Pavement crack detection based on sparse autoencoder

被引：0
|
作者：
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing [1 ]
Jiangsu
210094, China
机构：
[1] School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu
来源：
Beijing Ligong Daxue Xuebao | / 8卷 / 800-804 and 809期
关键词：
Anisotropy; Pavement crack; Sparse autoencoder; Tensor voting;
D O I：
10.15918/j.tbit1001-0645.2015.08.007
中图分类号：
学科分类号：
摘要：
Traditional pavement crack detection system can hardly detect cracks accurately due to the complicated background noises over the pavement surface. So a novel crack detection method based on sparse autoencoder was proposed. Firstly, an anisotropy detection algorithm was adopted to select the potential crack patches. Then the features of crack patches were extracted through sparse autoencoder and then trained by softmax to classify. Finally, benefited by the tensor voting based spatial enhancement, the cracks were extracted after noises-removing. Experimental results show that the proposed method can meet the requirement of crack detection. It is superior to other traditional methods with high accuracy and robustness. ©, 2015, Beijing Institute of Technology. All right reserved.
引用
收藏
页码：800 / 804and809
相关论文
共 11 条
  • [1] Xu W., Tang Z., Lu J., Pavement crack detection based on image saliency, Journal of Image and Graphics, 18, 1, pp. 69-77, (2013)
  • [2] Kirschke K.R., Velinsky S.A., A histogram-based approach for automated pavement cracks sensing, Journal of Transportation Engineering, 118, 5, pp. 700-710, (1992)
  • [3] Gao J., Ren M., Tang Z., Automatic road detection and identification, Computer Engineering, 29, 2, pp. 149-150, (2002)
  • [4] Subirats P., Dumoulin J., Legeay V., Et al., Automation of pavement surface crack detection using the continuous wavelet transform, Proceedings of 2006 IEEE International Conference on Image Processing, pp. 3037-3040, (2006)
  • [5] Zou Q., Cao Y., Li Q.Q., Et al., CrackTree: Automatic crack detection from pavement images, Pattern Recognition Letters, 33, pp. 227-238, (2012)
  • [6] Xu G.A., Ma J.L., Liu F.F., Et al., Automatic recognition of pavement surface crack based on BP neural network, Proceedings of 2008 International Conference on Computer and Electrical Engineering, pp. 19-22, (2008)
  • [7] Wei N., Wang T., Proximal support vector machine based pavement image classification, Proceedings of the Fifth International Conference on Advanced Computational Intelligence, pp. 18-20, (2012)
  • [8] Oliveira H., Correia P.L., Automatic road crack detection and characterization, Intelligent Transportation Systems, 14, 1, pp. 155-168, (2013)
  • [9] Vincent P., Larochelle H., Bengio Y., Et al., Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th International Conference on Machine Learning, pp. 1096-1103, (2008)
  • [10] Itti L., Koch C., Niebur E., A model of saliency-based visual attention for rapid scene analysis, Pattern Analysis and Machine Intelligence, 20, 11, pp. 1254-1259, (1998)
12