TY - GEN A1 - Schneidereit, Toni A1 - Gohrenz, Stefan A1 - Breuß, Michael T1 - Object detection characteristics in a learning factory environment using YOLOv8 N2 - AI-based object detection, and efforts to explain and investigate their characteristics, is a topic of high interest. The impact of, e.g., complex background structures with similar appearances as the objects of interest, on the detection accuracy and, beforehand, the necessary dataset composition are topics of ongoing research. In this paper, we present a systematic investigation of background influences and different features of the object to be detected. The latter includes various materials and surfaces, partially transparent and with shiny reflections in the context of an Industry 4.0 learning factory. Different YOLOv8 models have been trained for each of the materials on different sized datasets, where the appearance was the only changing parameter. In the end, similar characteristics tend to show different behaviours and sometimes unexpected results. While some background components tend to be detected, others with the same features are not part of the detection. Additionally, some more precise conclusions can be drawn from the results. Therefore, we contribute a challenging dataset with detailed investigations on 92 trained YOLO models, addressing some issues on the detection accuracy and possible overfitting. Y1 - 2025 U6 - https://doi.org/https://doi.org/10.48550/arXiv.2503.10356 VL - 2503.10356 SP - 1 EP - 18 ER - TY - GEN A1 - Schneidereit, Toni A1 - Gohrenz, Stefan A1 - Breuß, Michael T1 - Object detection characteristics in a learning factory environment using YOLOv8 T2 - Intelligent systems and applications : proceedings of the 2025 Intelligent Systems Conference (IntelliSys) : volume 2 N2 - AI-based object detection, and efforts to explain and investigate their characteristics, is a topic of high interest. The impact of, e.g., complex background structures with similar appearances as the objects of interest, on the detection accuracy and, beforehand, the necessary dataset composition are topics of ongoing research. In this study, we present a systematic investigation of background influences and different features of the object to be detected. The latter includes various materials and surfaces, partially transparent and with shiny reflections in the context of an Industry 4.0 learning factory. Different YOLOv8 models have been trained for each of the materials on different sized datasets, where the appearance was the only changing parameter. In the end, similar characteristics tend to show different behaviours and sometimes unexpected results. While some background components tend to be detected, others with the same features are not part of the detection. Additionally, some more precise conclusions can be drawn from the results. Therefore, we contribute a challenging dataset with detailed investigations on 92 trained YOLO models, addressing some issues on the detection accuracy and possible overfitting. KW - Object detection KW - Dataset construction KW - Complex KW - background KW - YOLO characteristics KW - YOLO heatmaps KW - Learning KW - factory Y1 - 2025 SN - 978-3-032-00071-2 U6 - https://doi.org/https://doi.org/10.1007/978-3-032-00071-2_18 SN - 2367-3370 VL - 2 SP - 288 EP - 308 PB - Springer Nature Switzerland CY - Cham ER -