A machine vision approach to rock fragmentation analysis

 

Show simple item record

dc.contributor.author Crida, Robert Charles en_ZA
dc.date.accessioned 2014-11-05T17:19:25Z
dc.date.available 2014-11-05T17:19:25Z
dc.date.issued 1996 en_ZA
dc.identifier.citation Crida, R. 1996. A machine vision approach to rock fragmentation analysis. University of Cape Town. en_ZA
dc.identifier.uri http://hdl.handle.net/11427/9228
dc.description Bibliography: p. 217-223. en_ZA
dc.description.abstract [pp. i - iv missing] This thesis is concerned with the development of an instrument for the purpose of performing online measurement of rock size distribution using machine vision. This instrument has application in the gold mining industry where it could be used to measure the fragmentation of gold ore on a conveyor belt feed to an autogenous mill, for the purpose of controlling the mill. The gold ore can range in size from fine material (< 20mm) to very large rocks (0.5m). A machine vision approach is only capable of directly measuring the projected area of particles at the surface of the rock-stream. A volume distribution has to be estimated from this using a stereological method. These methods have been investigated previously and are typically error prone. They have not been investigated here. An investigation of lighting demonstrates that a diffuse lighting arrangement is suitable for this application. This would have two advantages: specular reflection from wet material is suppressed; and intensity values can be used to predict the orientation of the surface of the particles. A computational structure has been developed to identify and delineate rocks in an image for the purpose of measuring their areas. It is based on the human visual system in that it consists of a low-level preattentive vision stage and a higher-level stage of attention focusing. Multiscalar image processing techniques have also been integrated in order to improve the detection of rocks across a wide range of sizes. A performance advantage can be obtained in this way because all the algorithms can be better matched to the size of the objects being detected. Results have been obtained with an average true detection rate of 69 and a further close miss rate of 14 , with very few false alarms. The overall result is that the measured projected area distribution closely matches the true value for each test image. en_ZA
dc.language.iso eng en_ZA
dc.subject.other Electrical Engineering en_ZA
dc.title A machine vision approach to rock fragmentation analysis en_ZA
dc.type Doctoral Thesis
uct.type.publication Research en_ZA
uct.type.resource Thesis en_ZA
dc.publisher.institution University of Cape Town
dc.publisher.faculty Faculty of Engineering and the Built Environment
dc.publisher.department Department of Electrical Engineering en_ZA
dc.type.qualificationlevel Doctoral
dc.type.qualificationname PhD en_ZA
uct.type.filetype Text
uct.type.filetype Image
dc.identifier.apacitation Crida, R. C. (1996). <i>A machine vision approach to rock fragmentation analysis</i>. (Thesis). University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/9228 en_ZA
dc.identifier.chicagocitation Crida, Robert Charles. <i>"A machine vision approach to rock fragmentation analysis."</i> Thesis., University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 1996. http://hdl.handle.net/11427/9228 en_ZA
dc.identifier.vancouvercitation Crida RC. A machine vision approach to rock fragmentation analysis. [Thesis]. University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 1996 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/9228 en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Crida, Robert Charles AB - [pp. i - iv missing] This thesis is concerned with the development of an instrument for the purpose of performing online measurement of rock size distribution using machine vision. This instrument has application in the gold mining industry where it could be used to measure the fragmentation of gold ore on a conveyor belt feed to an autogenous mill, for the purpose of controlling the mill. The gold ore can range in size from fine material (< 20mm) to very large rocks (0.5m). A machine vision approach is only capable of directly measuring the projected area of particles at the surface of the rock-stream. A volume distribution has to be estimated from this using a stereological method. These methods have been investigated previously and are typically error prone. They have not been investigated here. An investigation of lighting demonstrates that a diffuse lighting arrangement is suitable for this application. This would have two advantages: specular reflection from wet material is suppressed; and intensity values can be used to predict the orientation of the surface of the particles. A computational structure has been developed to identify and delineate rocks in an image for the purpose of measuring their areas. It is based on the human visual system in that it consists of a low-level preattentive vision stage and a higher-level stage of attention focusing. Multiscalar image processing techniques have also been integrated in order to improve the detection of rocks across a wide range of sizes. A performance advantage can be obtained in this way because all the algorithms can be better matched to the size of the objects being detected. Results have been obtained with an average true detection rate of 69 and a further close miss rate of 14 , with very few false alarms. The overall result is that the measured projected area distribution closely matches the true value for each test image. DA - 1996 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 1996 T1 - A machine vision approach to rock fragmentation analysis TI - A machine vision approach to rock fragmentation analysis UR - http://hdl.handle.net/11427/9228 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record