Multiple Visual Features Measurement With Gradient Domain Guided Filtering for Multisensor Image Fusion

• Published in: IEEE transactions on instrumentation and measurement Vol. 66; no. 4; pp. 691 - 703
• Main Authors: Yang, Yong, Que, Yue, Huang, Shuying, Lin, Pan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-04-2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Biomedical imaging; Computer vision; Discrete wavelet transforms; Gradient domain; guided filter; Image contrast; Image edge detection; Image filters; Image fusion; Image processing; Infrared imagery; Medical imaging; Multisensor fusion; Optimization; Optimization techniques; Salience; Sharpness; Smoothing; Visual effects; visual feature measurement; Visualization; Weight
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2017.2658098

Multisensor image fusion technologies, which convey image information from different sensor modalities to a single image, have been a growing interest in recent research. In this paper, we propose a novel multisensor image fusion method based on multiple visual features measurement with gradient domain guided filtering. First, a Gaussian smoothing filter is employed to decompose each source image into two components: approximate component formed by homogeneous regions and detail component with sharp edges. Second, an effective decision map construction model is presented by measuring three key visual features of the input sensor image: contrast saliency, sharpness, and structure saliency. Third, a gradient domain guided filtering-based decision map optimization technique is proposed to make full use of spatial consistency and generate weight maps. Finally, the resultant image is fused with the weight maps and then is experimentally verified through multifocus image, multimodal medical image, and infrared-visible image fusion. The experimental results demonstrate that the proposed method can achieve better performance than state-of-the-art methods in terms of subjective visual effect and objective evaluation.