Education, Science, Technology, Innovation and Life
Open Access
Sign In

Coal Gangue Identification Based on Improved YOLOv5s Algorithm

Download as PDF

DOI: 10.23977/acss.2022.060512 | Downloads: 17 | Views: 564

Author(s)

Shunan Jia 1

Affiliation(s)

1 School of Physics and Electronic Information Engineering, Henan Polytechnic University, Jiaozuo, Henan, China

Corresponding Author

Shunan Jia

ABSTRACT

For coal gangue sorting task, most of them are still in the traditional gangue sorting method, for this situation, based on the analysis and summary of previous research work, a coal For coal gangue sorting task, most of them are still in the traditional gangue sorting method, for this situation, based on the analysis and summary of previous research work, a coal gangue identification method based on improved YOLOv5s is proposed. On the basis of the original network model to make improvements in the backbone module to add non-local attention mechanism for multi-scale network prediction of gangue, improve the feature extraction ability of the model; and design adaptive anchor frame to predict gangue location information efficiently; improve the loss function of the original model to reduce the target miss detection, so as to effectively improve the accuracy of gangue identification. Finally, through experimental comparison, compared with the original network, the improved YOLOv5s model has an mAP value of 8.7%, and the detection speed has been greatly improved.

KEYWORDS

YOLOv5s, gangue, image recognition

CITE THIS PAPER

Shunan Jia, Coal Gangue Identification Based on Improved YOLOv5s Algorithm. Advances in Computer, Signals and Systems (2022) Vol. 6: 84-93. DOI: http://dx.doi.org/10.23977/acss.2022.060512.

REFERENCES

[1] Zhang T. Multivariate industrial order forecasting based on feature expansion and LSTM model. System Simulation Technology, 2021, 17 (4): 221-225.
[2] Cao, Xian-Gang, Xue, Zhen-Ye. Migration learning based GoogLenet coal gangue image recognition. Software Guide, 2019,18 (12): 183-186.
[3] Ma Jun, Yu Zhongming, Shu Shihai, et al. Environmental hazards of coal gangue in mining areas and management measures. Coal Engineering, 2015, 47 (10): 70-73.
[4] Zhang Zhenhong. Development status and application prospect of dry coal beneficiation technology in China. Coal Processing Technology, 2019 (01): 43-47+52.
[5] Yu D., Zou S. W., Qin C. Research on the application of image grayscale information in automatic coal gangue sorting. Industrial and mining automation, 2012, 38 (02): 36-39.
[6] YAN B, FAN P, LEI X Y, et al. A real-time apple targets detection method for picking robot based on improved YOLOv5. Remote Sensing, 2021, 13 (9): 1619.
[7] Liao Yenna, Li Wan. Bridge Crack Detection Method Based on Convolutional Neural Network. Computer Engineering and Design, 2021, 42 (08): 2366-2372.
[8] YAN B, FAN P, LEI X Y, et al. A real-time apple targets detection method for picking robot based on improved YOLOv5. Remote Sensing, 2021, 13 (9): 1619.
[9] LIN Sen, LIU Meiyi, TAO Zhiyong. Detection of underwater treasures using attention mechanism and improved YOLOv5. Transactions of the CSAE, 2021, 37 (18): 307-14.
[10] YU J, LUO S.Detection method of illegal building based on YOLOv5. Computer Engineering and Applications, 2021, 57 (20): 236-244.
[11] ZHAO Rui, LIU Hui, LIU Peilin, et al. Research on safety helmet detection algorithm based on improved YOLOv5s. Journal of Beijing University of Aeronautics and Astronautics, 2021, 1-16.

Downloads: 19344
Visits: 294516

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.