A detection and recognition system of pointer meters in substations based on computer vision. (February 2020)

• Record Type: Journal Article
• Authors: Liu, Yang; Liu, Jun; Ke, Yichen
• Is Part Of: Measurement. Volume 152(2020)
• Publication Date: 2020-02
• Subjects: Pointer meter -- Detection and recognition -- Computer vision -- Feature correspondence -- Perspective transform; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2019.107333
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlight: The Faster R-CNN is employed to detect meters in the substation. An algorithm based on feature correspondence to remove specular reflection is designed. The Perspective Transform is applied to calibrate the camera angle of images. The proposed recognition system can accurately read pointer meters. Abstract: In order to develop unattended intelligent substations, numerous automatic meter reading methods have been proposed with the invention of inspection robots. However, most methods have strict restrictions on the captured image quality, so they cannot meet the application requirements of the substation. In this paper, a versatile pointer meter detection and recognition system based on computer vision is proposed for different environments. A Faster Region-based Convolutional Network (Faster R-CNN) is first used to detect the position of the target meter and the camera is adjusted according to the detection box. Then, thanks to the feature correspondence algorithm and the Perspective Transform, the problem of specular reflection and image distortion is solved to obtain high quality images. Finally, reading can be obtained after the position of pointer detected by Hough Transform. The experimental results verify the stability and accuracy of recognition system which is proved to work well under different conditions.