| 引用本文: | 戴林华,黎远松,石 睿.YOLOv8-SSDW:基于 YOLOv8 的带钢表面缺陷检测算法(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2025，42（4）：44-52 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 目的 针对现有带钢表面缺陷检测精度较低、存在漏检和误检等问题,提出了一种改进 YOLOv8 的缺陷检测
算法 YOLOv8 - SSDW。 方 法 该 算 法 以 YOLOv8n 为 基 准 模 型, 在 骨 干 网 络 结 构 中 引 入 SKNet ( Selective Kernel
Networks) 注意力模块,加强骨干网络的特征提取能力和自适应能力,使网络在特征提取过程中更关注缺陷目标;同
时,在 YOLOv8 的颈部使用 Slim-Neck 结构,减少模型的参数量和计算量;为进一步提升网络的特征提取能力,提
出一种融合可变形卷积,强化对缺陷目标的特征学习;考虑缺陷样本质量不平衡问题,使用 WIoU( wise intersection
over union) 损失函数,其梯度增益分配策略使问题得到有效改善,并且提高模型收敛速度和回归精度。 结果 改进
后的模型在带钢数据集上进行实验,结果表明:改进后的模型的平均精度达到 85. 5%,相比基准模型提高了 2. 7%。
结论 通过大量实验可以证明改进网络的有效性,改善了带钢表面缺陷检测精度较低的问题,减少了漏检和误检的
情况,同时满足实时性要求;相较于目前主流模型,该改进算法在检测精度具有一定优势,对后续研究用于实际检
测具有参考价值。 |
| 关键词: YOLOv8 注意力机制 可变形卷积 WIoU |
| DOI： |
| 分类号: |
| 基金项目: |
|
| YOLOv8-SSDW A Steel Surface Defect Detection Algorithm Based on YOLOv8 |
|
DAI Linhua LI Yuansong SHI Rui
|
|
School of Computer Science and Engineering Sichuan University of Science & Engineering Sichuan Yibin 643002
China
|
| Abstract: |
| Objective In response to the issues of low detection accuracy missed detections and false alarms in existing
steel surface defect detection methods an improved defect detection algorithm YOLOv8-SSDW based on YOLOv8 was
proposed. Methods This algorithm took YOLOv8n as the benchmark model and introduced the SKNet Selective Kernel
Networks attention module into the backbone network structure to enhance the feature extraction and adaptability of the
backbone network allowing the network to pay more attention to defect targets during the feature extraction process. At
the same time the Slim-Neck structure was used in the neck of YOLOv8 to reduce the number of model parameters and
computational load. To further enhance the network ?? s feature extraction capability a deformable convolution fusion
method was proposed to strengthen the feature learning for defect targets. Considering the imbalance in defect sample
quality the WIoU wise intersection over union loss function was used which effectively addressed the issue through its gradient gain allocation strategy enhancing model convergence speed and regression accuracy. Results Experiments on
the steel dataset showed that the average accuracy of the improved model reached 85. 5% which was an increase of 2. 7%
over the benchmark model. Conclusion Extensive experiments demonstrate the effectiveness of the improved network
which resolves the issue of low accuracy in steel strip surface defect detection reduces missed and false detections and
meets real-time requirements. Compared with current mainstream models the proposed model has certain advantages in
detection accuracy and offers a valuable reference for practical detection in future research. |
| Key words: YOLOv8 attention mechanism deformable convolution WIoU |
