YOLO-WP: A Lightweight and Efficient Algorithm for Small-Target Detection in Weld Seams of Small-Diameter Stainless Steel Pipes

To address the low detection efficiency and high computational resource demands of current welded pipe defect detection algo-rithms for small target defects, this paper proposes the YO-LO-WP algorithm based on YOLOv5s. The improvements of YOLO-WP are mainly reflected in the following aspects: First, an innovative GhostFusion architecture is introduced in the backbone network. By replacing the C3 modules with C2f mod-ules and integrating the Ghost CBS module inspired by Ghost convolution, cross-stage feature fusion is achieved, significantly enhancing computational efficiency and feature representation for small target defects. Second, the Slim-Neck lightweight de-sign based on GSConv is employed in the neck to further opti-mize the network structure and reduce the number of parame-ters. Additionally, the SimAM lightweight attention mechanism is incorporated to improve the network's ability to extract de-fect features, and the Focal-EIou loss is utilized to optimize CIou loss, thereby enhancing small object detection and accelerating loss convergence. The experimental results show that the AP(D1) and mAP@0.5 of the YOLO-WP model are improved by 5.3% and 3%, respectively, over the original model. In addi-tion, the number of model parameters and FLOPs are reduced by 40% and 45%, respectively, achieving a good balance be-tween performance and efficiency. We evaluated the perfor-mance of YOLO-WP using other datasets and showed that YOLO-WP exhibits excellent applicability. Compared to exist-ing mainstream detection algorithms, YOLO-WP is more ad-vanced. The YOLO-WP model significantly enhances produc-tion quality in industrial defect detection, laying the foundation for building compact, high-performance embedded weld pipe surface defect detection systems.

@article{Hou2025,
  title     = {YOLO-WP: A Lightweight and Efficient Algorithm for Small-Target Detection in Weld Seams of Small-Diameter Stainless Steel Pipes},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {16},
  number    = {1},
  year      = {2025},
  publisher = {The Science and Information Organization},
  author    = {Huaishu Hou and Yukun Sun and Chaofei Jiao},
  doi       = {10.14569/IJACSA.2025.0160168},
  url       = {https://doi.org/10.14569/IJACSA.2025.0160168}
}