Raw Ore Selection By Artificial Vision (cc61426b-f93b-4b6c-89d5-720512c7133c)

Certain deposits of incoherent materials which are near the surface and exploitable by open-pit mining may be characterized in real time before they are mined through an analysis of ground-surface imagery. If the slice to be stripped is not overly thick, in fact, surface texture and color properties may be extrapolated to its entire thickness. Image analysis techniques to process ground surface images acquired in situ(or in the laboratory shortly after their acquisition) which yield pattern vectors representative of RGB color component distributions and HSB texture parameters have been developed. The techniques were applied to a mineral sandy ore deposit containing three different lithotypes. Geostatistical analyses showed that the data used to characterize the lithotypes were reliable. The correct recognition of the lithotypes was carried out using a multi-barycenter classification algorithm. Such in situ image-analysis procedures open the way to the proper selection of the ore to be mined, or the proper way for run of mine (r.o.m).processing, or the appropriate blend to be processed before or at the same time as the mining process itself is enacted.