Object detection characteristics in a learning factory environment using YOLOv8
This work addresses object detection challenges in industrial settings for researchers and practitioners, but it is incremental as it applies an existing method to new data.
The paper systematically investigates how background influences and object features like materials and surfaces affect object detection accuracy in an Industry 4.0 learning factory, using YOLOv8 models trained on varying datasets, with results showing unexpected behaviors and contributions including a challenging dataset and analysis of 92 trained models.
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.