Timely and accurately capturing the tiny cracks in the shaft lining is of great significance for shaft safety. Lightweight detection models are the key to realizing the automatic detection of shaft lining cracks. Departing from existing traditional methods that focus on extracting deep semantic information， the application of geometric structure information represented by shallow features should be paid attention to and a lightweight detection model E-YOLOv5s for shaft lining cracks is proposed. Firstly， the lightweight convolution module， ECAConv， is designed， which integrates traditional convolution， depth-separable convolution， and an attention mechanism called ECA. Then， thefeature extraction capabilities are further enhanced by incorporating skip connections to construct the feature comprehensive extraction unit， E-C3. Thereby， the backbone network ECSP-Darknet53 is obtained， which significantly reduces network parameters and enhances the ability to extract deep fracture features of cracks. Finally， the feature fusion module ECACSP is proposed and the thin neck feature fusion module E-Neck is built by using multiple groups of ECAConv and ECACSP modules. The purpose of E-Neck is to fully fuse the geometric information of small crack targets and the semantic information of crack cracking degrees while accelerating the network reasoning. Experimental results show that the detection accuracy of E-YOLOv5s on the self-made shaft lining dataset is improved by 3.3% compared to YOLOv5s while the number of model parameters and GFLOPs are reduced by 44.9% and 43.7%， respectively. E-YOLOv5s can help promote the application of automatic detection of shaft lining cracks.
上述实验充分证明了E-YOLOv5s在自制井壁裂纹数据集上的有效性.为了进一步验证E-YOLOv5s 的泛化性能，我们继续在公共数据集Aft Original Crack DataSet Second （AOCDS）［3］上进行实验.AOCDS由2 068张图像组成，仅包含裂缝等特征，每张图像的分辨率为1024×1024.由于图像数量有限，每张图像大小较大，计算资源有限，我们将每张图像裁剪为640×640.根据自制数据集中的筛选标准，在AOCDS数据集中选取严重缺陷、中等缺陷和轻度缺陷类别的200张图像进行测试.不同模型的结果如表5所示，其中以粗体为最佳指标.可以看出，我们的模型E-YOLOv5s除Precision和Recall略低于YOLOXs外，检测结果最好.E-YOLOv5s的综合指数mAP值达到87.2%，比原YOLOv5s网络提高3.1%.
YUANL ．Scientific problem and countermeasure for precision mining of coal and associated resources［J］．Journal of China Coal Society，2019，44（1）：1-9．（in Chinese）
[3]
袁亮 ．煤炭精准开采科学构想［J］．煤炭学报，2017，42（1）：1-7．
[4]
YUANL ．Scientific conception of precision coal mining［J］．Journal of China Coal Society，2017，42（1）：1-7．（in Chinese）
LIL F， MAW F， LIL，et al ．Research on detection algorithm for bridge cracks based on deep learning［J］．Acta Automatica Sinica，2019，45（9）：1727-1742．（in Chinese）
PENGY N， LIUM， WANZ，et al ．A dual deep network based on the improved YOLO for fast bridge surface defect detection［J］．Acta Automatica Sinica，2022，48（4）：1018-1032．（in Chinese）
[9]
ZOUQ， ZHANGZ， LIQ Q，et al ．DeepCrack：learning hierarchical convolutional features for crack detection［J］．IEEE Transactions on Image Processing，2019，28（3）：1498-1512．
[10]
XUB Q， LIUC ．Pavement crack detection algorithm based on generative adversarial network and convolutional neural network under small samples［J］．Measurement，2022，196：111219．
[11]
KANGD， BENIPALS S， GOPALD L，et al ．Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning［J］．Automation in Construction，2020，118：103291．
[12]
HOWARDA G， ZHUM L， CHENB，et al ．MobileNets：efficient convolutional neural networks for mobile vision applications［J］．ArXiv e-Prints，2017：arXiv：1704.04861．
[13]
CHOLLETF. Xception： deep learning with DSCs［C］//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017： 1251-1258.
[14]
ZHANGX Y， ZHOUX Y， LINM X， et al. ShuffleNet： an extremely efficient convolutional neural network for mobile devices［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition．Salt Lake City，UT，USA． IEEE，2018：6848-6856．
[15]
HANK Y. WANG Q. TIAN. GhostNet： more feature from cheap operations［C］， 2022， IEEE， CVPR 2020.
ZHAOZ H， HEP， HAOZ Y. A variable-scale VS-UNet model for road crack detection［J/OL］. Journal of Hunan University （Natural Science Edition），2024： 1-10.（in Chinese）
[24]
MEIQ，GUL M， AZIMR ．Densely connected deep neural network considering connectivity of pixels for automatic crack detection［J］．Automation in Construction，2020，110：103018．
[25]
KANGD H， CHAY J ．Efficient attention-based deep encoder and decoder for automatic crack segmentation［J］．Structural Health Monitoring，2022，21（5）：2190-2205．
[26]
CHOIW， CHAY J ．SDDNet：real-time crack segmentation［J］．IEEE Transactions on Industrial Electronics，2020，67（9）： 8016-8025．
[27]
REDMONJ， DIVVALAS， GIRSHICKR，et al ．You only look once：unified，real-time object detection［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）．Las Vegas， NV， USA： IEEE， 2016： 779-788．
[28]
REDMONJ， FARHADIA ．YOLO9000：better，faster，stronger［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）．Honolulu，HI，USA． IEEE，2017： 6517-6525．
WANGQ L， WUB G， ZHUP 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）．Seattle，WA，USA： IEEE，2020： 11531-11539．
[33]
WANGC Y， MARK LIAOH Y， WUY H，et al ．CSPNet：a new backbone that can enhance learning capability of CNN［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）．Seattle，WA，USA． IEEE，2020：1571-1580．
[34]
HEK M， ZHANGX Y， RENS Q， et al. Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， NV， USA：IEEE，2016：770-778．
[35]
WANGC Y， BOCHKOVSKIYA， LIAOH Y M ．Scaled-YOLOv4： scaling cross stage partial network［C］//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）．Nashville，TN，USA： IEEE，2021：13024-13033．
[36]
GEZ， LIUS， WANGF， et al. YOLOX： exceeding YOLO series in 2021［J］.2021.
[37]
WANGC Y， BOCHKOVSKIYA， LIAOH Y M.YOLOv7： trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［C］. 2023， IEEE， CVPR Vancouver，BC， Canada： IEEE， 2023： 7464-7475.
京公网安备11010202008535号
PDF
(2389KB)
