Spatial-Semantic Object Relation Graph Networks for Vehicle Attachment Detection in Automatic Car Wash System

Precise object detection is critical for preventing damage to vehicle attachments during automatic car washing. However, the existing methods often suffer from low accuracy and false detections due to the diverse shapes and visual ambiguity of these attachments. To address these challenges, we propose a novel framework integrating a YOLOv11-based detector with a graph neural network. Specifically, we introduce a spatial graph module to refine object localization by capturing invariant spatial constraints within the car wash environment. Furthermore, we incorporate a class graph module to model inter-class semantic correlations, thereby improving the classification of visually ambiguous objects such as emblems. Experimental results on a real-world dataset demonstrate that our method achieves an mAP50 of 97.9%, outperforming state-of-the-art models including D-FINE 96.5% and RT-DETR 96.1%. These findings confirm the robustness of our approach under varying viewpoints and background conditions, offering a significant improvement in the safety and reliability of automatic car wash systems.