Real-Time Strip Steel Defect Detection Algorithm Fused with Transformer

doi:10.3778/j.issn.1002-8331.2210-0450

Abstract

Abstract: In the production process of strip steel, surface defects often affect the quality of products. Aiming at the problems of poor detection accuracy and low detection efficiency of existing detection methods for small target defects on strip steel surface, a real-time detection algorithm TRSD-YOLO（Transformer real-time strip steel defects detection YOLO） fused with Transformer is proposed. Firstly, a feature extraction module BottleNeckCSPTR combined with Transformer’s self-attention mechanism is designed to enhance the module’s ability to obtain small target defect information through the enhancement of self-attention. Secondly, the BottleNeckCSPTR module is used to build a new backbone feature extraction network CSPDarknetTR, and the dynamic activation function Meta-ACON is integrated with the backbone to further strengthen the network’s ability to represent defect features. Finally, a lightweight bidirectional weighted feature pyramid structure BiFPN-Light is proposed as a way to fuse multi-scale features to improve the network’s detection accuracy for small defects. The experimental results show that the algorithm proposed in this paper achieves a mAP of 82.2% on the NEU-DET dataset, which is 5.3 percentage points higher than the original YOLOv4 algorithm. At the same time, the detection speed reaches 31.3 FPS, which can meet the needs of industrial scenarios.

Key words: strip steel defect detection, YOLOv4, Transformer, bidirectional feature pyramid network（BiFPN）

摘要： 在带钢的生产过程中通常会产生影响产品质量的表面缺陷。针对带钢表面缺陷检测效率低以及小目标缺陷检测精度差的问题，提出一种融合Transformer的带钢缺陷实时检测算法TRSD-YOLO（Transformer real-time strip steel defects detection-YOLO）。设计一种结合Transformer自注意力机制的特征提取模块BottleNeckCSPTR，通过自注意力的增强来提升模块对小目标缺陷信息的获取能力；运用BottleNeckCSPTR模块构建新的主干特征提取网络CSPDarknetTR，并将动态激活函数Meta-ACON与主干网络相融合，进一步强化网络对缺陷特征的表示能力；提出一种轻量级双向加权特征金字塔结构BiFPN-Light作为融合多尺度特征的方式，提高网络对小尺寸缺陷的检测精度。实验结果表明，提出的算法在NEU-DET数据集上mAP达到了82.2%，较原有的YOLOv4算法提高了5.3个百分点；同时检测速度达到31.3?FPS，可匹配工业场景的需求。

关键词: 带钢缺陷检测, YOLOv4, Transformer, 双向特征金字塔（BiFPN）

ZHANG Taoyuan, XIE Xinlin, XIE Gang, ZHANG Lin. Real-Time Strip Steel Defect Detection Algorithm Fused with Transformer[J]. Computer Engineering and Applications, 2023, 59(16): 232-239.

张涛源, 谢新林, 谢刚, 张林. 融合Transformer的带钢缺陷实时检测算法[J]. 计算机工程与应用, 2023, 59(16): 232-239.

References

[1] HE Y，SONG K，MENG Q，et al.An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J].IEEE Transactions on Instrumentation and Measurement，2019，69（4）：1493-1504.
[2] 罗东亮，蔡雨萱，杨子豪，等.工业缺陷检测深度学习方法综述[J].中国科学：信息科学，2022，52（6）：1002-1039.
LUO D L，CAI Y X，YANG Z H，et al.Survey on industrial defect detection with deep learning[J].Science in China：Information Sciences，2022，52：1002-1039.
[3] 郭萌，胡辽林，赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报，2016，36（9）：27-33.
GUO M，HU L L，ZHAO J T.Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J].Acta Optica Sinica，2016，36（9）：27-33.
[4] LIU K，LI A，WEN X，et al.Steel surface defect detection using GAN and one-class classifier[C]//2019 25th International Conference on Automation and Computing，2019：1-6.
[5] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28：Annual Conference on Neural Information Processing Systems，2015：91-99.
[6] 向宽，李松松，栾明慧，等.基于改进Faster RCNN的铝材表面缺陷检测方法[J].仪器仪表学报，2021，42（1）：191-198.
XIANG K，LI S S，LUAN M H，et al.Aluminum product surface defect detection method based on improved Faster RCNN[J].Chinese Journal of Scientific Instrument，2021，42（1）：191-198.
[7] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[8] CHOI J，CHUN D，KIM H，et al.Gaussian YOLOv3：an accurate and fast object detector using localization uncertainty for autonomous driving[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision，2019：502-511.
[9] WANG C Y，BOCHKOVSKIY A，LIAO H Y M.Scaled-YOLOv4：scaling cross stage partial network[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13029-13038.
[10] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision，2017：2980-2988.
[11] 李维刚，叶欣，赵云涛，等.基于改进YOLOv3算法的带钢表面缺陷检测[J].电子学报，2020，48（7）：1284-1292.
LI W G，YE X，ZHAO Y T，et al.Strip steel surface defect detection based on improved YOLOv3 algorithm[J].Acta Electronica Sinica，2020，48（7）：1284-1292.
[12] KOU X，LIU S，CHENG K，et al.Development of a YOLO-V3-based model for detecting defects on steel strip surface[J].Measurement，2021，182：109454.
[13] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems 30：Annual Conference on Neural Information Processing Systems，2017：5998-6008.
[14] DOSOVITSKIY A，BEYER L，KOLESNIKOV A，et al.An image is worth 16x16 words：transformers for image recognition at scale[C]//Proceedings of the 9th International Conference on Learning Representations，2021.
[15] CARION N，MASSA F，SYNNAEVE G，et al.End-to-end object detection with transformers[C]//Proceedings of the 16th European Conference on Computer Vision.Cham：Springer，2020：213-229.
[16] MA N，ZHANG X，LIU M，et al.Activate or not：learning customized activation[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：8032-8042.
[17] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.
[18] BAO Y Q，SONG K C，LIU J，et al.Triplet-graph reasoning network for few-shot metal generic surface defect segmentation[J].IEEE Transactions on Instrumentation and Measurement，2021，70：1-11.
[19] SELVARAJU R R，COGSWELL M，DAS A，et al.Grad-CAM：visual explanations from deep networks via gradient-based localization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision，2017：618-626.