Xiong Qiaoqiao, Chen Qipeng, Tang Saihong, Li Yiting
Department of Mechanical and Manufacturing Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia.
Department of Mechanical and Electronic Engineering, Guizhou Communications Polytechnic University, Guiyang, 551400, China.
Sci Rep. 2025 Jan 22;15(1):2879. doi: 10.1038/s41598-025-85721-9.
Deep learning has achieved significant success in the field of defect detection; however, challenges remain in detecting small-sized, densely packed parts under complex working conditions, including occlusion and unstable lighting conditions. This paper introduces YOLOv8-n as the core network to propose VEE-YOLO, a robust and high-performance defect detection model. Firstly, GSConv was introduced to enhance feature extraction in depthwise separable convolution and establish the VOVGSCSP module, emphasizing feature reusability for more effective feature engineering. Secondly, improvements were made to the model's feature extraction quality by encoding inter-channel information using efficient multi-Scale attention to consider channel importance. Precise integration of spatial structural and channel information further enhanced the model's overall feature extraction capability. Finally, EIoU Loss replaced CIoU Loss to address bounding box aspect ratio variability and sample imbalance challenges, significantly improving overall detection task performance. The algorithm's performance was evaluated using a dataset to detect stranded elastic needle defects. The experimental results indicate that the enhanced VEE-YOLO model's size decreased from 6.096 M to 5.486 M, while the detection speed increased from 179FPS to 244FPS, achieving a mAP of 0.926. Remarkable advancements across multiple metrics make it well-suited for deploying deep detection models in complex industrial environments.
深度学习在缺陷检测领域取得了显著成功；然而，在复杂工作条件下检测小尺寸、密集排列的部件仍存在挑战，包括遮挡和不稳定的光照条件。本文引入YOLOv8-n作为核心网络，提出了VEE-YOLO，一种强大且高性能的缺陷检测模型。首先，引入GSConv以增强深度可分离卷积中的特征提取，并建立VOVGSCSP模块，强调特征可重用性以进行更有效的特征工程。其次，通过使用高效多尺度注意力对通道间信息进行编码来考虑通道重要性，从而提高了模型的特征提取质量。空间结构和通道信息的精确整合进一步增强了模型的整体特征提取能力。最后，EIoU Loss取代CIoU Loss以解决边界框宽高比变化和样本不平衡挑战，显著提高了整体检测任务性能。使用一个数据集来检测 stranded elastic needle缺陷对该算法的性能进行了评估。实验结果表明，增强后的VEE-YOLO模型大小从6.096M降至5.486M，而检测速度从179FPS提高到244FPS，mAP达到0.926。在多个指标上的显著进步使其非常适合在复杂工业环境中部署深度检测模型。
