A Spatiotemporal Fusion Method Based on Multiscale Feature Extraction and Spatial Channel Attention Mechanism

Lei, Dajiang; Ran, Gangsheng; Zhang, Liping; Li, Weisheng

doi:10.3390/rs14030461

Cited by 20 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a kind of human landscape, the urban garden landscape is a complex natural landscape and artificial landscape. To achieve the ideal realm of “living in a poetic place,” the ideal realm of “original” urban landscape must be carried out, and an “original” urban landscape design must be carried out to maximize the value of the landscape [ 3 ]. Under the background of advocating a conservation-oriented society and a harmonious society, both urban landscape and small and medium-sized town landscape construction should take regionality as the most basic principle and explore the design methods of preserving culture, continuing history, and saving resources.…”

Section: Introductionmentioning

confidence: 99%

Urban Landscaping Landscape Design and Maintenance Management Method Based on Multisource Big Data Fusion

Zhu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the process of continuous urbanization construction, the construction scale of urban landscaping projects is getting larger. At the same time, the design and the maintenance of the management is becoming more important. Recently, the rocketing development of the ternary world of many people, machines, and things has triggered the generation of multisource fusion data and the development of artificial intelligence technology, and the world has entered the era of multisource big data intelligence. Multisource data refer to the fusion of multiple types of data with effective characteristic information, which has richer, more comprehensive, more detailed, and more effective information than a single data source, and can provide high-quality data sources for various complex problems. Therefore, more effective data can be provided for the definition of urban fringe areas. From the moment Google’s AlphaGo defeated Go world champion Li Shishi, the chess game has been occupied by AI, setting off an upsurge in the study, research, and application of AI technology. Colleges and universities around the world have followed suit and set up AI-related majors. Deep learning is one of the cutting-edge technologies in the field of artificial intelligence. It is a method to solve complex real-life problems by extracting effective information from the data and mining key features on the basis of a large amount of learning and computing data.

show abstract

Section: Introductionmentioning

confidence: 99%

Urban Landscaping Landscape Design and Maintenance Management Method Based on Multisource Big Data Fusion

Zhu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Attention mechanisms can ignore certain irrelevant regional information and focus on the key areas in the image through learning. Different from other methods, the proposed DMRFAB module includes a dense multi-receptive field module both introducing SAM 21 and CAM 22 , which helps multi- receptive field blocks better extract deep feature information, improve feature representation capabilities, and ultimately improve module deblurring performance. The DMRFAB module, illustrated in Fig.…”

Section: The Proposed Methodsmentioning

confidence: 99%

An image deblurring method using improved U-Net model based on multilayer fusion and attention mechanism

Lian,

Wang

2023

Sci Rep

View full text Add to dashboard Cite

The investigation of image deblurring techniques in dynamic scenes represents a prominent area of research. Recently, deep learning technology has gained extensive traction within the field of image deblurring methodologies. However, such methods often suffer from limited inherent interconnections across various hierarchical levels, resulting in inadequate receptive fields and suboptimal deblurring outcomes. In U-Net, a more adaptable approach is employed, integrating diverse levels of features effectively. Such design not only significantly reduces the number of parameters but also maintains an acceptable accuracy range. Based on such advantages, an improved U-Net model for enhancing the image deblurring effect was proposed in the present study. Firstly, the model structure was designed, incorporating two key components: the MLFF (multilayer feature fusion) module and the DMRFAB (dense multi-receptive field attention block). The aim of these modules is to improve the feature extraction ability. The MLFF module facilitates the integration of feature information across various layers, while the DMRFAB module, enriched with an attention mechanism, extracts crucial and intricate image details, thereby enhancing the overall information extraction process. Finally, in combination with fast Fourier transform, the FRLF (Frequency Reconstruction Loss Function) was proposed. The FRLF obtains the frequency value of the image by reducing the frequency difference. The present experiment results reveal that the proposed method exhibited higher-quality visual effects. Specifically, for the GoPro dataset, the PSNR (peak signal-to-noise ratio) reached 31.53, while the SSIM (structural similarity index) attained a value of 0.948. Additionally, for the Real Blur dataset, the PSNR achieved 31.32, accompanied by an SSIM score of 0.934.

show abstract

“…CNNs have been applied to spatiotemporal image fusion deep learning methods [28,29], and the fusion performance has been improved. The deep CNN for spatiotemporal fusion (STFDCNN) [30] reconstructs spatial resolution images from temporal resolution images using a spatiotemporal fusion method involving deep CNNs; notably, nonlinear mapping super-resolution-based CNNs are less efficient than the sparse representation method.…”

Section: Related Workmentioning

confidence: 99%

STF-EGFA: A Remote Sensing Spatiotemporal Fusion Network with Edge-Guided Feature Attention

Fang

Tang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Spatiotemporal fusion in remote sensing plays an important role in Earth science applications by using information complementarity between different remote sensing data to improve image performance. However, several problems still exist, such as edge contour blurring and uneven pixels between the predicted image and the real ground image, in the extraction of salient features by convolutional neural networks (CNNs). We propose a spatiotemporal fusion method with edge-guided feature attention based on remote sensing, called STF-EGFA. First, an edge extraction module is used to maintain edge details, which effectively solves the boundary blurring problem. Second, a feature fusion attention module is used to make adaptive adjustments to the extracted features. Among them, the spatial attention mechanism is used to solve the problem of weight variation in different channels of the network. Additionally, the problem of uneven pixel distribution is addressed with a pixel attention (PA) mechanism to highlight the salient features. We transmit the different features extracted by the edge module and the encoder to the feature attention (FA) module at the same time after the union. Furthermore, the weights of edges, pixels, channels and other features are adaptively learned. Finally, three remote sensing spatiotemporal fusion datasets, Ar Horqin Banner (AHB), Daxing and Tianjin, are used to verify the method. Experiments proved that the proposed method outperformed three typical comparison methods in terms of the overall visual effect and five objective evaluation indexes: spectral angle mapper (SAM), peak signal-to-noise ratio (PSNR), spatial correlation coefficient (SCC), structural similarity (SSIM) and root mean square error (RMSE). Thus, the proposed spatiotemporal fusion algorithm is feasible for remote sensing analysis.

show abstract

A Spatiotemporal Fusion Method Based on Multiscale Feature Extraction and Spatial Channel Attention Mechanism

Cited by 20 publications

References 47 publications

Urban Landscaping Landscape Design and Maintenance Management Method Based on Multisource Big Data Fusion

Urban Landscaping Landscape Design and Maintenance Management Method Based on Multisource Big Data Fusion

An image deblurring method using improved U-Net model based on multilayer fusion and attention mechanism

STF-EGFA: A Remote Sensing Spatiotemporal Fusion Network with Edge-Guided Feature Attention

Contact Info

Product

Resources

About