Skip to main content
Erschienen in: Multimedia Systems 4/2023

24.05.2023 | Regular Paper

A fast recognition method for coal gangue image processing

verfasst von: Dailiang Wei, Juanli Li, Bo Li, Xin Wang, Siyuan Chen, Xuewen Wang, Luyao Wang

Erschienen in: Multimedia Systems | Ausgabe 4/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This paper proposes a modified YOLOv4 model, named GYOLO, for coal gangue recognition with the aim of reducing model parameters, improving calculation speed, and reducing equipment requirements. To achieve this, the paper optimizes the feature extraction network structure by using linear operation instead of traditional convolution to obtain redundant feature maps, thus reducing the number of parameters by 29.7%. A feature fusion network structure is also reconstructed to strengthen the model’s use of feature information, further explore the dependence of each channel feature, and make better use of feature information. The ablation experiment is designed to verify the effect of each improvement. The image is blurred to improve the difficulty of target detection and test the robustness of the GYOLO model. The generative adversarial network is trained with a small amount of coal gangue data, and then a large amount of virtual data is obtained by using the generative adversarial neural network. The GYOLO model is trained by transfer learning, which reduces the dependence of the model on real data. The GYOLO algorithm is compared with a variety of excellent target detection algorithms to analyze the performance of the algorithm. It is verified that the accuracy of the proposed method is 97.08%, which is 2.3% higher than that of the original model, the amount of parameters is reduced by 19.6%, and the amount of data required is reduced by 57.3%. The balance between data volume, parameter quantity and model performance is further realized.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Alfarzaeai, M.S., Niu, Q., Zhao, J., Eshaq, R.: Coal/gangue recognition using convolutional neural networks and thermal images. IEEE Access 8, 76780–76789 (2020)CrossRef Alfarzaeai, M.S., Niu, Q., Zhao, J., Eshaq, R.: Coal/gangue recognition using convolutional neural networks and thermal images. IEEE Access 8, 76780–76789 (2020)CrossRef
2.
Zurück zum Zitat Bai, F.Y., Fan, M.Q., Yang, H.L., Dong, L.P.: Fast recognition using convolutional neural network for the coal particle density range based on images captured under multiple light sources. Int. J. Min. Sci. Technol. 31(6), 1053–1061 (2021)CrossRef Bai, F.Y., Fan, M.Q., Yang, H.L., Dong, L.P.: Fast recognition using convolutional neural network for the coal particle density range based on images captured under multiple light sources. Int. J. Min. Sci. Technol. 31(6), 1053–1061 (2021)CrossRef
3.
Zurück zum Zitat Dou, D., Wu, W., YANG, J., Zhang, Y.: Classification of coal and gangue under multiple surface conditions via machine vision and relief-SVM. Powder Technol. 356, 1024–1028 (2019)CrossRef Dou, D., Wu, W., YANG, J., Zhang, Y.: Classification of coal and gangue under multiple surface conditions via machine vision and relief-SVM. Powder Technol. 356, 1024–1028 (2019)CrossRef
4.
Zurück zum Zitat Dwivedi, N., et al.: Employing data generation for visual weapon identification using Convolutional neural networks. Multimedia Syst. 28(1), 347 (2022)CrossRef Dwivedi, N., et al.: Employing data generation for visual weapon identification using Convolutional neural networks. Multimedia Syst. 28(1), 347 (2022)CrossRef
5.
Zurück zum Zitat Gilanie, G., et al.: RiceNet: convolutional neural networks-based model to classify Pakistani grown rice seed types. Multimedia Syst. 27(5), 867 (2021)CrossRef Gilanie, G., et al.: RiceNet: convolutional neural networks-based model to classify Pakistani grown rice seed types. Multimedia Syst. 27(5), 867 (2021)CrossRef
6.
Zurück zum Zitat Hu, Y.C., et al.: Video-based driver action recognition via hybrid spatial-temporal deep learning framework. Multimedia Syst. 27(3), 483 (2021)CrossRef Hu, Y.C., et al.: Video-based driver action recognition via hybrid spatial-temporal deep learning framework. Multimedia Syst. 27(3), 483 (2021)CrossRef
7.
Zurück zum Zitat Hu, F., Zhou, M.R., Yan, P.C., Bian, K.: Multispectral imaging: a new solution for identification of coal and gangue. IEEE Access 7, 169697–169704 (2019) CrossRef Hu, F., Zhou, M.R., Yan, P.C., Bian, K.: Multispectral imaging: a new solution for identification of coal and gangue. IEEE Access 7, 169697–169704 (2019) CrossRef
8.
Zurück zum Zitat Han, K., Wang, Y., Tian, Q., Guo, J.Y., Xu, C.J.: GhostNet: more features from cheap operations, pp. 1577–1586. IEEE Computer Society, DC USA (2019) Han, K., Wang, Y., Tian, Q., Guo, J.Y., Xu, C.J.: GhostNet: more features from cheap operations, pp. 1577–1586. IEEE Computer Society, DC USA (2019)
9.
Zurück zum Zitat Hu, F., Bian, K.: Accurate identification strategy of coal and gangue using infrared imaging technology combined with convolutional neural network. IEEE Access 10, 8758–8766 (2022)CrossRef Hu, F., Bian, K.: Accurate identification strategy of coal and gangue using infrared imaging technology combined with convolutional neural network. IEEE Access 10, 8758–8766 (2022)CrossRef
10.
Zurück zum Zitat Eshaq, R., Hu, E.Y., Qaid, H., Zhang, Y., Liu, T.G.: Using deep convolutional neural networks and infrared thermography to identify coal quality and gangue. IEEE Access 9, 147315–147327 (2021)CrossRef Eshaq, R., Hu, E.Y., Qaid, H., Zhang, Y., Liu, T.G.: Using deep convolutional neural networks and infrared thermography to identify coal quality and gangue. IEEE Access 9, 147315–147327 (2021)CrossRef
11.
Zurück zum Zitat Li, D., Wu, D., Xu, F., Lai, J., Shao, L.: Literature overview of Chinese research in the field of better coal utilization. J. Clean. Prod. 185, 959–980 (2018)CrossRef Li, D., Wu, D., Xu, F., Lai, J., Shao, L.: Literature overview of Chinese research in the field of better coal utilization. J. Clean. Prod. 185, 959–980 (2018)CrossRef
12.
Zurück zum Zitat Lei, H., Wang, S., Guo, Y.C., Cheng, G.: Multi-scale coal and gangue dual-energy X-ray image concave point detection and segmentation algorithm. Measurement 196, 111041 (2022)CrossRef Lei, H., Wang, S., Guo, Y.C., Cheng, G.: Multi-scale coal and gangue dual-energy X-ray image concave point detection and segmentation algorithm. Measurement 196, 111041 (2022)CrossRef
13.
Zurück zum Zitat Li, D., Zhang, Z.X., Xu, Z., Xu, L., Meng, G.Y.: An image-based hierarchical deep learning framework for coal and gangue detection. IEEE Access 7, 184686–184699 (2019)CrossRef Li, D., Zhang, Z.X., Xu, Z., Xu, L., Meng, G.Y.: An image-based hierarchical deep learning framework for coal and gangue detection. IEEE Access 7, 184686–184699 (2019)CrossRef
14.
Zurück zum Zitat Li, D., Wang, G., Zhang, Y., Wang, S.: Coal gangue detection and recognition algorithm based on deformable convolution YOLOv3. IET Image Proc. 16(1), 134–144 (2022)CrossRef Li, D., Wang, G., Zhang, Y., Wang, S.: Coal gangue detection and recognition algorithm based on deformable convolution YOLOv3. IET Image Proc. 16(1), 134–144 (2022)CrossRef
15.
Zurück zum Zitat Liu, Q., Li, J.G., Li, Y.S., Gao, M.: Recognition methods for coal and coal gangue based on deep learning. IEEE Access 9, 77599–77610 (2021)CrossRef Liu, Q., Li, J.G., Li, Y.S., Gao, M.: Recognition methods for coal and coal gangue based on deep learning. IEEE Access 9, 77599–77610 (2021)CrossRef
16.
Zurück zum Zitat Muhammad, I., Akhtar, J., Sheikh, N., Munir, S.: Reverse flotation of cut-of-grade of Lakhra coal. Energy Sourc Part A Recov Utilizat Environ Ef-fects 39(20), 1999–2005 (2017) Muhammad, I., Akhtar, J., Sheikh, N., Munir, S.: Reverse flotation of cut-of-grade of Lakhra coal. Energy Sourc Part A Recov Utilizat Environ Ef-fects 39(20), 1999–2005 (2017)
18.
Zurück zum Zitat Pan, H., Shi, Y.H., Lei, X., Wang, Z., Xin, F.: Fast identification model for coal and gangue based on the improved tiny YOLOv3. J. Real-Time Image Proc. 19(3), 687–701 (2022)CrossRef Pan, H., Shi, Y.H., Lei, X., Wang, Z., Xin, F.: Fast identification model for coal and gangue based on the improved tiny YOLOv3. J. Real-Time Image Proc. 19(3), 687–701 (2022)CrossRef
19.
Zurück zum Zitat Pu, Y., Apel, D., Szmigiel, A., Chen, J.: Image recognition of coal and coal gangue using a convolutional neural network and transfer learning. Energies 12(9), 1735–1745 (2019)CrossRef Pu, Y., Apel, D., Szmigiel, A., Chen, J.: Image recognition of coal and coal gangue using a convolutional neural network and transfer learning. Energies 12(9), 1735–1745 (2019)CrossRef
20.
Zurück zum Zitat Ran, Z., Pan, Y., Liu, W.: Co-disposal of coal gangue and red mud for prevention of acid mine drainage generation from self-heating gangue dumps. Minerals 11(6) (2020) Ran, Z., Pan, Y., Liu, W.: Co-disposal of coal gangue and red mud for prevention of acid mine drainage generation from self-heating gangue dumps. Minerals 11(6) (2020)
21.
Zurück zum Zitat Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. International Conference on Learning Representations. Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. International Conference on Learning Representations.
22.
Zurück zum Zitat Wu, D., Wang, Y., Wang, M., Wei, C., Hu, G., He, X., Fu, W.: Basic characteristics of coal gangue in a small-scale mining site and risk assessment of radioactive elements for the surrounding soils. Minerals. 11(6), 647 (2021)CrossRef Wu, D., Wang, Y., Wang, M., Wei, C., Hu, G., He, X., Fu, W.: Basic characteristics of coal gangue in a small-scale mining site and risk assessment of radioactive elements for the surrounding soils. Minerals. 11(6), 647 (2021)CrossRef
23.
Zurück zum Zitat Wang, X., Wang, S., Guo, Y., Hu, K., Wang, W.: Dielectric and geometric feature extraction and recognition method of coal and gangue based on VMD-SVM. Powder Technol 7, 241–250 (2021)CrossRef Wang, X., Wang, S., Guo, Y., Hu, K., Wang, W.: Dielectric and geometric feature extraction and recognition method of coal and gangue based on VMD-SVM. Powder Technol 7, 241–250 (2021)CrossRef
24.
Zurück zum Zitat Wang, B., Huang, H., Dou, D., Qiu, Z.: Detection of coal content in gangue via image analysis and particle swarm optimization-support vector machine. Int. J. Coal Prep. Util. 42(7), 1915–1924 (2021)CrossRef Wang, B., Huang, H., Dou, D., Qiu, Z.: Detection of coal content in gangue via image analysis and particle swarm optimization-support vector machine. Int. J. Coal Prep. Util. 42(7), 1915–1924 (2021)CrossRef
27.
Zurück zum Zitat Xing, J., Zhao, Z., Wang, Y., Nie, L., Du, X.: Coal and gangue identification method based on the intensity image of lidar and DenseNet. Appl. Opt. 60(22), 6566–6572 (2021)CrossRef Xing, J., Zhao, Z., Wang, Y., Nie, L., Du, X.: Coal and gangue identification method based on the intensity image of lidar and DenseNet. Appl. Opt. 60(22), 6566–6572 (2021)CrossRef
28.
Zurück zum Zitat Xu, G., Bu, X., Mao, Y., Ni, C., Peng, Y., Xie, G.: Combined column and cell flotation process for improving clean coal quality: Laboratory-scale and industry-scale studies. Energy Sourc. Part A Recov. Utilizat. Environ-mental Eff. 42(21), 2678–2687 (2020) Xu, G., Bu, X., Mao, Y., Ni, C., Peng, Y., Xie, G.: Combined column and cell flotation process for improving clean coal quality: Laboratory-scale and industry-scale studies. Energy Sourc. Part A Recov. Utilizat. Environ-mental Eff. 42(21), 2678–2687 (2020)
29.
Zurück zum Zitat Yang, D., Li, J., Du, C., Zheng, K., Liu, S.: Particle size distribution of coal and gangue after impact-crush separation. J. Cent. South Univ. 24(6), 1252–1262 (2017)CrossRef Yang, D., Li, J., Du, C., Zheng, K., Liu, S.: Particle size distribution of coal and gangue after impact-crush separation. J. Cent. South Univ. 24(6), 1252–1262 (2017)CrossRef
30.
Zurück zum Zitat Yang, D., Li, J., Zheng, K., Du, C., Liu, S.: Impact-crush separation characteristics of coal and gangue. Int. J. Coal Prep. Util. 38(3), 127–134 (2018)CrossRef Yang, D., Li, J., Zheng, K., Du, C., Liu, S.: Impact-crush separation characteristics of coal and gangue. Int. J. Coal Prep. Util. 38(3), 127–134 (2018)CrossRef
31.
Zurück zum Zitat Zhao, Y., Wang, S., Cheng, G., He, L.: Study on coal and gangue recognition method based on the combination of X-ray transmission and diffraction principle. Energy Sourc. Part A Recov. Utilizat. Environ. Eff. 44(4), 9716–9728 (2022) Zhao, Y., Wang, S., Cheng, G., He, L.: Study on coal and gangue recognition method based on the combination of X-ray transmission and diffraction principle. Energy Sourc. Part A Recov. Utilizat. Environ. Eff. 44(4), 9716–9728 (2022)
32.
Zurück zum Zitat Zhang Y, Zhu H, Zhu J, Ou Z, Shen T, Sun J, Feng A 2021 Experimental study on separation of lumpish coal and gangue using X-ray. Energy Sources, Part A: Recovery, Utilization, and Environ-mental Effects. Zhang Y, Zhu H, Zhu J, Ou Z, Shen T, Sun J, Feng A 2021 Experimental study on separation of lumpish coal and gangue using X-ray. Energy Sources, Part A: Recovery, Utilization, and Environ-mental Effects.
33.
Zurück zum Zitat Zhang, N., Liu, C.: Radiation characteristics of natural gamma-ray from coal and gangue for recognition in top coal caving. Sci. Rep. 8(1), 190 (2018)MathSciNetCrossRef Zhang, N., Liu, C.: Radiation characteristics of natural gamma-ray from coal and gangue for recognition in top coal caving. Sci. Rep. 8(1), 190 (2018)MathSciNetCrossRef
34.
Zurück zum Zitat Zhang, Z., Yang, J.: Online analysis of coal ash content on a moving conveyor belt by machine vision. J. Coal Prepara. Utilizat. 37(2), 100–111 (2022)MathSciNetCrossRef Zhang, Z., Yang, J.: Online analysis of coal ash content on a moving conveyor belt by machine vision. J. Coal Prepara. Utilizat. 37(2), 100–111 (2022)MathSciNetCrossRef
35.
Zurück zum Zitat Zhang, Y., Wang, J., Yu, Z., Zhao, S., Bei, G.: Research on intelligent detection of coal gangue based on deep learning. Measurement 198, 111415 (2022)CrossRef Zhang, Y., Wang, J., Yu, Z., Zhao, S., Bei, G.: Research on intelligent detection of coal gangue based on deep learning. Measurement 198, 111415 (2022)CrossRef
Metadaten
Titel
A fast recognition method for coal gangue image processing
verfasst von
Dailiang Wei
Juanli Li
Bo Li
Xin Wang
Siyuan Chen
Xuewen Wang
Luyao Wang
Publikationsdatum
24.05.2023
Verlag
Springer Berlin Heidelberg
Erschienen in
Multimedia Systems / Ausgabe 4/2023
Print ISSN: 0942-4962
Elektronische ISSN: 1432-1882
DOI
https://doi.org/10.1007/s00530-023-01109-7

Weitere Artikel der Ausgabe 4/2023

Multimedia Systems 4/2023 Zur Ausgabe