Transformer substation foreign matter detection method based on binocular vision

Abstract

The invention relates to a transformer substation foreign matter detection method based on binocular vision. The transformer substation foreign matter detection method comprises the following steps: S1, uniformly arranging a plurality of groups of binocular cameras in a substation; s2, acquiring internal and external parameters of a binocular camera; s3, dividing safety alert areas of different levels, storing vertex three-dimensional coordinate values of the safety alert areas, and constructing a database; s4, performing binocular preprocessing operation on the dynamic target, extracting pixel coordinates of five pairs of feature points, and calculating a three-dimensional coordinate value, an intrusion speed and a motion direction of the dynamic target; and S5, comprehensively judging the invasion degree of the dynamic target by combining the three-dimensional coordinate value, the invasion speed and the movement direction of the dynamic target. Compared with the prior art, the depthvalue of the to-be-detected target can be obtained, and the real three-dimensional coordinates of the detected object can be restored; the area where the foreign matter is located can be accurately judged, the advancing direction and the advancing speed of the foreign matter are obtained, the foreign matter invasion level is comprehensively judged, and corresponding measures are reasonably taken.

Description

technical field [0001] The invention relates to the field of substation safety protection, in particular to a binocular vision-based foreign object detection method in a substation. Background technique [0002] Power transmission directly affects the national economy and people's livelihood, and substations play a vital role in power transmission. Substations are often built in the outskirts of cities or remote areas, and a lot of manpower and material resources will be invested in daily on-duty substations. With the application of video detection technology in the field of substation monitoring, the goal of unattended substations has been completed to a certain extent, but the traditional video monitoring technology still has certain limitations. Although the operation and maintenance personnel can remotely grasp the information of the substation, the video information transmitted back to the main control center needs to be manually screened to extract valuable informatio...

AI Technical Summary

Problems solved by technology

With the application of video detection technology in the field of substation monitoring, the goal of unattended substations has been achieved to a certain extent, but the traditional video monitoring technology still has certain limitations.

Although the operation and maintenance personnel can remotely grasp the information of the substation, the video information transmitted back to the main control center needs to be manually screened to extract valuable information; in addition, most of the current surveillance cameras are monocular cameras, which cannot provide the depth of the surveillance scene Information, the actual intrusion distance can only be judged by human subjective, there are a lot of subjective factors, which increases the probability of false positives

Images