Infrared and visible image fusion with spectral graph wavelet transform

Yan, Xiang; Qin, Hanlin; Li, Jia; Zhou, Huixin; Zong, Jingguo

doi:10.1364/josaa.32.001643

Cited by 41 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final fused images are obtained by inverse transforms. There are several representative transforms for infrared and visible image fusion: pyramid transforms [28][29][30], wavelet transforms [31][32][33], contourlet transforms, and non-subsampled contourlet transform [12,34,35]. SR [36] is a novel image representation theory that simulates the sparse coding mechanism of human vision systems [37].…”

Section: Conventional Fusion Methodsmentioning

confidence: 99%

Infrared and Visible Image Fusion with a Generative Adversarial Network and a Residual Network

Wang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Infrared and visible image fusion can obtain combined images with salient hidden objectives and abundant visible details simultaneously. In this paper, we propose a novel method for infrared and visible image fusion with a deep learning framework based on a generative adversarial network (GAN) and a residual network (ResNet). The fusion is accomplished with an adversarial game and directed by the unique loss functions. The generator with residual blocks and skip connections can extract deep features of source image pairs and generate an elementary fused image with infrared thermal radiation information and visible texture information, and more details in visible images are added to the final images through the discriminator. It is unnecessary to design the activity level measurements and fusion rules manually, which are now implemented automatically. Also, there are no complicated multi-scale transforms in this method, so the computational cost and complexity can be reduced. Experiment results demonstrate that the proposed method eventually gets desirable images, achieving better performance in objective assessment and visual quality compared with nine representative infrared and visible image fusion methods.

show abstract

Section: Conventional Fusion Methodsmentioning

confidence: 99%

Infrared and Visible Image Fusion with a Generative Adversarial Network and a Residual Network

Wang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…It is also observed that the difference in performance between the proposed frame and the spectrum-adapted frame is more pronounced when using up to eight scales. In recent studies that use the SGWT [31], [51]- [55], typically, up to six scales are used, which can be explained by observing that the performance for this frame saturates at J = 5. In contrast, the proposed frames show a monotonic increase in performance also for larger number of scales.…”

Section: Signal Denoisingmentioning

confidence: 99%

Signal-Adapted Tight Frames on Graphs

Behjat

Richter

Ville

et al. 2016

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Abstract-The analysis of signals on complex topologies modeled by graphs is a topic of increasing importance. Decompositions play a crucial role in the representation and processing of such information. Here, we propose a new tight frame design that is adapted to a class of signals on a graph. The construction starts from a prototype Meyer-type system of kernels with uniform subbands. The ensemble energy spectral density is then defined for a given set of signals defined on the graph. The prototype design is then warped such that the resulting subbands capture the same amount of energy for the signal class. This approach accounts at the same time for graph topology and signal features. The proposed frames are constructed for three different graph signal sets and are compared with non-signal-adapted frames. Vertex localization of a set of resulting atoms is studied. The frames are then used to decompose a set of real graph signals and are also used in a setting of signal denoising. The results illustrate the superiority of the designed signal-adapted frames, over frames blind to signal characteristics, in representing data and in denoising.

show abstract

“…Mean and standard deviation: The statistical parameters mean (μ), a measure of average intensity and variance ( (9) where MN is the total number of pixels in the image and x ij is the pixel intensity at that location.…”

Section: Performance Evaluation 41 Subjective and Objective Evaluationmentioning

confidence: 99%

“…Several fusion methods for low-light visible and infrared image fusion have been proposed by researchers [7][8][9] . Generally, pixel-based fusion methods are employed for fusion as they are simple to implement as compared with the computational complexity in implementing region-based and feature-based fusion techniques.…”

Section: Introductionmentioning

confidence: 99%

Contrast Enhanced Low-light Visible and Infrared Image Fusion

2016

View full text Add to dashboard Cite

Multi-modal image fusion objective is to combine complementary information obtained from multiple modalities into a single representation with increased reliability and interpretation. The images obtained from low-light visible cameras containing fine details of the scene and infrared cameras with high contrast details are the two modalities considered for fusion. In this paper, the low-light images with low target contrast are enhanced by using the phenomenon of stochastic resonance prior to fusion. Entropy is used as a measure to tune iteratively the coefficients using bistable system parameters. The combined advantage of multi scale decomposition approach and principal component analysis is utilized for the fusion of enhanced low-light visible and infrared images. Experimental results were carried out on different image datasets and analysis of the proposed methods were discussed.

show abstract

Infrared and visible image fusion with spectral graph wavelet transform

Cited by 41 publications

References 29 publications

Infrared and Visible Image Fusion with a Generative Adversarial Network and a Residual Network

Infrared and Visible Image Fusion with a Generative Adversarial Network and a Residual Network

Signal-Adapted Tight Frames on Graphs

Contrast Enhanced Low-light Visible and Infrared Image Fusion

Contact Info

Product

Resources

About