Automatic Defect Detection of Ground Line from Images Acquired by UAV

Hiroshi Ohta, Kenta Takaya, Valeri Kroumov

The inspection of ground lines on transmission towers is necessary to maintain stable power transmission. We already developed a UAV which automatically acquires images of the ground line for inspections. In this paper, we propose a method for detecting defect locations of the ground line from the images acquired by the UAV. In order to identify the defect locations, it is necessary to extract a ground line region from the image in advance. The proposed method finds the ground line from multiple line segments in the image by using edge intensity of the image. The identification of defect locations is performed by a deep neural network (DNN) for each divided image of a ground line region. As a result of the experiment, a success rate of 0.978 was obtained for the extraction of a ground line from UAV images. In case of using the GoogLeNet as the DNN, an accuracy rate of 0.975 was obtained for defect detection.

電気学会論文誌

145

3

408

416

10.1541/ieejeiss.145.408