What question did this study set out to answer?

This research aims to improve coal gangue sorting methods using an optimized YOLOv7-tiny detection model.

February 2, 2026ProcessesOpen Access

Research and Application of Coal Gangue Detection Method Based on Improved YOLOv7-Tiny

View Full Paper

Ask AI

Bookmark

Authors

Image recognition technique demonstrates enhanced coal gangue sorting efficiency in industrial settings, indicating practical benefits.

This research aims to improve coal gangue sorting methods using an optimized YOLOv7-tiny detection model.
Introduced an ELAN-PC feature extraction module based on partial convolution and ELAN.
Proposed a GhostCSP module integrating cross-stage aggregation and Ghost bottleneck concepts.
Adopted the SIoU loss function to enhance detection accuracy.
Improved model increased mAP0.5 from 86.9% to 88.7%, a gain of 1.8%.
Reduced FLOPs from 13.2 G to 9.2 G, a decrease of 30%.
Cut parameters from 6.0 M to 4.3 M, a reduction of 28%.
Achieved a coal gangue sorting rate of 82.2% with a misclassification rate of 8.1%.

Hao et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark