A detection and identification method for transformer oil surface temperature controller

Abstract

The invention discloses a method for detecting and identifying a transformer oil level temperature controller. The method includes: firstly, an inspection robot arrives at a designated position to acquire a picture of a transformer oil level temperature controller to be detected; secondly, based on the transformer oil level temperature controller to be detected, Surface temperature controller image, screen the final target image of the target transformer oil surface temperature controller area; then, read in the target image, and use different image preprocessing operations according to the pointer color; then, use the target detector to locate the instrument and segment the dial Area, eliminate the interference factors outside the dial of the transformer oil level thermostat; then, use the corresponding method to extract the outline of the pointer according to the color of the pointer; finally, use the cosine law to calculate the direction of rotation of the pointer and the reading it points to; this method can detect and identify a variety of lighting , Transformer oil surface temperature controller under attitude change.

Description

technical field [0001] The invention relates to the field of electric power inspection robots, in particular to a method for detecting and identifying a transformer oil level temperature controller. Background technique [0002] The power inspection robot needs to realize the basic functions such as autonomous positioning and navigation in the substation, field instrument display number recognition, and automatic charging. The core function is to detect and identify the indications of instruments and meters of on-site electrical equipment. [0003] At present, it is difficult for the power inspection robot to detect and identify the readings of the transformer oil level thermostat. Due to cost and historical reasons, most transformer oil level thermostats do not have the remote transmission function of smart meters, and inspection robots can only read the meter indications through computer vision. The premise of accurately identifying the indication of the transformer oil ...

AI Technical Summary

Problems solved by technology

Due to cost and historical reasons, most transformer oil level thermostats do not have the remote transmission function of smart meters, and only inspection robots can use computer vision to read the data indicated by the meter.

The premise of accurately identifying the indication of the transformer oil level thermostat is to accurately detect the position of the transformer oil level thermostat in the visual image, and most of the transformer oil level thermostats are outdoors. At present, most methods use traditional image The detection and identification are carried out by means of processing. In the case of changing lighting conditions, the detection effect is not good. Generally, a set of parameters is required for one lighting condition. In the identification process, there are also situations such as different outdoor lighting and different shooting angles of inspection robots.

Images