Surface defect detection based on scaling cross-stage partial network

被引：0

作者：

Cao Z. ^{[1
]}

Ji W. ^{[1
,2
]}

Su X. ^{[1
]}

Zhang Y. ^{[1
]}

Wang K. ^{[1
]}

机构：

[1] School of Mechanical Engineering, Jiangnan University, Wuxi

[2] Jiangsu Provincial Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Wuxi

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2022年 / 28卷 / 08期

关键词：

convolutional neural network; cross stage partial network; deep learning; defect detection;

D O I：

10.13196/j.cims.2022.08.011

中图分类号：

学科分类号：

摘要：

In industry, equipments for surface defect detection currently face performance bottlenecks due to limited computational resources of hardware. Orienting the trade-off between high efficiency and high accuracy, a surface-defect-detection model based on scaling Cross Stage Partial Network (CSPNet) was established. A Y0L0v5s-P model that be scaled up and down for networks of different sizes was established based on the scaling algorithm of cross-stage partial network and YOLOv5s model. Specially, the neck network structure was CSP-ized to improve the feature extraction capability of the model. The SoftPool downsampling method was used to optimize network structure and parameters of the Spatial Pyramid Pooling(SPP) module, and the depthwise separable convolution was introduced to make the model lightweight while avoiding accuracy loss. Experiments showed that 96. 1% mAP was obtained on DAGM 2007 surface defect data set, which improved the detection accuracy by 5% and reduced the parameter amount by 1. 7% compared with the original model. At the same time, the detection speed was 4fps when deployed on the edge device Raspberry Pi4B. © 2022 CIMS. All rights reserved.

引用

页码：2399 / 2407

页数：8

共 25 条

[1] SUN R Y., Optimization for deep learning: Theory and algorithms [E B/O L]
[2] SU Hu, ZHANG Jiabin, ZHANG Bohao, Et al., Review of research on the inspection of surface defect based on visual perception[J/OL], Computer Integrated Manufacturing Systems, (2021)
[3] ZHAO Yu, YANG Jie, LIU Miao, Et al., Federated learning based intelligent edge computing technique for video surveillance[J], Journal on Communications, 41, 10, pp. 109-115, (2020)
[4] LEI Jie, GAO Xin, SONG Jie, Et al., Survey of deep neural network model compression[j], Journal of Software, 29, 2, pp. 251-266, (2018)
[5] CHENG Y, WANG D, ZHOU P, Et al., A survey of model compression and acceleration for deep neural networks
[6] HOWARD A, SANDLER M, CH U G, Et al., Searching for MobileNetV3, Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV), (2019)
[7] WANG C Y, LIAO M H Y, WU Y H, Et al., CSPNet: A new backbone that can enhance learning capability of C N N, Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), (2020)
[8] TAN M X, PANG R M, LE Q V., EfficientDet: Scalable and efficient object detection, Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020)
[9] XIANG W, MAO H D, ATHITSOS V., ThunderNet: A turbo unified network for real-time semantic segmentation, Proceedings of 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), (2019)
[10] HAN K, WANG Y H, TIAN Q, Et al., GhostNet: More features from cheap operations, Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020)

← 1 2 3 →