Abstract | ||
---|---|---|
The fusion of infrared and visible images of the same scene aims to generate a composite image which can provide a more comprehensive description of the scene. In this paper, we propose an infrared and visible image fusion method based on convolutional neural networks (CNNs). In particular, a siamese convolutional network is applied to obtain a weight map which integrates the pixel activity information from two source images. This CNN-based approach can deal with two vital issues in image fusion as a whole, namely, activity level measurement and weight assignment. Considering the different imaging modalities of infrared and visible images, the merging procedure is conducted in a multi-scale manner via image pyramids and a local similarity-based strategy is adopted to adaptively adjust the fusion mode for the decomposed coefficients. Experimental results demonstrate that the proposed method can achieve state-of-the-art results in terms of both visual quality and objective assessment. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1142/S0219691318500182 | INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING |
Keywords | Field | DocType |
Infrared and visible image fusion, convolutional neural networks, image pyramids, activity level measurement, weight assignment | Computer vision,Level measurement,Mathematical optimization,Image fusion,Convolutional neural network,Fusion,Composite image filter,Artificial intelligence,Pixel,Merge (version control),Infrared,Mathematics | Journal |
Volume | Issue | ISSN |
16 | 3 | 0219-6913 |
Citations | PageRank | References |
11 | 0.54 | 15 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Liu | 1 | 492 | 30.80 |
Xun Chen | 2 | 458 | 52.73 |
Juan Cheng | 3 | 62 | 11.53 |
Hu Peng | 4 | 46 | 13.63 |
Zengfu Wang | 5 | 1133 | 85.70 |