An Accurate Reading Algorithm for Substation Pointer Meters Based on Improved 2-D Gamma Function and PA-RetinaNet

Abstract

Aiming at the low reading accuracy of the substation pointer meter caused by illumination and shooting angle, an accurate reading algorithm based on improved 2-D Gamma function and PA-RetinaNet is proposed. Firstly, the multi-scale Gaussian function is used to extract the illumination components and the 2-D Gamma function is reconstructed to adaptively adjust pointer meter images under different illumination intensity. Then, the path augmentation is integrated into the RetinaNet to detect the dial scale digital key points. Meanwhile, combined with the elliptical transformation theory, the correction reference point in the perspective transformation is reselected to realize the tilt correction of the pointer meter image. Finally, the centripetal constraint is added to the line segment detector to achieve accurate positioning of the pointer, and the function between the pointer angle and the meter reading is deduced. Experimental results demonstrated that the method can effectively solve the problem of illumination and shooting angle in the reading of the substations pointer meter.