Title :
Study of FPGA-based visual detection for pointer dial
Author :
Bin Sun ; Changsheng Zhang ; Ziyu Liu ; Bin Qian ; Hanping Zhang
Author_Institution :
Fac. of Inf. Eng. & Autom., Kunming Univ. of Sci. & Technol., Kunming, China
fDate :
May 31 2014-June 2 2014
Abstract :
The lubricating oil pressure of ball mill in ore dressing plant is a critical real-time monitoring parameter. In this paper, bilinear interpolation, DoG filter, Marr-Hildreth edge detector and watershed algorithms are studied on FPGA. In particular, the algorithm HVPP is proposed. Segmentation, extraction and number identification are realized for the pressure pointer dial image by using these algorithms, such that intelligent reading for the gauge is achieved. Experiment shows that employing the fast algorithm based on logic circuit to accomplish the machine recognition has advantages of good real-time performance and high recognition rate.
Keywords :
Gaussian processes; ball milling; character recognition; computer vision; edge detection; feature extraction; field programmable gate arrays; gauges; image segmentation; interpolation; lubricating oils; mineral processing; process monitoring; production engineering computing; DoG filter; FPGA-based visual detection; Gaussian difference filter; HVPP algorithm; Marr-Hildreth edge detector; ball mill; bilinear interpolation; extraction; gauge; intelligent reading; logic circuit; lubricating oil pressure; machine recognition; number identification; ore dressing plant; pressure pointer dial image; real-time monitoring parameter; segmentation; watershed algorithm; Feature extraction; Field programmable gate arrays; Image edge detection; Image segmentation; Interpolation; Pressure gauges; Bilinear interpolation; HVPP; Marr-Hildreth edge detector; Watershed algorithm;
Conference_Titel :
Control and Decision Conference (2014 CCDC), The 26th Chinese
Conference_Location :
Changsha
Print_ISBN :
978-1-4799-3707-3
DOI :
10.1109/CCDC.2014.6852398
