Detection of Remnant Material and Its Quantification
H. B. Kekre1, Dhirendra Mishra2, Prasad Rangnekar3, Raja Ketkar4
1Dr. H. B. Kekre, Senior professor, Department, of Computer Engineering, Technology, Management and Engineering, Mumbai, India.
2Dr. Dhirendra Mishra, Associate professor & HOD, Department, of Computer Engineering, Technology, Management and Engineering, Mumbai, India.
3Mr. Prasad Rangnekar, EVP and Global Head, Strategic Solutions Group, CMC Ltd, Mumbai, India.
4Mr. Raja Ketkar, Department of Information Technology, of Technology, Management and Engineering, Mumbai, India.
Manuscript received on May 14, 2013. | Revised Manuscript received on June 05, 2013. | Manuscript published on June 30, 2013. | PP: 81-85 | Volume-2, Issue-5, June 2013. | Retrieval Number: E1710062513/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Loading-unloading of goods is an essential task that is undertaken at every industrial site. Mines witness a large scale transportation activity. As the volume of such goods is large in size, the mode of transport used for delivery is usually dumpers. Huge cranes load the dumpers at one location with some material and then the dumper moves to the desired destination for unloading. After the unloading process, the dumper may still hold some residual matter in its dumping bed which may be misused stealthily; theft of which may amount to huge loss for the concerned industry. This paper mainly discusses attempts in the direction to devise an automatic system that will detect and quantify the remnant material which is left behind in the dump-trucks after the unloading process is formally completed. In this piece of research we have applied grey level co-occurrence matrix (GLCM) and Material specific techniques to detect the carry back for materials like aluminium, coal, copper, iron ore, manganese and lime stone. Results of both these approaches have been compared.
Keywords: Carry-back detection, GLCM, Material specific techniques, monochrome, r-plane, Intensity adjustment.