基于边缘感知深度残差网络的带钢表面缺陷检测

doi:10.3969/j.issn.0255-8297.2023.06.006

摘要/Abstract

摘要： 基于深度学习的显著目标检测方法已被用于带钢表面缺陷检测中，但仍存在模型收敛速度慢、检测结果边缘不清晰等问题。针对现有问题，本文提出了基于边缘感知深度残差网络（boundary-aware deeply residual network,BADRNet），以此进行带钢表面缺陷的显著目标检测。将边缘信息引入至缺陷检测任务中，解决了因目标尺寸多样性带来的检测结果边缘不清晰的问题；通过在边缘提取、显著特征融合部分采用具有残差结构的3个卷积层作为基本块，提高了训练效率且保持原有的检测精度不变。在公开的SD-saliency-900数据集上的实验结果表明，所提模型相比于现有模型，在6个评价指标上均取得了最优效果。BADRNet比当前最优的EDRNet在S-measure指标上提升了1.6%，同时对于缺陷区域边缘的检测效果具有明显提升。

关键词: 显著性检测, 缺陷检测, 深度学习, 残差结构, 边缘特征

Abstract: Deep learning-based salient object detection has been used in strip steel surface defects, but there are still some problems such as slow model training speed and unclear boundary of detection results. To address these issues, we proposed a boundary-aware deeply residual network (BADRNet) for salient object detection of strip steel surface defects. Boundary features are introduced into the steel surface defects to solve the problem of unclear boundary of detection results caused by varying object sizes. Three convolution layers with residual structure are used as basic blocks for boundary extraction and salient feature aggregation, improving training efficiency while maintaining original detection accuracy. Experimental results on the public strip steel benchmark dataset, SD-saliency-900, show that our model outperforms existing models in all six evaluation indicators. The proposed BADRNet improves the S-measure performance by 1.6%, and significantly enhances the detection effect on the defect area.

Key words: salient object detection, defect detection, deep learning, residual structure, boundary feature

中图分类号:

TP391

沈坤烨, 周晓飞, 费晓波, 陈雨中, 张继勇, 颜成钢. 基于边缘感知深度残差网络的带钢表面缺陷检测[J]. 应用科学学报, 2023, 41(6): 978-988.

SHEN Kunye, ZHOU Xiaofei, FEI Xiaobo, CHEN Yuzhong, ZHANG Jiyong, YAN Chenggang. Boundary-Aware Deeply Residual Network for Salient Object Detection of Strip Steel Surface Defects[J]. Journal of Applied Sciences, 2023, 41(6): 978-988.

参考文献

[1] Wang X L, Shrivastava A, Gupta A. A-fast-RCNN:hard positive generation via adversary for object detection[C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017:3039-3048.
[2] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016:640-651.
[3] Zhang Y, Gao X B, He L H, et al. Blind video quality assessment with weakly supervised learning and resampling strategy[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(8):2244-2255.
[4] Artacho B, Savakis A. UniPose:unified human pose estimation in single images and videos[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:7033-7042.
[5] Margolin R, Tal A, Zelnik-Manor L. What makes a patch distinct?[C]//2013 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2013:1139-1146.
[6] Shen X H, Wu Y. A unified approach to salient object detection via low rank matrix recovery[C]//2012 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2012:853-860.
[7] Cheng M M, Mitra N J, Huang X L, et al. Global contrast based salient region detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(3):569-582.
[8] 郁志鸣, 王朔中, 张新鹏, 等. 结合对比特性与局部清晰特性的图像显著区域检测[J]. 应用科学学报, 2010, 28(1):24-31. Yu Z M, Wang S Z, Zhang X P, et al. Image saliency detection based on contrast features and local sharpness[J]. Journal of Applied Sciences, 2010, 28(1):24-31. (in Chinese)
[9] Rahtu E, Kannala J, Salo M, et al. Segmenting salient objects from images and videos[C]//2010 European Conference on Computer Vision, 2010:366-379.
[10] Wang J D, Jiang H Z, Yuan Z J, et al. Salient object detection:a discriminative regional feature integration approach[J]. International Journal of Computer Vision, 2017, 123(2):251- 268.
[11] Mai L, Niu Y Z, Liu F. Saliency aggregation:a data-driven approach[C]//2013 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2013:1131-1138.
[12] Li G B, Yu Y Z. Visual saliency based on multiscale deep features[C]//2015 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2015:5455-5463.
[13] Chen T S, Lin L, Liu L B, et al. DISC:deep image saliency computing via progressive representation learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(6):1135-1149.
[14] Zeng Y, Zhang P P, Lin Z, et al. Towards high-resolution salient object detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2020:7233-7242.
[15] Feng M Y, Lu H C, Ding E R. Attentive feedback network for boundary-aware salient object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:1623-1632.
[16] Zhou X F, Shen K Y, Liu Z, et al. Edge-aware multiscale feature integration network for salient object detection in optical remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-15.
[17] Huang M K, Liu Z, Li G Y, et al. FANet:features adaptation network for 360 omnidirectional salient object detection[J]. IEEE Signal Processing Letters, 2020, 27:1819-1823.
[18] Fan D P, Ji G P, Sun G L, et al. Camouflaged object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:2774-2784.
[19] Song G R, Song K C, Yan Y H. EDRNet:encoder-decoder residual network for salient object detection of strip steel surface defects[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(12):9709-9719.
[20] Ronneberger O, Fischer P, Brox T. U-Net:convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2015:234-241.
[21] Wang Q L, Wu B G, Zhu P F, et al. ECA-net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:11531-11539.
[22] Zhao J X, Liu J J, Fan D P, et al. EGNet:edge guidance network for salient object detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2020:8778-8787.
[23] Qin X B, Zhang Z C, Huang C Y, et al. BASNet:boundary-aware salient object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019:7471-7481.
[24] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778.
[25] Kingma D P, Ba J. Adam:a method for stochastic optimization[DB/OL]. 2014[2021-12-07]. https://arxiv.org/abs/1412.6980.
[26] Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection[C]//2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2009:1597-1604.
[27] Perazzi F, Krähenbühl P, Pritch Y, et al. Saliency filters:contrast based filtering for salient region detection[C]//2012 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2012:733-740.
[28] Margolin R, Zelnik-Manor L, Tal A. How to evaluate foreground maps[C]//2014 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2014:248-255.
[29] Fan D P, Cheng M M, Liu Y, et al. Structure-measure:a new way to evaluate foreground maps[C]//2017 IEEE/CVF International Conference on Computer Vision (ICCV), 2017:4558- 4567.
[30] Abdou I E, Pratt W K. Quantitative design and evaluation of enhancement/thresholding edge detectors[J]. Proceedings of the IEEE, 1979, 67(5):753-763.
[31] Yuan Y C, Li C Y, Kim J, et al. Reversion correction and regularized random walk ranking for saliency detection[J]. IEEE Transactions on Image Processing, 2018, 27(3):1311-1322.
[32] Zhou L, Yang Z H, Zhou Z T, et al. Salient region detection using diffusion process on a two-layer sparse graph[J]. IEEE Transactions on Image Processing, 2017, 26(12):5882-5894.
[33] Zhu W J, Liang S, Wei Y C, et al. Saliency optimization from robust background detection[C]//2014 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2014:2814-2821.
[34] Peng H W, Li B, Ling H B, et al. Salient object detection via structured matrix decomposition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):818-832.
[35] Huang F, Qi J Q, Lu H C, et al. Salient object detection via multiple instance learning[J]. IEEE Transactions on Image Processing, 2017, 26(4):1911-1922.
[36] Zhao T, Wu X Q. Pyramid feature attention network for saliency detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019:3080- 3089.
[37] Luo Z M, Mishra A, Achkar A, et al. Non-local deep features for salient object detection[C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017:6593-6601.
[38] Hou Q B, Cheng M M, Hu X W, et al. Deeply supervised salient object detection with short connections[C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017:5300-5309.
[39] Deng Z J, Hu X W, Zhu L, et al. R3Net:recurrent residual refinement network for saliency detection[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018:684-690.
[40] Zhang L, Dai J, Lu H C, et al. A bi-directional message passing model for salient object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018:1741-1750.
[41] Liu J J, Hou Q B, Cheng M M, et al. A simple pooling-based design for real-time salient object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:3912-3921.
[42] Liu N, Han J W, Yang M H. PiCANet:learning pixel-wise contextual attention for saliency detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018:3089-3098.
[43] Wu Z, Su L, Huang Q M. Cascaded partial decoder for fast and accurate salient object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020:3902-3911.