Text Detection of Power Equipment Nameplates Based on Deep Learning

Guo, Chenjun; Ma, Xianlong; Shu, Yue; Duan, Yuting; Yu, Hong; Ma, Yi; Wang, Jiayu; Zhong, Linlin; Gao, Bingtuan

doi:10.1109/cyber46603.2019.9066516

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fan et al [8] derived the meter dials through YOLOv5 [30], and further obtained the scale and pointer through UNet [9], and then performed a reading of the meter. Guo et al [31] applied EAST [32] to the character detection of power equipment nameplates to acquire the location and content of the text. Salomon et al [33] utilized Faster R-CNN and YOLOv3 [34] to detect the dials and obtain the numbers, and finally combined the reading.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Scale value guided Lite-FCOS for pointer meter reading recognition

Wang,

Tian,

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

As intelligent power grid construction advances, substation inspection becomes crucial, particularly in identifying meter readings.Existing meter reading methods are mainly based on the relationship between pointer and scale. However, these methods commonly suffer from the issue of over-relying on prior reading information, limiting readings to known meters.Hereby in this paper, we propose a method reaching more accurate and robust performance for meter reading by utilizing the unnoticed scale value.We determine the meter pointer direction with the aid of Hough transform and the pointer distribution.To detect meters from the scene as well as obtain scale values and pointers from the meter dial, we build an object detection network, named Lite-FCOS, whose backbone adopts a fast global context network (FGCNet) that is lightweight and is of powerful feature extraction capabilities.For training these, meter dial detection dataset (MDDD) and dial reading information dataset (DRID) are constructed.Lite-FCOS achieves 94.4 mAP50 and 96.7 mAP50 on the above two datasets with only 4.2M parameters and 56.2 FPS.The entire pointer meter reading recognition process only spends 52 ms on an RTX 3080Ti with a successful meter reading rate (SMR rate) of 89.6%, which indicates that the proposed method achieves promising accuracy and speed.

show abstract