Characterizing segregation in blast rock piles a deep-learning approach leveraging aerial image analysis

TL;DR

This paper presents a deep learning-based image analysis method using drone imagery and an enhanced Unet model to accurately characterize particle size segregation in quarry rock piles, revealing vertical segregation patterns.

Contribution

It introduces a scalable, drone-based image analysis approach with an improved Unet model for detailed rock fragment size distribution assessment.

Findings

Pronounced vertical segregation patterns identified

Finer particles in upper slopes, coarser in lower slopes

Method offers accurate, scalable size distribution analysis

Abstract

Blasted rock material serves a critical role in various engineering applications, yet the phenomenon of segregation-where particle sizes vary significantly along the gradient of a quarry pile-presents challenges for optimizing quarry material storage and handling. This study introduces an advanced image analysis methodology to characterize such segregation of rock fragments. The accurate delineation of detailed rock fragment size distributions was achieved through the analysis of drone-captured imagery, coupled with the application of an enhanced Unet semantic segmentation model integrated with an expansion-based post-processing technique. The quarry slope was stratified into four vertical sections, with the size distribution of each section quantified via ellipsoid shape approximations. Our results disclose pronounced vertical segregation patterns, with finer particles concentrated in the upper slope regions and coarser particles in the lower. Utilizing relative characteristic diameters, we offered insight into the degree of segregation, thereby illustrating the spatial heterogeneity in fragment size more clearly. The techniques outlined in this study deliver a scalable and accurate method for assessing fragment size distribution, with the potential to better inform resource management and operational decisions in quarry management.