YOLOv8-Coal: a coal-rock image recognition method based on improved YOLOv8

被引：0
作者：
Wang, Wenyu [1 ]
Zhao, Yanqin [1 ]
Xue, Zhi [2 ]
机构：
[1] School of Computer and Information Engineering, Heilongjiang University of Science and Technology, Heilongjiang, Harbin
[2] College of Science, Heilongjiang University of Science and Technology, Heilongjiang, Harbin
来源：
PeerJ Computer Science | 2024年 / 10卷
关键词：
Attention mechanisms; Coal-rock image recognition; Deep learning; Object detection; YOLOv8;
D O I：
10.7717/PEERJ-CS.2313
中图分类号：
学科分类号：
摘要：
To address issues such as misdetection and omission due to low light, image defocus, and worker occlusion in coal-rock image recognition, a new method called YOLOv8- Coal, based on YOLOv8, is introduced to enhance recognition accuracy and processing speed. The Deformable Convolution Network version 3 enhances object feature extraction by adjusting sampling positions with offsets and aligning them closely with the object’s shape. The Polarized Self-Attention module in the feature fusion network emphasizes crucial features and suppresses unnecessary information to minimize irrelevant factors. Additionally, the lightweight C2fGhost module combines the strengths of GhostNet and the C2f module, further decreasing model parameters and computational load. The empirical findings indicate that YOLOv8- Coal has achieved substantial enhancements in all metrics on the coal rock image dataset. More precisely, the values for AP50, AP50:95, and AR50:95 were improved to 77.7%, 62.8%, and 75.0% respectively. In addition, optimal localization recall precision (oLRP) were decreased to 45.6%. In addition, the model parameters were decreased to 2.59M and the FLOPs were reduced to 6.9G. Finally, the size of the model weight file is a mere 5.2 MB. The enhanced algorithm’s advantage is further demonstrated when compared to other commonly used algorithms. © 2024 Wang et al.
引用
收藏
相关论文
共 35 条
  • [1] Cao Z, Li Z, Fang L, Li J, Yang H, Hui D., Research on coal and gangue segmentation based on MFCCM-Mask R-CNN, Energy Science & Engineering, 12, 7, pp. 2958-2973, (2024)
  • [2] Dai S, Finkelman RB., Coal as a promising source of critical elements: progress and future prospects, International Journal of Coal Geology, 186, 5, pp. 155-164, (2018)
  • [3] Faghani S, Codipilly DC, Vogelsang D, Moassefi M, Rouzrokh P, Khosravi B, Agarwal S, Dhaliwal L, Katzka DA, Hagen C, Lewis J, Leggett CL, Erickson BJ, Iyer PG., Development of a deep learning model for the histologic diagnosis of dysplasia in Barrett’s esophagus, Gastrointestinal Endoscopy, 96, 6, pp. 918-925, (2022)
  • [4] Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C., GhostNet: more features from cheap operations, (2020)
  • [5] He K, Gkioxari G, Dollar P, Girshick R., Mask R-CNN, (2018)
  • [6] Hua T, Xing C, Zhao L., Recognition of coal rock and positioning measurement of coal seam based on Faster R-CNN, Mining & Processing Equipment, 47, pp. 4-9, (2019)
  • [7] Huiling G, Xin L., Coal-rock interface recognition method based on image recognition, Nature Environment and Pollution Technology, 18, 5, pp. 1627-1633, (2019)
  • [8] Humayun MF, Bhatti FA, Khurshid K., iVision MRSSD: a comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applicationsiVision MRSSD, Data in Brief, 50, 5, (2023)
  • [9] Li D, Wang G, Zhang Y, Wang S., Coal gangue detection and recognition algorithm based on deformable convolution YOLOv3, IET Image Processing, 16, 1, pp. 134-144, (2022)
  • [10] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC., SSD: single shot multibox detector, Lecture Notes in Computer Science, 9905, pp. 21-37, (2016)
1234