Logo des Repositoriums

Auflistung nach Autor:in "Pamornnak, Burawich"

1 - 4 von 4
  • Konferenzbeitrag
    A digital weed counting system for the weed control performance evaluation
    (42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft, 2022) Pamornnak, Burawich; Scholz, Christian; Becker, Silke; Ruckelshausen, Arno
    The weed counting method is one of the keys to indicate the performance of the weed control process. This article presents a digital weed counting system to use instead of a conventional manual counting system called “Göttinger Zähl- und Schätzrahmen” or “Göttinger Rahmen” due to the limitation of human counting on big-scale field experiment areas. The proposed method demonstrated on the maize field consists of two main parts, a virtual weed counting frame and a weed counting core, respectively. The system was implemented as a mobile application for the smartphone (Android) with server-based processing. The pre-processed image on the mobile phone will be sent to the weed counting core based on the pre-trained convolution neural network model (CNN or deep learning) on the server. Finally, the number of detected weeds will be sent back to the mobile phone to show the results. In the first implementation, 100 frames on a 1-hectare field area were evaluated. The absolute weed counting errors were categorized into three groups, A-Group (0-10 weeds error) achieves 73 %, B-Group (11-20 weeds error) achieves 17 %, and C-Group (21-30 weeds error) achieves 10 %, respectively. For overall performance, the system achieves the  = 0.97 from the correlation and 12.8 % counting error. These results show the digital version of “Göttinger Rahmen” has the potential to become a practical tool for weed control evaluations.
  • Konferenzbeitrag
    Field plant characterization method based on a multi-wavelength line profiling system
    (41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten, 2021) Pamornnak, Burawich; Scholz, Christian; Nieberg, Dominik; Igelbrink, Matthias; Ruckelshausen, Arno
    Phenotyping of plant characteristics is essential for plant breeding. Especially the growth stages of plants during field emergence, described by parameters such as plant height and plant counting, are of interest. But large-scale manual phenotyping is very inconvenient due to the workload, the harsh weather conditions, and time-consumption. Therefore, an automated system is needed. This research describes a field plant characterization method implemented in a plot divider machine for rapeseeds. The method consists of a plant height estimation and a plant counting system. Based on a multi-wavelength line profiling (MWLP) sensor system, the 2D and 3D point cloud information from visible wavelengths to near-infrared (NIR) are automatically mapped without any need for a matching method. The plant characterization processes consist of two main steps, 1) plant detection, and 2) height estimation. These processes use the 2D NIR and 3D point cloud as the main features. The proposed method was demonstrated with highly accurate results in several rapeseeds, illustrating the potential of this method to become a basic tool for crop characterization in plant sciences
  • Konferenzbeitrag
    “Ready for Autonomy (R4A)”: concept and application for autonomous feeding
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Pamornnak, Burawich; Scholz, Christian; Gode, Eduard; Sommer, Karen; Novak, Timo; Hellermann, Steffen; Wegmann, Benjamin; Ruckelshausen, Arno
    This paper presents the development of the “Ready for Autonomy (R4A)” application for evaluating the feasibility of integrating an autonomous feeding machine Strautmann Verti-Q into farmyards and evaluating the machine’s performance. The proposed application consists of three main R4A checklists for telling whether the farmyard, the machine, and the farmer are ready for autonomy or not. The farmyard is the first part to be checked with the R4A application with the Verti-Q system requirements. The R4A result will be instantly generated from the application based on the Boolean function. The second part is the machine operation record which tells the overall performance of the Verti-Q machine as the R4A distribution results, e.g., excellent, good, and failure. The final part is the farmer operation training in manual and autonomous modes, in which farmers have to go through every topic to be ready to use the machine. From the experimental results, seven farmyards were observed with the R4A application. Therefore, the four farmyards are ready for autonomy with different R4A levels. The minimum working condition of the Verti-Q machine has been tested on the lowest R4A level farmyard. The distribution results from the prototype machine with 218 autonomous feeding jobs, achieving 42% in excellent distribution, 38% in good condition, and 21% in failure caused by various reasons, e.g., hardware, software, and user error, respectively. These results show the possibility of using the improved version of the autonomous feeding machine in the farmyard for sustainable farming in the future.
  • Konferenzbeitrag
    Von der Forschung in die Praxis: das KI-basierte optisch-selektive mechanische Beikrautregulierungssystem MWLP-Weeder in verschiedenen Trägersystemen im Feldeinsatz
    (41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten, 2021) Strothmann, Wolfram; Scholz; Pamornnak, Burawich; Ruckelshausen, Arno
    Mechanische Beikrautregulierung gewinnt in der landwirtschaftlichen Praxis eine zunehmende Bedeutung. Während sich hierbei für den Zwischenreihenbereich („inter-row“) kommerzielle Lösungen, insb. mit kamerabasierter Reihenerkennung, mittlerweile durchgesetzt haben, und auch für den Bereich zwischen den Pflanzen in der Reihe („intrarow“) erste Systeme kommerziell verfügbar sind, ist mechanisches Hacken im Bereich nahe der Pflanze („close-to-crop“) nach wie vor eine Herausforderung. Gerade für Pflanzen in BBCH-Stadien 10 bis 12 sind hier noch keine optisch angesteuerten Systeme kommerziell verfügbar. Durch den MWLP-Weeder kann diese Lücke geschlossen werden. Der MWLP-Weeder zeichnet sich durch eine Multi-Stempelaktorik in Kombination mit optischer Sensorik und intelligenter Pflanzenerkennung aus, welche eine flächige Bearbeitung von Beikräutern speziell auch sehr nahe an den Nutzpflanzen ermöglicht. Aufbauend auf Forschungsergebnissen wurde das System in 2020 aufgebaut und im Experimentierfeld AgroNordWest sowie im praktischen Ökolandbau – sowohl im Roboterbetrieb als auch als Anbau-gerät für einen Traktor – getestet.