Geometric Shape Modelling and Volume Estimation of Dry Bulk Cargo Piles using a Single Image

TL;DR

This paper introduces a novel geometric model for estimating the volume of dry bulk cargo piles from a single optical image, achieving high accuracy and providing a foundation for future integration with machine learning methods.

Contribution

The work presents a new mathematical approach for volume estimation of cargo piles using material properties and fixed height models from a single image, different from existing stereographic methods.

Findings

Achieved 95% accuracy in volume estimation from real remote sensing data.

Developed a closed-form formula for volume estimation based on geometric modeling.

Validated the approach on silica sand storage facility data.

Abstract

Volume estimation of onshore cargo piles is of economic importance for shipping and mining companies as well as public authorities for real-time planning of logistics, business intelligence, transport services by land or sea and governmental oversight. In remote sensing literature, the volume of pile is estimated by relying on the illumination property of object to construct the geometric shape from a single image, alternatively, stereographic imaging for construction of a digital elevation model from pairs of images. In a fresh perspective, we propose a novel approach for estimating volume from a single optical image in this work where we use the material property, which relates the base dimensions of the pile to its height through the critical angle of repose. In materials literature, often this is well-studied for fixed base and their \textit{in situ} volume estimation for different materials. In this work, however, we mathematically model the geometric shape of the pile through a fixed height model. This is appropriate because the unloading crane arm that forms the pile can rise only up to a certain height and generally moved in the horizontal plane during unloading of the material. After mathematically modelling the geometric shape of regular piles for fixed heights under rectilinear motion of unloader, we provide closed form formula to estimate their volume. Apart from laying the mathematical foundations, we also test it on real optical remote sensing data of an open bulk cargo storage facility for silica sand and present the results. We obtain an accuracy of $95\%$ in estimating the total bulk storage volume of the storage facility. This is a first demonstration study and will be integrated with applied machine learning approaches or current state-of-art approaches in the future for more complex scenarios for estimating dry bulk cargo pile volume.