{"publisher":"KIT Scientific Publishing","publication":"Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024","publication_identifier":{"isbn":["978-3-7315-1386-5"]},"quality_controlled":"1","doi":"10.58895/ksp/1000174496-7","department":[{"_id":"DEP5023"}],"author":[{"last_name":"Senke","full_name":"Senke, Hanna","first_name":"Hanna"},{"first_name":"Dennis","full_name":"Sprute, Dennis","last_name":"Sprute"},{"first_name":"Ulrich","id":"81453","last_name":"Büker","full_name":"Büker, Ulrich","orcid":"0000-0002-4403-3889"},{"first_name":"Holger","last_name":"Flatt","full_name":"Flatt, Holger"}],"date_created":"2025-05-08T14:01:20Z","user_id":"81453","publication_status":"published","title":"Deep learning-based localisation of combine harvester components in thermal images","type":"conference_editor_article","date_updated":"2025-05-08T14:19:15Z","year":"2024","citation":{"apa":"Senke, H., Sprute, D., Büker, U., & Flatt, H. (2024). Deep learning-based localisation of combine harvester components in thermal images. In Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024. KIT Scientific Publishing. https://doi.org/10.58895/ksp/1000174496-7","mla":"Senke, Hanna, et al. “Deep Learning-Based Localisation of Combine Harvester Components in Thermal Images.” Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024, KIT Scientific Publishing, 2024, https://doi.org/10.58895/ksp/1000174496-7.","ieee":"H. Senke, D. Sprute, U. Büker, and H. Flatt, Deep learning-based localisation of combine harvester components in thermal images. KIT Scientific Publishing, 2024. doi: 10.58895/ksp/1000174496-7.","bjps":"Senke H et al. (2024) Deep Learning-Based Localisation of Combine Harvester Components in Thermal Images. KIT Scientific Publishing.","havard":"H. Senke, D. Sprute, U. Büker, H. Flatt, Deep learning-based localisation of combine harvester components in thermal images, KIT Scientific Publishing, 2024.","din1505-2-1":"Senke, Hanna ; Sprute, Dennis ; Büker, Ulrich ; Flatt, Holger: Deep learning-based localisation of combine harvester components in thermal images : KIT Scientific Publishing, 2024","short":"H. Senke, D. Sprute, U. Büker, H. Flatt, Deep Learning-Based Localisation of Combine Harvester Components in Thermal Images, KIT Scientific Publishing, 2024.","van":"Senke H, Sprute D, Büker U, Flatt H. Deep learning-based localisation of combine harvester components in thermal images. Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024. KIT Scientific Publishing; 2024.","ama":"Senke H, Sprute D, Büker U, Flatt H. Deep Learning-Based Localisation of Combine Harvester Components in Thermal Images. KIT Scientific Publishing; 2024. doi:10.58895/ksp/1000174496-7","ufg":"Senke, Hanna u. a.: Deep learning-based localisation of combine harvester components in thermal images, o. O. 2024.","chicago-de":"Senke, Hanna, Dennis Sprute, Ulrich Büker und Holger Flatt. 2024. Deep learning-based localisation of combine harvester components in thermal images. Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024. KIT Scientific Publishing. doi:10.58895/ksp/1000174496-7, .","chicago":"Senke, Hanna, Dennis Sprute, Ulrich Büker, and Holger Flatt. Deep Learning-Based Localisation of Combine Harvester Components in Thermal Images. Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024. KIT Scientific Publishing, 2024. https://doi.org/10.58895/ksp/1000174496-7."},"abstract":[{"lang":"eng","text":"It is crucial to identify defective machine components\r\nin production to ensure quality. Some components generate heat\r\nwhen defective, so automating the inspection process with a\r\nthermal imaging camera can provide qualitative measurements.\r\nThis work aims to use computer vision methods to locate these\r\ncomponents in thermal images. Since there is currently no\r\ncomparison of object detection and semantic segmentation algorithms\r\nfor this use case, this study compares different architectures\r\nwith the goal of localising these components for further\r\ndefect inspection. Moreover, as there are currently no datasets\r\nfor this use case, this study contributes a novel annotated dataset\r\nof thermal images of combine harvester components. The different\r\nalgorithms are evaluated based on the quality of their predictions\r\nand their suitability for further defect inspection. As\r\nsemantic segmentation and object detection cannot be directly\r\ncompared with each other, custom weighted metrics are used.\r\nThe architectures evaluated include RetinaNet, YOLOV8 Detector,\r\nDeepLabV3+, and SegFormer. Based on the experimental\r\nresults, semantic segmentation outperforms object detection regarding\r\nthe use case, and the SegFormer architecture achieves\r\nthe best results with a weighted MeanIOU of 0.853."}],"_id":"12904","status":"public","language":[{"iso":"eng"}]}