A Robust Multi-source Image Matching Method for Power Equipment Based on Improved PIIFD

Robust feature matching for multi-source images of power equipment is critical for automatic diagnosis of power grid. However, classical image matching methods may not be suitable for this challenging task due to different resolution, spectrum and viewpoint between multi-source images. To solve this problem, a robust multi-source image matching algorithm is presented. First, the maximum moment map of phase congruency of input image is computed to enhance the raw image. Then, Canny operator and contour tracking method are employed to detect contour map of enhanced image. A set of feature points on contours is extracted by the curvature scale space corner detector. Second, a robust method is presented to assign main orientation to each feature point based on the local contour information, and a scale-invariant PIIFD descriptor is computed for feature point description. Finally, the bidirectional matching procedure is implemented to achieve feature correspondence and matching results are refined by both geometric and photometric information. We conduct the experiments on pairs of visible and infrared images of power equipment, and the results can demonstrate the effectiveness of our methods.