Software implementation of the algorithm for automatic detection of lineaments and their properties on open-pit dumps

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

The paper presents an algorithm and a description of its software implementation for detecting lineaments (ground erosions or cracks) in aerial photography images of open-pits. The proposed approach is based on the apparatus of convolutional neural networks based on the semantic classification of binarized images of objects (lineaments), as well as graph theory for determining the geometric location of linearized objects, followed by determining their lengths and areas. Three-channel RGB images of high-resolution aerial photography (pixel 10x10 cm) were used as initial data. The software unit of the model is logically divided into three layers: pre-processing, detection and post-processing. The first level includes preprocessing of input data to form a training sample based on successive transformations of an RGB image into a binary one using the OpenCV library. A neural network of the U-Net type, which includes blocks of the convolutional (Encoder) and scanning parts (Decoder), represents the second level of the information model. At this level, automatic lineament detection (washouts) is implemented. The third level of the model is responsible for calculating the areas and lengths of lineaments. The result of the work of the convolutional neural network is transferred to the input. Lineament area is calculated by summing the total number of points multiplied by the pixel size. The length of the lineaments is computed by linearizing a plane object into a line segmental object with nodal points and then calculating the lengths between them, also relying on the resolution of the original image. The software module can work with input images, with their subsequent resulting merging to the size of the original image.

Full Text

Restricted Access

About the authors

S. E. Popov

Federal Research Center for Information and Computational Technologies

Author for correspondence.
Email: popov@ict.nsc.ru
ORCID iD: 0000-0001-9495-6561
Russian Federation, 6, Academician M.A. Lavrentiev av., Novosibirsk, 630090

V. P. Potapov

Federal Research Center for Information and Computational Technologies

Email: vadimptpv@gmail.com
ORCID iD: 0000-0002-1530-5902
Russian Federation, 6, Academician M.A. Lavrentiev av., Novosibirsk, 630090

R. Y. Zamaraev

Federal Research Center for Information and Computational Technologies

Email: zamaraev@ict.nsc.ru
ORCID iD: 0000-0003-4822-4794
Russian Federation, 6, Academician M.A. Lavrentiev av., Novosibirsk, 630090

References

  1. Potapov V.P., Oparin V.N., Mikov L.S., Popov S.E. Information Technologies in Problems of Nonlinear Geomechanics. Part I: Earth Remote Sensing Data and Lineament Analysis of Deformation Wave Processes. Journal of Mining Science, 2022, vol. 58, pp. 486–50.
  2. Hao X., Du W., Zhao Y., Sun Z., Zhang Q., Wang S., Qiao H. Dynamic tensile behaviour and crack propagation of coal under coupled static-dynamic loading. Int. J. Min. Sci. Technol, 2020, vol. 30, pp. 659–668.
  3. Krull B., Patrick J., Har, K., White S., Sottos N. Automatic optical crack tracking for double cantilever beam specimens. Exp. Tech., 2016, vol. 40, pp. 937–945.
  4. Sun H., Liu Q., Fang L. Research on fatigue crack growth detection of M (T) specimen based on image processing technology. J. Fail. Anal. Prev., 2018, vol. 18, pp. 1010–1016.
  5. Zhang W., Zhang Z., Qi D., Liu Y. Automatic crack detection and classification method for subway tunnel safety monitoring. Sensors, 2014, vol. 14, pp. 19307–19328.
  6. Kong X., Li J. Vision-based fatigue crack detection of steel structures using video feature tracking. Comput.-Aided Civ. Inf., 2018, vol. 33, pp. 783–799.
  7. Kong X., Li J. Non-contact fatigue crack detection in civil infrastructure through image overlapping and crack breathing sensing. Automat. Constr., 2019, vol. 99, pp. 125–139.
  8. Li D., Huang P., Chen Z., Yao G., Guo X., Zheng X., Yang Y. Experimental study on fracture and fatigue crack propagation processes in concrete based on DIC technology. Eng. Fract. Mech., 2020, vol. 235, pp. 107–166.
  9. Vanlanduit S., Vanherzeele, J., Longo, R. Guillaume P. A digital image correlation method for fatigue test experiments. Opt. Laser. Eng., 2009, vol. 47, pp. 371–378.
  10. Valença J., Dias-da-Costa D., Júlio E., Araújo H., Costa H. Automatic crack monitoring using photogrammetry and image processing. Measurement, 2013, vol. 46, pp. 433–441.
  11. Yeum C.M., Dyke S.J. Vision-based automated crack detection for bridge inspection. Comput.-Aided Civ. Inf., 2015, vol. 30, pp. 759–770.
  12. Dong L., Tang Z., Li X., Chen Y., Xue J. Discrimination of mining microseismic events and blasts using convolutional neural networks and original waveform. J. Cent. S. Univ., 2020, vol. 27, pp. 3078–3089.
  13. Yu Y., Wang C., Gu X., Li J. A novel deep learning-based method for damage identification of smart building structures. Struct. Health Monit., 2019, vol. 18, pp. 143–163.
  14. Su C., Wang W. Concrete Cracks Detection Using Convolutional Neural Network Based on Transfer Learning. Mathematical Problems in Engineering, 2020, Article ID 7240129, 10 p. doi: 10.1155/2020/7240129
  15. Pauly L., Hogg D., Fuentes R., Peel H. Deeper networks for pavement crack detection. In Proc. 34th ISARC, 2017, pp. 479–485.
  16. Maeda H., Sekimoto Y., Seto T., Kashiyama T., Omata Y. Road damage detection using deep neural networks with images captured through a smartphone. arXiv preprint, 2018, pp. 1–14. URL: https://arxiv.org/abs/ 1801.09454
  17. Xu H., Su X., Wang Y., Cai H., Cui K., Chen X. Automatic bridge crack detection using a convolutional neural network. Applied Sciences, 2019, vol. 9, no. 14, p. 2867. doi: 10.3390/app9142867
  18. Yuan Y., Ge Z., Su X., Guo X., Suo T., Liu Y., Yu Q. Crack Length Measurement Using Convolutional Neural Networks and Image Processing. Sensors, 2021, vol. 21, p. 5894.
  19. Gehri N., Mata-Falcón J., Kaufmann W. Automated crack detection and measurement based on digital image correlation. Construction and Building Materials, 2020, vol. 256. p. 119383. doi: 10.1016/j.conbuildmat.2020.119383
  20. Shelhamer E., Long J., Darrell T. Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, vol. 39, no. 4, pp. 640–651. doi: 10.1109/TPAMI.2016.2572683
  21. Chen L., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proc. European conference on computer vision (ECCV). 2018. pp. 801-818. URL: https://arxiv.org/abs/1802.02611

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. The scheme of converting an RGB image into a binary image. The names of the components correspond to the OpenCV API software library (https://docs.opencv.org/4.x /) and scikit-image (https://scikit-image.org /). The vertical number is the size of the image, and the horizontal number is the number of channels.

Download (223KB)
Indexing metadata
3. Fig. 3. A fragment of the code for preprocessing images of the training sample.

Download (367KB)
Indexing metadata
4. Fig. 2. The scheme of training sample preparation based on the transformation scheme (Fig. 1).

Download (386KB)
Indexing metadata
5. Fig. 4. Neural network configuration

Download (431KB)
Indexing metadata
6. Fig. 5. Software implementation of the Encoder and Decoder blocks. The variables “c1-c9” denote the convolution modules.

Download (646KB)
Indexing metadata
7. Fig. 6. A fragment of the compilation code and the start of the network learning process.

Download (146KB)
Indexing metadata
8. Fig. 7. Code snippet for starting the crack detection procedure.

Download (129KB)
Indexing metadata
9. Fig. 8. Diagram of the crack detection process for the test subimage.

Download (327KB)
Indexing metadata
10. Fig. 9. A fragment of the program code for obtaining a set of pixel coordinates for each crack object.

Download (737KB)
Indexing metadata
11. Fig. 10. Example of a graph object. The vertices corresponding to the edge pixels are indicated in black, and the arrows indicate the path of traversing the graph between two edge points. The dashed arrows are the largest path in terms of the number of pixels in each iteration. The edges of the graph have weights equal to 1.

Download (96KB)
Indexing metadata
12. Fig. 11. The results of calculating the lengths (left) and areas (right) of cracks.

Download (1MB)
Indexing metadata
13. Fig. 12. DFS is a diagram of the data flows of the crack detection process and the calculation of their lengths and areas.

Download (499KB)
Indexing metadata

Copyright (c) 2024 Russian Academy of Sciences

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies