Two‐scale fusion method of infrared and visible images via parallel saliency features. Issue 16 (24th February 2021)

• Record Type: Journal Article
• Authors: Duan, Chaowei; Xing, Changda; Lu, Shanshan; Wang, Zhisheng
• Is Part Of: IET image processing. Volume 14:Issue 16(2020)
• Page Start: 4412
• Page End: 4423
• Publication Date: 2021-02-24
• Subjects: image representation -- image fusion -- feature extraction -- infrared imaging -- image texture -- image reconstruction -- Gaussian processes -- image filtering -- tensors; visible images -- parallel saliency features -- efficient fusion method -- feature information -- source images -- multiple imaging modalities -- single fused image -- multiscale domain -- input images -- two‐scale image representations -- contrast saliency weight map -- base layers -- weighted local intensity energy -- infrared images -- detail saliency weight map -- fused base -- two‐scale fusion method -- Gaussian filter -- detail texture information extraction -- image reconstruction -- structure tensor; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.1165
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : An efficient fusion method of infrared and visible images is proposed based on the parallel saliency features. The method integrates significant feature information from the source images of multiple imaging modalities into a single fused image in a multi‐scale domain, while suppressing visual artefacts and retaining more detail and texture information. First, the input images are decomposed into two‐scale image representations, namely the base and detail layers, using a Gaussian filter. Second, the parallel saliency features of the high contrast and detail textures are captured to acquire the saliency maps. The contrast saliency weight map of the base layers based on the weighted local intensity energy aims to highlight the salient targets in infrared images and preserve the high‐intensity regions in visible images, while the detail saliency weight map of the detail layers using the structure tensor to extract the detail texture information. Finally, the final image is reconstructed by the fused base and detail layers. Sufficient experimental results convincingly demonstrate that the presented method can achieve a comparable or superior performance compared with several state‐of‐the‐art fusion methods via subjective assessments and objective evaluations, and it is more suitable for the practical applications due to the high computing efficiency.