Intelligent identification system of drainage pipelines defects based on deep learning model

doi:10.13474/j.cnki.11-2246.2021.322

Abstract

Abstract: The health condition of the drainage pipeline directly affects the drainage effect of the whole city. In order to find the hidden danger of the drainage pipeline, it is necessary to detect the internal defects of the pipeline in time. CCTV detection technology is currently the most common pipeline defect method, but there are some problems such as low automation degree, low work efficiency and heavy reliance on manual experience. To solve these problems, this paper combines the deep learning technology with the detection technology of drainage pipeline, and put forward an intelligent identification technology of drainage pipelines defects based on deep learning model. Meanwhile, the intelligent identification of pipeline defects and pipeline detection workflow are closely combined to realize the rapid and automatic generation of drainage pipeline detection report, thus greatly improving the detection efficiency of drainage pipeline defects.

Key words: drainage pipelines defect, deep learning model, CCTV detection, convolutional neural network, intelligent identification system

CLC Number:

P208

WANG Dacheng, TAN Junhui, PENG Shugang, ZHONG Zhensheng, CHEN Guoqiang, LI Guoqiao. Intelligent identification system of drainage pipelines defects based on deep learning model[J]. Bulletin of Surveying and Mapping, 2021, 0(10): 141-145.

References

[1] SU T C, YANG M D. Application of morphological segmenta-tion to leaking defect detection in sewer pipelines[J]. Sensors, 2014, 14(5):8686-8704.
[2] HAWARI A, ALAMIN M, ALKADOUR F, et al. Auto-mated defect detection tool for closed circuit television (CCTV) inspected sewer pipelines[J]. Automation in Construction, 2018, 89:99-109.
[3] 孙文雅, 李天剑, 黄民, 等.基于图像处理的管道裂缝检测[J]. 制造业自动化, 2012, 34(1):36-39.
[4] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[5] 孙志军, 薛磊, 许阳明, 等.深度学习研究综述[J]. 计算机应用研究, 2012, 29(8):2806-2810.
[6] KRIZHENSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communication of the ACM, 2017, 60(6):84-90.
[7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus:IEEE, 2014:580-587.
[8] SHELHAMER E, LONG J, DARRELL T. Fully convolu-tional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[9] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3d convolutional networks[C]//Proceedings of 2015 IEEE international conference on computer vision. Santiago, Chile:IEEE, 2015:4489-4497.
[10] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//European Conference on Computer Vision. Cham:Springer, 2014:818-833.
[11] XU Y, CHEN Z, XIE Z, et al. Quality assessment of building footprint data using a deep autoencoder network[J]. International Journal of Geographical Information Science, 2017, 31(10):1-23.
[12] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Santiago:IEEE, 2015:1-9.
[13] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE, 2016:770-778.
[14] ZHANG L, ZHANG L, Bo D. Deep learning for remote sensing data:a technical tutorial on the state of the art[J]. IEEE Geoscience & Remote Sensing Magazine, 2016, 4(2):22-40.
[15] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[J]. ICML'15, 2015, 37:448-456.
[16] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th international conference on artificial intelligence and statistics.[S.l.]:Journal of Machine Learning Research, 2011:315-323.
[17] ZHOU L, ZHANG C, MING W. D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake City:[s.n.], 2018:192-1924.
[18] ZHANG Z, LIU Q, WANG Y. Road extraction by deep residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 99:1-5.
[19] GOODMAN J.Classes for fast maximum entropy training[C]//Proceedings of 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing.[S.l.]:IEEE, 2001:561-564.