Infrared and Visible Image Fusion of Electric Equipment Using FDST and DC-PCNN

Abstract

Multi-sensor image fusion leads to more abundant details and a better description of the electric equipment monitoring scene. To improve the accuracy of overheating fault localization, a novel image fusion method based on Finite Discrete Shearlet Transform (FDST) and Dual-Channel Pulse Coupled Neuron Network (DC-PCNN) is proposed for fusing infrared and visible images of electric equipment. Firstly, FDST is utilized to decompose the source images. Then, two modified-spatial-frequency motivated DC-PCNNs with different linking strengths are used to fuse low-frequency and high-frequency subbands. Finally, the final fused image is reconstructed from the fused subbands by inverse FDST. Experimental results demonstrate the proposed method can achieve a remarkable improvement in preserving detail information and outperform other typical fusion methods in both overall visual performance and objective criteria.