For the past few years, image fusion technology has made great progress, especially in infrared and visible light image infusion. However, the fusion methods, based on traditional or deep learning technology, have some disadvantages such as unobvious structure or texture detail loss. In this regard, a novel generative adversarial network named MSAt-GAN is proposed in this paper. It is based on multi-scale feature transfer and deep attention mechanism feature fusion, and used for infrared and visible image fusion. First, this paper employs three different receptive fields to extract the multi-scale and multi-level deep features of multi-modality images in three channels rather than artificially setting a single receptive field. In this way, the important features of the source image can be better obtained from different receptive fields and angles, and the extracted feature representation is also more flexible and diverse. Second, a multi-scale deep attention fusion mechanism is designed in this essay. It describes the important representation of multi-level receptive field extraction features through both spatial and channel attention and merges them according to the level of attention. Doing so can lay more emphasis on the attention feature map and extract significant features of multi-modality images, which eliminates noise to some extent. Third, the concatenate operation of the multi-level deep features in the encoder and the deep features in the decoder are cascaded to enhance the feature transmission while making better use of the previous features. Finally, this paper adopts a dual-discriminator generative adversarial network on the network structure, which can force the generated image to retain the intensity of the infrared image and the texture detail information of the visible image at the same time. Substantial qualitative and quantitative experimental analysis of infrared and visible image pairs on three public datasets show that compared with state-of-the-art fusion methods, the proposed MSAt-GAN network has comparable outstanding fusion performance in subjective perception and objective quantitative measurement.
Regarding the problems of image distortion, edge blurring, Gibbs phenomena in the traditional wavelet transform algorithm and the loss of subtle features in the Non-Subsampled Shearlet Transform (NSST), and considering the physical characteristics of infrared and visible images, an infrared and visible image fusion algorithm based on the Lifting Stationary Wavelet Transform (LSWT) and Non-Subsampled Shearlet Transform is proposed in this paper. First, since LSWT can quickly calculate and has all advantages of traditional WT, it is utilized to decompose infrared and visible images to obtain lowfrequency coefficients and multi-scale and multi-directional high-frequency coefficients, respectively. Second, NSST multi-scale decomposition is used to extract the target features and detailed features of the image from the high and low-frequency sub-bands to obtain new high and low-frequency sub-bands. Third, according to the physical characteristics that low and high-frequency coefficients represent, different fusion rules are designed. Discrete Cosine Transform (DCT) and Local Spatial Frequency (LSF) are introduced in the low-frequency sub-band, and LSF adaptive weighted fusion rules are used in the DCT domain. The fusion strategy improves the regional contrast in the high-frequency sub-band with the spectral characteristics of human vision. Finally, the Inverse Lifting Stationary Wavelet Transform (ILSWT) is used to reconstruct the fusion coefficients to obtain the final fused images. To verify the advantages of the proposed algorithm in this paper, the classic and advanced 9 IR and VI fusion algorithms are selected for subjective and objective comparison. In the objective evaluation, a comprehensive ranking index is designed based on 9 classical indicators. Simulation experiments with 10 IR and VI fusion algorithms prove that the proposed algorithm has better performance and flexibility. The results show that the proposed algorithm in this paper fuses the images with clear edges, prominent targets, and good visual perception, and it outperforms state-of-the-art image fusion algorithms.
Most of the significant petroleum- and coal-bearing sedimentary basins in Northeast Asia originated via rifting and thermal subsidence during the Late Jurassic-Early Cretaceous, followed by basin inversion in the Late Cretaceous. However, the tectonic background governing these basin prototype shifts has not been fully explored. The unconformities are excellent archives of plate boundary interactions and geodynamic switches in subduction zones. The Eastern Heilongjiang Province (EHLJ), Northeast China (NE China), comprises a series of Mesozoic-Cenozoic residual basins with well-preserved successions and provides significant insights into the tectonic characteristics and background of Northeast Asia. Mesozoic unconformities and large-scale contractional structures in the basins mark a series of important tectonic transitions in Northeast Asia. Based on the synthesis information of regional Mesozoic unconformities identified in the seismic reflection profiles and field outcrops of EHLJ, the tectonic characteristics and geodynamic background of the Mesozoic continental margin basins in Northeast Asia are analysed. The Middle-Upper Jurassic/basement unconformity (U1) can only be found in some areas of the Sanjiang and Hulin basins. It was a response to the continental collision of Siberia and the northern China–Mongolia tract along the Mongolia–Okhotsk suture during the Jurassic. The Paleo-Pacific Plate rapidly subducted in the NNW direction towards the eastern margin of Eurasia in the early Lower Cretaceous resulting in a mass of strike-slip faults and the widespread absence of deposits (Valanginian) (U2) in the EHLJ. Because of the subduction slab rollback of the Paleo-Pacific Plate during the late Lower Cretaceous, the local asthenospheric material upwelled, and fault and volcanic activities intensified in Northeast Asia. The Lower Cretaceous Dongshan Formation (Fm)/Muleng Fm unconformity (U3-1) reflects a specific scale of bimodal magmatism in the Songliao Basin and the EHLJ. The Pacific Plate subducted in a transformation from NNW to WNW during the early Upper Cretaceous (Cenomanian). The Houshigou Fm (Qixinhe Fm)/Lower Cretaceous angular unconformity (U3) reflects that on the basins experienced denudation after being extensively uplifted from the subduction events. With the subduction of the Kula Plate, a compression stress field during the later Upper Cretaceous Period controlled NE China. The basins underwent a widely compressive deformation, accompanied by large-scale thrusts, denudation and deplanation, resulting in Paleogene/Cretaceous unconformity (U4) was formed.
As for the problems of boundary blurring and information loss in the multi-focus image fusion method based on the generative decision maps, this paper proposes a new gradient-intensity joint proportional constraint generative adversarial network for multi-focus image fusion, with the name of GIPC-GAN. First, a set of labeled multi-focus image datasets using the deep region competition algorithm on a public dataset is constructed. It can train the network and generate fused images in an end-to-end manner, while avoiding boundary errors caused by artificially constructed decision maps. Second, the most meaningful information in the multi-focus image fusion task is defined as the target intensity and detail gradient, and a jointly constrained loss function based on intensity and gradient proportional maintenance is proposed. Constrained by a specific loss function to force the generated image to retain the information of target intensity, global texture and local texture of the source image as much as possible and maintain the structural consistency between the fused image and the source image. Third, we introduce GAN into the network, and establish an adversarial game between the generator and the discriminator, so that the intensity structure and texture gradient retained by the fused image are kept in a balance, and the detailed information of the fused image is further enhanced. Last but not least, experiments are conducted on two multi-focus public datasets and a multi-source multi-focus image sequence dataset and compared with other 7 state-of-the-art algorithms. The experimental results show that the images fused by the GIPC-GAN model are superior to other comparison algorithms in both subjective performance and objective measurement, and basically meet the requirements of real-time image fusion in terms of running efficiency and mode parameters quantity.
Significant circulating currents in the modular multilevel converter (MMC) increase system losses and complicate heat-sink design. Conventional PI and PR controllers can achieve steady-state error adjustment, but are sensitive to parameter changes and model uncertainty, heavily relying on coordinate transformations and careful design of model parameters. Model predictive control (MPC) has the characteristics of simple design, good robustness, and excellent dynamic response; however, it encountered the complexity of adjusting weighting factors. This paper proposed circulating the current model predictive proportional integral control (MPPIC) method in abc reference frame. This hybrid control solution utilized the predictive model and traditional PI algorithm to combine the advantages of nonlinear and linear control. Compared with existing suppression methods, this method avoided complex mathematical operations and a selection of weight coefficients, was easy to implement, and can effectively suppress circulating currents under different modulation ratios. Simulations were conducted on MATLAB/Simulink to verify the effectiveness of the proposed control strategy. MPPIC can not only distinctly suppress the circulating currents, but also reduce the overall voltage fluctuation of sub-modules capacitors under different modulation ratios, and had almost no any adverse effect on the performance of MMC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.