An Automated Deep Segmentation and Spatial-Statistics Approach for Post-Blast Rock Fragmentation Assessment
This work addresses the need for rapid, automated blast-effect assessment in mining and construction, though it is incremental as it builds on existing segmentation models and spatial analysis techniques.
The paper tackles the problem of assessing rock fragmentation after blasting by introducing an automated pipeline that uses a fine-tuned YOLO12l-seg model for real-time instance segmentation, achieving Box mAP@0.5 of 0.769 and Mask mAP@0.5 of 0.800 at 15 FPS, and extracts spatial statistics from the masks to analyze fragmentation patterns.
We introduce an end-to-end pipeline that leverages a fine-tuned YOLO12l-seg model -- trained on over 500 annotated post-blast images -- to deliver real-time instance segmentation (Box mAP@0.5 ~ 0.769, Mask mAP@0.5 ~ 0.800 at ~ 15 FPS). High-fidelity masks are converted into normalized 3D coordinates, from which we extract multi-metric spatial descriptors: principal component directions, kernel density hotspots, size-depth regression, and Delaunay edge statistics. We present four representative examples to illustrate key fragmentation patterns. Experimental results confirm the framework's accuracy, robustness to small-object crowding, and feasibility for rapid, automated blast-effect assessment in field conditions.