The comparison of canny and structured forests edge detection application in precision identification of pointer instrument

Wang, Cui; Yuansheng, Fang; Jia, Li

doi:10.1109/ccdc.2018.8408247

Cited by 3 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alegria and Serra detected the position of the pointer in a pointer meter and achieved number recognition in the digital meter, based on early stage computer vision technology [10]. Wang et al used a structured random forest edge detection algorithm and canny edge detection algorithm, further combined with Hough straight line detection to detect the pointer of the meter, and completed automatic meter reading recognition [5]. Wu et al accomplished the reading of a substation meter pointer based on digital image processing technology, and proposed an adaptive gamma image enhancement algorithm based on Retinex theory to finalize the details and colors of the image [6].…”

Section: Computer Vision Methodsmentioning

confidence: 99%

“…The pointer linear equation is determined from the line connecting the pointer tip point and the center of rotation. Document [5,11,24] and others use Hough straight line detection to obtain the straight line equation of the left and right edges of the pointer, and determine the straight line equation of the pointer according to the intersection point of the straight line of the pointer edge at the pointer tip and the center of the meter. Zhou et al detected the first half section of the pointer tip using the YOLOv5 target detection network, and determined the pointer straight line equation according to the corner of the detection frame [29].…”

Section: Pointer Detection Comparison Experimentsmentioning

confidence: 99%

“…With the rapid development of artificial intelligence, machine vision has become effective in attaining industrial images and video information [4]. Accordingly, the accuracy and efficiency of reading recognition in large-scale industrial practice have been enhanced thanks to the application of machine vision in industrial meter reading and other technologies [5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Correction and pointer reading recognition of circular pointer meter

Zhang

Zhao

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

For the meter images collected in the actual environment, there is the possibility of tilt and rotation. This paper presents a method to calibrate the circular pointer-type meter based on YOLOv5s network. The convolution neural network (CNN) framework is used to detect the scale value in the meter panel as the key point, the position information and value information of the detected scale value are used to fit the elliptic equation of the position of the scale value with the least square method for perspective correction and rotation correction of the meter, and the corrected meter image is used to obtain the meter pointer reading. This paper proposes the weighted angle method to read the meter reading. The accumulated error of the meter image after multiple transformations is eliminated. Finally, comparing the pointer detection method of this paper with the traditional pointer detection method, the error of this detection method is smaller; comparing the meter reading results before and after correction, the meter reading error after correction is 50\% less than before correction, and comparing the method of this paper with other mainstream methods, it proves the effectiveness of the correction method of this paper.

show abstract

Section: Computer Vision Methodsmentioning

confidence: 99%