Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO
Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approach...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/15/4817 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406314318397440 |
|---|---|
| author | Xinyu Wang Shuhui Ma Shiting Wu Zhaoye Li Jinrong Cao Peiquan Xu |
| author_facet | Xinyu Wang Shuhui Ma Shiting Wu Zhaoye Li Jinrong Cao Peiquan Xu |
| author_sort | Xinyu Wang |
| collection | DOAJ |
| description | Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems. |
| format | Article |
| id | doaj-art-22094e4d1ebe4a418a26db3ba3eb535c |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-22094e4d1ebe4a418a26db3ba3eb535c2025-08-20T03:36:26ZengMDPI AGSensors1424-82202025-08-012515481710.3390/s25154817Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLOXinyu Wang0Shuhui Ma1Shiting Wu2Zhaoye Li3Jinrong Cao4Peiquan Xu5School of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Arts and Sciences, Northeast Agricultural University, Harbin 150030, ChinaSchool of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Lilac, Harbin Institute of Technology (Weihai), Weihai 264209, ChinaSchool of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaAutomated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems.https://www.mdpi.com/1424-8220/25/15/4817MBDNetYOLOdynamic align fusionMultiSEAMInner-SIoUsteel surface defect detection |
| spellingShingle | Xinyu Wang Shuhui Ma Shiting Wu Zhaoye Li Jinrong Cao Peiquan Xu Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO Sensors MBDNet YOLO dynamic align fusion MultiSEAM Inner-SIoU steel surface defect detection |
| title | Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO |
| title_full | Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO |
| title_fullStr | Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO |
| title_full_unstemmed | Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO |
| title_short | Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO |
| title_sort | detection of surface defects in steel based on dual backbone network mbdnet attention yolo |
| topic | MBDNet YOLO dynamic align fusion MultiSEAM Inner-SIoU steel surface defect detection |
| url | https://www.mdpi.com/1424-8220/25/15/4817 |
| work_keys_str_mv | AT xinyuwang detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo AT shuhuima detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo AT shitingwu detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo AT zhaoyeli detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo AT jinrongcao detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo AT peiquanxu detectionofsurfacedefectsinsteelbasedondualbackbonenetworkmbdnetattentionyolo |