Abstract
Infrared-RGB image registration plays an important role in thermal fault detection for monitoring transformer substation, because infrared thermal (IT) image can detect temperature difference information between normal and fault power equipment, and RGB image can detect detail information. But some challenges exist due to different representation of pixels in IT and RGB images. To solve these problems, a new gradient hash matching (GHM) model is proposed. First, image patches for IT and RGB images can be obtained, and thermal fault patch can be found in IT image. Then, pixel character can be described by horizontal and vertical gradient in all image patches. Third, discrete cosine transform (DCT) is used to turn patches from spatial domain to frequency domain. After extracting main character information in frequency domain for IT and RGB images, Hamming distance can be computed between corresponding patches. The proposed algorithm was tested on more than 20 patches of actual images for power equipment of transformer substation, which shows GHM algorithm can obtain correct matching in real scenes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
