Open Access

ARTICLE

FSS-YOLO: The Lightweight Drill Pipe Detection Method Based on YOLOv8n-obb

Mingyang Zhao^1,2,*, Xiaojun Li^1,3, Miao Li^1,2, Bangbang Mu^1,2

1 School of Energy Science and Engineering, Henan Polytechnic University, Jiaozuo, 454003, China
2 School of Innovation and Entrepreneurship, Henan Polytechnic University, Jiaozuo, 454003, China
3 Henan International Joint Laboratory of Coalmine Ground Control, Jiaozuo, 454003, China

* Corresponding Author: Mingyang Zhao. Email:

Computers, Materials & Continua 2025, 84(2), 2827-2846. https://doi.org/10.32604/cmc.2025.065251

Received 07 March 2025; Accepted 08 May 2025; Issue published 03 July 2025

Abstract

The control of gas extraction in coal mines relies on the effectiveness of gas extraction. The main method of gas extraction is to drive drill pipes into the coal seam through a drilling rig and use technologies such as hydraulic fracturing to pre-extract gas in the drill holes. Therefore, the real-time detection of the drill pipe status is closely related to the effectiveness of gas extraction. To achieve fast and accurate identification of drill pipes, we propose FSS-YOLO, which is a lightweight drill pipe detection method based on YOLOv8n-obb. This method first introduces the FasterBlock module into the C2f module of YOLOv8n-obb to reduce the number of model parameters and decrease the computational cost of the model and redundant feature maps. Next, the SimAM attention mechanism is added to the backbone network to enhance the weight of important features in the feature map and improve the model’s feature extraction capability. In addition, using shared convolution to optimize the detection head, not only lightens the detection head but also enhances its ability to learn features of different scales, improving the model’s generalization ability. Finally, the FSS-YOLO algorithm is validated on the self-built dataset. The results show that compared with the original algorithm, FSS-YOLO achieves improvements of 5.1% in mAP50 and 11.5% in Recall, reduces the number of parameters by 45.8%, and achieves an inference speed of 27.8 ms/frame on Jetson Orin NX. Additionally, the visual detection results for different scenarios demonstrate that the improved YOLOv8n-obb algorithm has promising application prospects.

---

Keywords

---