An Automated Deep Segmentation and Spatial-Statistics Approach for Post-Blast Rock Fragmentation Assessment

TL;DR

This paper presents an automated, real-time deep learning pipeline for post-blast rock fragmentation assessment, combining instance segmentation with spatial analysis to improve accuracy and speed in field conditions.

Contribution

It introduces a novel end-to-end system integrating YOLO-based segmentation with spatial-statistics for detailed fragmentation analysis.

Findings

High segmentation accuracy (Box mAP@0.5 ~ 0.769, Mask mAP@0.5 ~ 0.800)

Robust performance in crowded small-object scenarios

Feasible for rapid, automated field assessment

Abstract

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.