raspberry Pi family and modules of the NVIDIA Jetson family, for which changes in power modes were also taken into account.

  • Camera-based light source localization for precise luminous intensity measurement of airport lamps

    by Kacper Podbucki, Tomasz Marciniak

    Measuring luminous intensity using electronic sensors requires their precise positioning. In the case of mobile measurement platforms, it is important to detect the light source and thus determine the correct direction of movement of the measuring device. This article presents research on a solution for the initial detection of glowing airport lamps based on camera images. The impact of the selection of parameters and image processing methods on the prepared data set was assessed. The histogram filtration method was introduced to improve the effectiveness of airport lamp localization. The proposed solution was investigated in different weather and daytime conditions. The overall accuracy of the proposed solution is more than ${9 0 \%}$.


  • Open Access

    Laboratory Assessment of In-Pavement Airport Lamp’s Luminous Intensity Distribution

    by Kacper Podbucki, Tomasz Marciniak, Jakub Suder

    The luminous intensity measurements of airport navigational lighting should be performed in accordance with the recommendations of the European Aviation Safety Agency (EASA), which allows for the determination of the possibility of further operation or the need to replace particular lamps. This article presents a device and method for measuring the light main beam of in-pavement airport lamps used on runways and taxiways. During the measuring process in the laboratory dark room, the proposed system automatically prepares reports as heatmaps presenting angular relationships of light distribution. Photometric measurements were made using a BH1750 illuminance sensor, which was compared to a certified Sonopan L-200P luxmeter. The measurement stability of different BH1750 modes was investigated for different airport lamp power source thresholds. Due to distortions in spectral characteristic of BH1750, polynomial corrections were proposed. The functionality of the device was presented for the exemplary assessment of used and refurbished runway in-pavement airport lamps to compare their parameters change. The research results and device implementation were possible through scientific cooperation with the Poznań-Ławica Airport.


  • Open Access

    Chromaticity measurement of airport navigation lighting using integrated colour sensor

    by Jakub Suder, Kacper Podbucki, Tomasz Marciniak

    The paper presents an analysis of using a TCS3430 light colour sensor to verify the chromaticity of navigation lighting installed at airports. These measurements can help determine the correct operation of the tested lamp using of specialised measuring devices. The emitted light colour is critical for pilots during flight operations such as takeoff , landing and taxiing, especially in low visibility conditions. Chromaticity standards (in CIE1931 colour space) are specified in the relevant regulations of the European Union Aviation Safety Agency (EASA) and the International Civil Aviation Organisation (ICAO), and require regular inspection of each light point (both in-pavement and elevated lamps). Tests were carried out for various types of aviation navigation lighting lamps. The stability of measurements and possibilities of visualization on the chromaticity chart were assessed. The article also presents software that allows for quick verification of the operation of a given lamp, intended for airport maintenance services.


  • Influence of power supply on airport navigation lamps photometric test accuracy

    by Kacper Podbucki, Jakub Suder, Tomasz Marciniak, Adam Dąbrowski

    The paper presents research on the accuracy of measuring illuminance and chromaticity of airport lamps. The impact of the type of DC and AC power supply on measurement was assessed with the use of electronic sensors. BH1750 and BH1745 type sensors in a microprocessor system with an I 2 C interface were used for the measurements. A professional luxmeter was used for comparison purposes. Experimental tests were carried out under laboratory conditions for three types of halogen lamps: approach system lamps, runway centerline lamps, and touchdown zone lamps.