Multi-Spectral Fusion and Denoising of RGB and NIR Images Using Multi-Scale Wavelet Analysis

Su, Haonan; Jung, Cheolkon

doi:10.1109/icpr.2018.8545108

Cited by 7 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiment we used a PC running Windows with an AMD Ryzen7 3700X CPU (3.59ghz). In order to compare the experimental results, we used the traditional multi-scale analysis method DWT, 18 WLS, 22 SM, 23 and the neural network-based Dense-Fuse 25 to compare with our proposed method.…”

Section: Experimental Results and Analysis Experimental Resultsmentioning

confidence: 99%

“…17 The problem of step processing is that the near-infrared image information is not used in noise reduction, resulting in poor noise reduction effect and much information loss. In Haonan Su et al, 18 multi-scale fusion is adopted to calculate wavelet scale image on each layer, and then wavelet coefficients are denoised based on the scale image to suppress high-frequency noise. Finally, the denoised coefficients are fused and transmitted upward as visible high-frequency information of the next layer, but flaws such as halo are easily generated in the edge region.…”

Section: Related Workmentioning

confidence: 99%

“…The results are shown in Table 2. Compared with other methods, the method adopted in this paper carries out optimization 22 scale map (SM), 23 DenseFuse, 25 DWT, 18 and the proposed method.…”

Section: Experiments Analysismentioning

confidence: 99%

“…The image information fusion using the proposed method has high utilization rate and is more consistent with the visual perception of human eyes. 23 DenseFuse, 25 DWT, 18 and the proposed method.…”

Section: Experiments Analysismentioning

confidence: 99%

See 3 more Smart Citations

An image fusion algorithm based on iterative wavelet transform for space non-cooperative targets

Zhao

Zhou

Sun

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

Due to the interference of outer space environment, the real image data of non-cooperative targets collected by a single sensor often has problems such as low contrast and insufficient color information display. In this paper, we propose an image fusion method with iterative wavelet transform, which utilizes the respective advantages of visible image and near-infrared image to improve the clarity of space non-cooperative target and retain color information. The dataset in this paper comes from the satellite model group taken by ourselves. Due to different shooting angles and resolutions, we need to carry out accurate registration of near-infrared images and visible light. Therefore, we also propose an improved registration algorithm based on ORB feature matching. In order to verify the effectiveness of the method, other image fusion methods are selected for comparative analysis. The method proposed can preserve texture features and color information of space non-cooperative targets.

show abstract

Section: Experimental Results and Analysis Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Experiments Analysismentioning

confidence: 99%

Section: Experiments Analysismentioning

confidence: 99%

See 2 more Smart Citations

An image fusion algorithm based on iterative wavelet transform for space non-cooperative targets

Zhao

Zhou

Sun

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

show abstract

“…Compared to our previous work [ 21 ], we have four extensions: (1) We introduce two observation models of noise and discrepancy from RGB data, NIR data, and the wavelet scale map in problem formulation. These models provide the mathematical basis for Bayesian derivation.…”

Section: Introductionmentioning

confidence: 99%

Multi-Spectral Fusion and Denoising of Color and Near-Infrared Images Using Multi-Scale Wavelet Analysis

Jung

2021

Sensors

Self Cite

View full text Add to dashboard Cite

We formulate multi-spectral fusion and denoising for the luminance channel as a maximum a posteriori estimation problem in the wavelet domain. To deal with the discrepancy between RGB and near infrared (NIR) data in fusion, we build a discrepancy model and introduce the wavelet scale map. The scale map adjusts the wavelet coefficients of NIR data to have the same distribution as the RGB data. We use the priors of the wavelet scale map and its gradient as the contrast preservation term and gradient denoising term, respectively. Specifically, we utilize the local contrast and visibility measurements in the contrast preservation term to transfer the selected NIR data to the fusion result. We also use the gradient of NIR wavelet coefficients as the weight for the gradient denoising term in the wavelet scale map. Based on the wavelet scale map, we perform fusion of the RGB and NIR wavelet coefficients in the base and detail layers. To remove noise, we model the prior of the fused wavelet coefficients using NIR-guided Laplacian distributions. In the chrominance channels, we remove noise guided by the fused luminance channel. Based on the luminance variation after fusion, we further enhance the color of the fused image. Our experimental results demonstrated that the proposed method successfully performed the fusion of RGB and NIR images with noise reduction, detail preservation, and color enhancement.

show abstract

NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

Sun

Jung

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Near infrared (NIR) images have clear textures but do not contain color. In this paper, we propose NIR to RGB domain translation using asymmetric cycle generative adversarial networks (ACGANs). The RGB image (3 channels) has richer information than the NIR image (1 channel), which makes NIR-RGB domain translation asymmetric in information. We adopt asymmetric cycle GANs that have different network capacities according to the translation direction. We combine UNet and ResNet in generator and use the feature pyramid networks (FPNs) in discriminator. With the help of a 128 × 128 large receptive field, we capture rich spatial context information with a multiscale architecture. Experimental results show that the proposed method achieves natural looking NIR colorization results with high generalization ability, i.e. feasible in category unaware cases, and outperforms state-of-the-art ones in realistic colorization and resistance to unregistration.

show abstract

Multi-Spectral Fusion and Denoising of RGB and NIR Images Using Multi-Scale Wavelet Analysis

Cited by 7 publications

References 19 publications

An image fusion algorithm based on iterative wavelet transform for space non-cooperative targets

An image fusion algorithm based on iterative wavelet transform for space non-cooperative targets

Multi-Spectral Fusion and Denoising of Color and Near-Infrared Images Using Multi-Scale Wavelet Analysis

NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

Contact Info

Product

Resources

About