Blast fragmentation size distribution is one of the most critical factors in evaluating the blasting results and affecting the downstream mining and processing operations in open-pit mines. Image-based methods are widely applied to address the problem but require heavy user interaction and experience. This study deployed a deep learning model Mask R-CNN to develop an automatic measurement method of blast fragmentation. The model was trained using images captured from real blasting sites in Nui Phao open-pit mine in Vietnam. The trained model reported high average precision scores (Intersection over Union, IoU = 0.5) 92% and 83% for bounding box and segmentation masks, respectively. The results lay a solid technical basis for the automated measurement of blast fragmentation in open-pit mines.
ChakrabortyAK, RainaAK, RamuluM, ChoudhuryPB, HaldarA, SahuP, BandopadhyayC.2004. Parametric study to develop guidelines for blast fragmentation improvement in jointed and massive formations. Eng Geol. 73 (1–2): 105 – 116.
3.
ChenLC, HermansA, PapandreouG, SchroffF, WangP, AdamH.2018. Masklab: Instance segmentation by refining object detection with semantic and direction features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA ; p. 4013 – 4022.
4.
CubesM.1987. A high resolution 3D surface construction algorithm. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques; July. New York (NY): Association for Computing Machinery. p. 163–169.
5.
DaiJ, HeK, LiY, RenS, SunJ.2016. Instance-sensitive fully convolutional networks. In European Conference on Computer Vision; Oct 8. Cham: Springer. p. 534–549.
EnayatollahiI, BazzaziAA, AsadiA.2014. Comparison between neural networks and multiple regression analysis to predict rock fragmentation in open-pit mines. Rock Mech Rock Eng. 47 (2): 799 – 807.
8.
EveringhamM, Van GoolL, WilliamsCK, WinnJ, ZissermanA.2010. The pascal visual object classes (voc) challenge. Int J Comput Vision. 88 (2): 303 – 338.
9.
FitzgibbonA, PiluM, FisherRB.1999. Direct least square fitting of ellipses. IEEE Trans Pattern Anal Mach Intell. 21 (5): 476 – 480.
10.
GirshickR.2015. Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile ; p. 1440 – 1448.
11.
HeK, GkioxariG, DollárP, GirshickR.2017. Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy ; p. 2961 – 2969.
12.
HeK, ZhangX, RenS, SunJ.2016. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE: Piscataway, NJ, USA, 2016 ; p. 770 – 778. doi: 10.1109/CVPR.2016.90.
13.
HunterGC, McDermottC, MilesNJ, SinghA, ScobleMJ.1990. A review of image analysis techniques for measuring blast fragmentation. Min Sci Technol. 11 (1): 19 – 36.
14.
KulatilakePH, QiongW, HudaverdiT, KuzuC.2010. Mean particle size prediction in rock blast fragmentation using neural networks. Eng Geol. 114 (3–4): 298 – 311.
15.
La RosaDM, GirdnerK, ValeryW, AbramsonS.2001. Recent applications of the SPLIT on-line image analysis system. p. 15–19.
16.
LiY, QiH, DaiJ, JiX, WeiY.2017. Fully convolutional instance-aware semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA ; p. 2359 – 2367.
17.
LinTY, DollárP, GirshickR, HeK, HariharanB, BelongieS.2017. Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA ; p. 2117 – 2125.
LongJ, ShelhamerE, DarrellT.2015. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA ; p. 3431 – 3440.
20.
MonjeziM, RezaeiM, VarjaniAY.2009. Prediction of rock fragmentation due to blasting in Gol-E-gohar iron mine using fuzzy logic. Int J Rock Mech Min Sci. 46 (8): 1273 – 1280.
21.
OnederraI, MardonesF, ScherpenisseC.2010. Application of stochastic approach to blast fragmentation modelling. Min Technol. 119 (4): 221 – 232.
22.
OnederraI, ThurleyMJ, CatalanA.2015. Measuring blast fragmentation at esperanza mine using high-resolution 3D laser scanning. Min Technol. 124 (1): 34 – 36.
23.
OuchterlonyF, SanchidriánJA.2019. A review of development of better prediction equations for blast fragmentation. J Rock Mech Geotech Eng. 11 (5): 1094 – 1109.
PinheiroPO, LinTY, CollobertR, DollárP.2016. Learning to refine object segments. European Conference on Computer Vision; Oct 8. Cham: Springer. p. 75–91
26.
RenS, HeK, GirshickR, SunJ.2015. Faster r-cnn: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497.
27.
RonnebergerO, FischerP, BroxT.2015. U-net: convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention; Oct 5. Cham: Springer. p. 234–241.
28.
SayadiA, MonjeziM, TalebiN, KhandelwalM.2013. A comparative study on the application of various artificial neural networks to simultaneous prediction of rock fragmentation and backbreak. J Rock Mech Geotech Eng. 5 (4): 318 – 324.
29.
SchenkF, TscharfA, MayerG, FraundorferF.2019. Automatic muck pile characterization from UAV images. ISPRS annals of the photogrammetry. Remote Sens Spat Inf Sci. 4 (W5): 163 – 170.
30.
ShiXZ, JianZH, WuBB, HuangD, WeiWE.2012. Support vector machines approach to mean particle size of rock fragmentation due to bench blasting prediction. Trans Nonferrous Met Soc China. 22 (2): 432 – 441.
31.
SiddiquiFI.2009. Measurement of size distribution of blasted rock using digital image processing. Eng Sci. 20 (2): 81 – 93.
SudhakarJ, AdhikariGR, GuptaRN.2006. Comparison of fragmentation measurements by photographic and image analysis techniques. Rock Mech Rock Eng. 39 (2): 159 – 168.
34.
ThorntonDM, KanchibotlaSS, EsterleJS.2001. A fragmentation model to estimate ROM size distribution of soft rock types. Proceedings of the Twenty-Seventh Annual Conference on Explosives and Blasting Technique, Vol I; Jan 1. International Society of Explosives Engineers. p. 41–53.
