Infrared and visible image fusion technologies make full use of different image features obtained by different sensors, retain complementary information of the source images during the fusion process, and use redundant information to improve the credibility of the fusion image. In recent years, many researchers have used deep learning methods (DL) to explore the field of image fusion and found that applying DL has improved the time-consuming efficiency of the model and the fusion effect. However, DL includes many branches, and there is currently no detailed investigation of deep learning methods in image fusion. In this work, this survey reports on the development of image fusion algorithms based on deep learning in recent years. Specifically, this paper first conducts a detailed investigation on the fusion method of infrared and visible images based on deep learning, compares the existing fusion algorithms qualitatively and quantitatively with the existing fusion quality indicators, and discusses various fusions. The main contribution, advantages, and disadvantages of the algorithm. Finally, the research status of infrared and visible image fusion is summarized, and future work has prospected. This research can help us realize many image fusion methods in recent years and lay the foundation for future research work.

The purpose of image fusion is to combine the source images of the same scene into a single composite image with more useful information and better visual effects. Fusion GAN has made a breakthrough in this field by proposing to use the generative adversarial network to fuse images. In some cases, considering retain infrared radiation information and gradient information at the same time, the existing fusion methods ignore the image contrast and other elements. To this end, we propose a new end-to-end network structure based on generative adversarial networks (GANs), termed as FLGC-Fusion GAN. In the generator, using the learnable grouping convolution can improve the efficiency of the model and save computing resources. Therefore, we can have a better trade-off between the accuracy and speed of the model. Besides, we take the residual dense block as the basic network building unit and use the perception characteristics of the inactive as content loss characteristics of input, achieving the effect of deep network supervision. Experimental results on two public datasets show that the proposed method performs well in subjective visual performance and objective criteria and has obvious advantages over other current typical methods.

Clouds and their shadows hinder accurate analysis of optical remote sensing imagery, making cloud removal an indispensable preprocessing step in remote sensing. However, existing methods lack efficient long-range modeling capabilities and overlook the impact of cloud irregularities and uncertainties on cloud removal. Additionally, resolving spectral confusion between cloud shadows and surface information remains a significant challenge. To tackle this issue, this study introduces an innovative cloud removal algorithm termed the multiscale hybrid sparse transformer (HSFormer), which adaptively removes clouds and shadows while reconstructing land surface semantics. HSFormer leverages pixel correlation explicit sparsity and uncertainty-driven implicit sparsity to maximize attention gains, enabling efficient cloud recognition and removal. The global pixel correlation based on attention relations enhances the semantic integrity of reconstructed images and avoids information loss across frequency domains. Furthermore, the uncertainty-guided adaptive receptive field enhances the model’s ability to resolve complex cloud-covered spatial relationships and reduces the spatial uncertainty of the reconstructed image. Experiments on simulated cloud shadow, real RICE, and full-band WHUS2-CRv datasets demonstrate HSFormer’s superiority over existing methods, improving PSNR and SSIM by 0.49% and 0.62%, respectively, in average evaluations across all bands of the WHUS2-CRv dataset and effectively addresses spectral aliasing between cloud shadows and dark surfaces.

The research about online monitoring and leakage automatic location of water distribution networks (WDN) has a wide range of applications that include water resource protection, monitoring, and allocation. Variational mode decomposition (VMD) and cross-correlation (CC) based leakage location is a popular and effective method in WDN. However, the value of K intrinsic mode functions (IMFs) based on VMD decomposition needs to be determined artificially, which affects the separation effect of signal frequency band characteristics directly. Hence, this work proposes an adaptive method to determine the parameter K of leakage vibration signals IMFs, which will be applied to automatic leakage location in WDN. Firstly, the number of saddle points in the frequency domain envelope of the sampled signal in different step sizes is calculated. The parameter K is determined according to the curvature change of the number of saddle points and the sampled signal. Finally, the selective IMFs are reconstituted into a new signal, which can determine a leak position using CC based time-delay estimation (TDE). To verify the effectiveness of the proposed algorithm, the different methods based on EMD and Fast ICA are compared. The experimental results demonstrate that the proposed parameter K value adaptive VMD (KVA-VMD) decomposition method is more suitable for leakage location in WDN.