Shuo Gao
ABSTRACT
Steel surface quality inspection is a necessary process to ensure industrial product quality. With the development of the industrial internet of things (IIoT), deep learning methods started to detect defects for high efficiency and accuracy. It is challenging to improve the model's performance when considering the different characteristics of the device in the IIoT scenario. There is a tremendous amount of computing resources in the cloud and limited computing power on edge devices. A lightweight deep neural detection network with a Dynamic structural re-parameterization strategy, Multi-task Enhanced Module, and Dual weight label assignment method (DN-DMD) is thus proposed for steel surface detection in the IIoT. To utilize the computing power in the cloud, a dynamic learning strategy is first designed to expand the backbone's structure with high significance to extract more information during training. The model can be losslessly compressed into a lightweight model by structural re-parameterization during inferencing on edge devices. Secondly, a lightweight Multi-task Enhanced Module is embedded to improve scale, spatial, and task perception features. Finally, an anchor-free label assignment method called dual weight assignment is applied to develop more information from positive and negative samples to improve performance without inference cost. This DN-DMD has been proven to achieve much better mean average precision (MAP) and mean average recall (MAR) than traditional methods.
- Ghorai S, Mukherjee A, Gangadaran M and Dutta P K (2013). Automatic Defect Detection on Hot-Rolled Flat Steel Products IEEE Transactions on Instrumentation and Measurement 62 612-621Google Scholar
Cross Ref
- Hao R, Lu B, Cheng Y, Li X and Huang B (2021). A Steel Surface Defect Inspection Approach towards Smart Industrial Monitoring Journal of Intelligent Manufacturing 32 1833-1843Google Scholar
- Chen T, Tian G.Y, Sophian A and Que P.W (2008). Feature Extraction and Selection for Defect Classification of Pulsed Eddy Current NDT NDT & E International 41 467-476Google Scholar
- Liu Y, Xu K and Xu J (2019). An Improved MB-LBP Defect Recognition Approach for the Surface of Steel Plates Applied Sciences 9 4222Google Scholar
- Liu K, Luo N, Li A, Tian Y, Sajid H and Chen H (2020). A New Self-Reference Image Decomposition Algorithm for Strip Steel Surface Defect Detection IEEE Transactions on Instrumentation and Measurement 69 4732-4741Google Scholar
- He Y, Song K, Meng Q and Yan Y (2020). An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features IEEE Transactions on Instrumentation and Measurement 69 1493-1504Google Scholar
- Konovalenko I, Maruschak P and Brevus V (2021). Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks Journal of Computing and Information Science in Engineering 22Google Scholar
- Chen X, Lv J, Fang Y and Du S (2022). Online Detection of Surface Defects Based on Improved YOLOV3 Sensors 22 817Google Scholar
- Li M, Wang H and Wan Z (2022). Surface Defect Detection of Steel Strips Based on Improved YOLOv4 Computers and Electrical Engineering 102 108208Google Scholar
- Cheng X and Yu J 2020 RetinaNet with Difference Channel Attention and Adaptively Spatial Feature Fusion for Steel Surface Defect Detection IEEE Transactions on Instrumentation and Measurement 70 2503911Google Scholar
- Gao Y, Lin J, Xie J and Ning Z (2021). A Real-Time Defect Detection Method for Digital Signal Processing of Industrial Inspection Applications IEEE Transactions on Industrial Informatics 17 3450-3459Google Scholar
- Yu J, Cheng X and Li Q (2022). Surface Defect Detection of Steel Strips Based on Anchor-Free Network With Channel Attention and Bidirectional Feature Fusion IEEE Transactions on Instrumentation and Measurement 71 5000710Google Scholar
- Zhang J, Jing J, Lu P and Song S 2022 Improved MobileNetV2-SSDLite for Automatic Fabric Defect Detection System Based on Cloud-Edge Computing Measurement 201 111665Google Scholar
- Guan L, Jia L, Xie Z and Yin C 2022 A Lightweight Framework for Obstacle Detection in the Railway Image Based on Fast Region Proposal and Improved YOLO-Tiny Network IEEE Transactions on Instrumentation and Measurement 5009116Google Scholar
- Liu Z, Lyu W, Wang C, Guo Q, Zhou D and Xu W 2022 D-CenterNet: An Anchor-Free Detector With Knowledge Distillation for Industrial Defect Detection IEEE Transactions on Instrumentation and Measurement 71 2518412Google Scholar
- Zhang Z.-K, Zhou M.-L, Shao R, Li M and Li G 2022 A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation Computational Intelligence and Neuroscience 2022 e6174255Google Scholar
- Huang T, You S, Zhang B, Du Y, Wang F, Qian C and Xu C 2022 DyRep: Bootstrapping Training with Dynamic Re-Parameterization Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE: New Orleans, LA, USA pp. 578-587Google Scholar
- Ren S, He K, Girshick R and Sun J 2017 Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks IEEE Transactions on Pattern Analysis and Machine Intelligence 39 1137-1149Google ScholarDigital Library
- Redmon J, Divvala S, Girshick R and Farhadi A 2016 You Only Look Once: Unified, Real-Time Object Detection Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) IEEE: New York pp. 779-788Google Scholar
- Chen Q, Wang Y, Yang T, Zhang X, Cheng J and Sun J 2021 You Only Look One-Level Feature Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 13034-13043Google Scholar
- Ge Z, Liu S, Wang F, Li Z and Sun J 2021 YOLOX: Exceeding YOLO Series in 2021Google Scholar
- Ding X, Zhang X, Han J and Ding G 2021 Diverse Branch Block: Building a Convolution as an Inception-like Unit Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 10881-10890Google Scholar
- Ding X, Zhang X, Ma N, Han J, Ding G and Sun J 2021 RepVGG: Making VGG-Style ConvNets Great Again Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 13728-13737Google Scholar
- Dai X, Chen Y, Xiao B, Chen D, Liu M, Yuan L and Zhang L 2021 Dynamic Head: Unifying Object Detection Heads with Attentions Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 7369-7378Google Scholar
- Li S, He C, Li R and Zhang L 2022 A Dual Weighting Label Assignment Scheme for Object Detection Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 9377-9386Google Scholar
- Lin T.-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P and Zitnick C.L 2014 Microsoft COCO: Common Objects in Context Proceedings of the Computer Vision – ECCV 2014 Fleet D, Pajdla T, Schiele B, Tuytelaars T, Eds.; Springer International Publishing: Cham, 2014; pp. 740-755Google Scholar
Index Terms
- A Dynamic Learning Network for Steel Surface Inspection Based on Structural Re-parameterization
Recommendations
Surface Parameterization Using Riemann Surface Structure
ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2We propose a general method that parameterizes general surfaces with complex (possible branching) topology using Riemann surface structure. Rather than evolve the surface geometry to a plane or sphere, we instead use the fact that all orientable ...
Brain surface parameterization using riemann surface structure
MICCAI'05: Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part IIWe develop a general approach that uses holomorphic 1- forms to parameterize anatomical surfaces with complex (possibly branching) topology. Rather than evolve the surface geometry to a plane or sphere, we instead use the fact that all orientable ...
Quasi-isometric surface parameterization
Applied scientific computing: Recent approaches to grid generation, approximation and numerical modellingParameterization of surface is defined by a one-to-one mapping from a planar domain to the surface. Well established methods based on harmonic, conformal and quasi-conformal mappings may create parameterizations with singularities. Singularity-free ...
Comments