Advances in developing vision systems for fully automated, non-invasive, rapid particle sizing in the mining and aggregates industries are presented using the example of fragmentation measurement of ore in an underground LHD unit bucket. 3D surface data (Figure 1) of the bucket contents was collected during operation and fully automated offline processing of the data was performed on 424 data sets, determining the individual fragments in the bucket and estimating their sieve size. Results are presented covering; fully automatic fragment identification, determination of non-overlapped and overlapped fragments to eliminate misclassification of overlapped fragments as smaller fragments, automatic identification of areas of fine material below the resolution of the 3D sensor, and sizing based on the measured 3D fragment profile that takes fragment overlap into consideration. The presented research allows the possibility of feedback to blasting, and automatic control of mills and crushers when applied to conveyor belt applications.