An Improved YOLOX Model for Detecting Strip Surface Defects. Issue 11 (23rd September 2022)

• Record Type: Journal Article
• Authors: Yi, Cancan; Xu, Biao; Chen, Jun; Chen, Qirui; Zhang, Lei
• Is Part Of: Steel research international. Volume 93:Issue 11(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-09-23
• Subjects: attention mechanisms -- deep learning -- defect detections -- efficient intersection over union losses -- you only look once X; Steel -- Periodicals; Steel -- Metallurgy -- Periodicals; 669.142
• DOI: 10.1002/srin.202200505
• Languages: English
• ISSNs: 1611-3683

Abstract

Abstract : During the process of producing hot‐rolled strips in the metallurgical industry, various defects inevitably appear on its surface due to harsh environments and complex manufacturing, consequently bringing about quality problems and economic loss. However, the existing detection methods are difficult to meet the actual requirements of commercial production due to their problems, such as low efficiency and low accuracy. Herein, an improved You only look once X (YOLOX) model for detecting strip surface defects is proposed. Based on the existing YOLOX model, herein, the MobileViT block is introduced to enhance the capability of feature extraction of the backbone network output. The feature pyramid networks through efficient channel attention (ECA) module to strengthen important channel weights are improved, and finally, the original positioning loss function by efficient intersection over union (EIOU) to increase the locating accuracy is replaced. The experimental results show that the improved YOLOX model can obtain 80.67 mAP and 75.69 mAP detection effects on the Northeast University dataset and Xsteel surface defect dataset, respectively. Compared with the original YOLOX, the model increases by 3.95 mAP and 4.02 mAP, respectively. The data fully show that the improved YOLOX model proposed herein is more effective for strip surface defect detection. Abstract : Based on the You only look once X (YOLOX) model, herein, the MobileViT block to strengthen the backbone network is used; meanwhile, the efficient channel attention (ECA) module to improve the feature pyramid performance is performed, and the efficient intersection over union (EIOU) as the loss function is finally used. The improved model can get nearly 4%AP improvement.