Re2FAD: A differential image registration and robust image fusion method framework for power thermal anomaly detection

Previous image fusion methods may not effectively characterize thermal anomalies in power equipment fault detection. In addition, the source images of power equipment collected on-site are not registered and cannot be directly used for image fusion. To these problems, this paper proposes a framework for differential image registration and robust image fusion to assist thermal anomaly detection (Re2FAD). First, Re2FAD calculates a joint histogram of the source images after low-frequency decomposition and constructs a criterion function to solve the optimal registration parameters. Second, the membership function is constructed to clarify the labels of the segmented regions. Third, the fusion strategy is selected according to the label to reconstruct the fused image. We built the power equipment dataset of the Shanghai Sanlin 500kV substation and proved that the dataset has higher registration accuracy compared with other image registration methods. Meanwhile, the proposed method is compared with state-of-the-art image fusion methods on this dataset. It can be seen from the objective evaluation indicators that the proposed method is 29.03% higher than the comparison method in terms of the accuracy of highlighting thermal anomalies, and the average running time is 2.696 s, which can meet the requirements of auxiliary thermal anomaly detection.