A robust visible and infrared image matching algorithm for power equipment based on phase congruency and scale-invariant feature

•An intensity invariant feature detection method based on phase congruency and corner detector is proposed to detect feature points with high repeatability.•A novel descriptor named the histogram of phase congruency orientation (HPCO) is proposed for feature description.•An effective refinement strategy is devised to achieve dense and accurate feature matching.•Performance of the visible and infrared image matching algorithm is validated with experiments carried out on power equipment images.