11265.rar

: Salt-and-pepper noise and arithmetic mean filtering to mimic camera sensor interference.Through these methods, the dataset was expanded to a total of 11,265 pieces of gangue samples, providing the necessary volume for high-accuracy training. 3. Model Architecture: Improved YOLOv8

The research implemented an "improved YOLOv8" model, specifically optimized for segmentation rather than just object detection. Key hyperparameters were adjusted to better suit the morphology of coal and rock. 4. Results and Performance 11265.rar

) and real-time processing speeds, outperforming traditional YOLO architectures in underground mining environments. 1. Introduction : Salt-and-pepper noise and arithmetic mean filtering to

The following is a structured paper based on the methodologies and results associated with that dataset. Key hyperparameters were adjusted to better suit the

A critical challenge in training neural networks for mining is the lack of diverse data. In the primary study, an initial set of 1,980 original images was collected. To improve generalization and prevent overfitting, various were applied: Geometric Transformations : Image rotation (randomly ±90plus or minus 90 Photometric Adjustments : Random luminance changes (up to ) to simulate varying lighting underground.