Convolutional-neural-network-based sewer defect detection in videos captured by CCTV

doi:10.13474/j.cnki.11-2246.2019.0361

Abstract

Abstract: Sewer network is related to the public safety and environmental protection. The defect detection of sewer has received more attention. CCTV is a technology widely used in the sewer defect detection. Motivated by the success of the CNN (Convolutional Neural Network) in the image recognition, this paper proposes a CNN-based sewer defect detection to improve the intelligence and automation of the CCTV technology. Experimental results show that the proposed method is effective and the accuracy, recall and run-time meet the requirements of the sewer defect detection. Moreover, this method has been widely used in the city of Shenzhen.

Key words: Convolutional neural network, Sewer detection, CCTV endoscopic detection, automation, intelligence

CLC Number:

P258

Lü Bing, LIU Yuxian, YE Shaoze, YAN Zhen. Convolutional-neural-network-based sewer defect detection in videos captured by CCTV[J]. Bulletin of Surveying and Mapping, 2019, 0(11): 103-108.

References

[1] SU T, YANG M. Application of morphological segmentation to leaking defect detection in sewer pipelines[J]. Sensors, 2014(14):8686-8704.
[2] HAWARI A, ALAMIN M, ALKADOUR F, et al. Automated defect detection tool for closed circuit television (cctv) inspected sewer pipelines[J]. Automation in Construction, 2018(89):99-109.
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Imagenet classification with deep convolutional neural networks[C]//Annual Conference on Neural Information Processing Systems. Lake Tahoe:[s.n.], 2012:1097-1105.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Washington, D C:IEEE, 2014:580-587.
[5] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[6] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//IEEE International Conference on Computer Vision. Santiago:IEEE, 2015:4489-4497.
[7] LECUN Y, BENGIO Y. Convolutional networks for images, speech, and time-series[C]//The Handbook of Brain Theory and Neural Networks. Cambrideg:The MIT Press, 1995.
[8] FUKUSHIMA K. Neocognitron:a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4):193-202.
[9] WERBOS P J. Beyond regression:new tools for prediction and analysis in the behavioral sciences[D]. Harvard:Harvard University, 1975.
[10] FERGUSON T. An inconsistent maximum likelihood estimate[J]. Journal of the American Statistical Association, 1982, 77(380):831-834.
[11] KINGMA D, BA J. Adam:a method for stochastic optimization[C]//International Conference on Learning Representation. San Diego:[s.n.], 2015.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representation. Banff, Canada:[s.n.], 2014.
[13] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//International Conference on Artificial Intelligence and Statistics. Fort Lauderdale:[s.n.], 2011:315-323.
[14] DENG J, DONG W, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[C]//IEEE Conference on Computer Vision and Pattern Recognition. Miami:IEEE, 2009:248-255.
[15] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM, 2014.