YOLO-DTO: Automotive door panel fastener detection algorithm based on deep learning

Abstract The common detection of fasteners of automobile door panels is based on the template matching method, which has the problems of low detection accuracy and poor real-time performance under the influence of different lighting and different placement positions. To improve the detection speed and accuracy of fasteners in complex scenes, a small object detection algorithm YOLO-DTO (Detect Tiny Object) was proposed based on the YOLOv8 algorithm. Firstly, according to the characteristics of fasteners accounting for fewer image pixels, this paper reconstructs the early stage of the original algorithm by introducing the SPD (space-to-depth) module to retain more fine-grained information about fasteners, secondly, to enhance the algorithm's ability to pay attention to the context information of fasteners, the selective attention module is embedded in the Neck output position of the algorithm, and to optimize the regression efficiency of the bounding box, the CIOU loss function is replaced by the MPDIOU loss function. The experimental results show that the average detection accuracy of the YOLO-DTO algorithm is 98.8%, which is 9.1% and 1.7% higher than that of the template matching method and the YOLOv8 algorithm, respectively, which meets the detection standard of the factory production line and has practical value.