NSTL国家科技图书文献中心

1. Infrared and visible image fusion using quantum computing induced edge preserving filter NSTL国家科技图书文献中心

Parida P. | Panda M.K.... - 《Image and vision computing》 - 2025,153(Jan.) - 1.1～1.16 - 共16页

摘要： source images efficiently. Initially, the proposed edge | detail preserving strategy is capable of retaining the | © 2024 Elsevier B.V.Information fusion by | utilization of visible and thermal images provides a more | comprehensive scene understanding in the resulting image

关键词： Edge detail | Image fusion | Infrared | Quantum computing | Visible | Weight map

2. MSDFNet: multi-scale detail feature fusion encoder-decoder network for self-supervised monocular thermal image depth estimation NSTL国家科技图书文献中心

Kong, Lingjun | Zheng, Qianhui ... - 《Measurement Science & Technology》 - 2025,36(1) - 1～17 - 共17页

摘要：-scale detail* feature fusion encoder-decoder network* | a detail* feature weight evaluation decoder to fuse* | each feature, thereby emphasizing critical edge | Currently available thermal image depth | estimation methods are difficult to efficiently extract

关键词： multi-scale features | edge detail | encoder-decoder | thermal image depth estimation

3. Edge Feature Enhanced Transformer Network for RGB and infrared image fusion based detection NSTL国家科技图书文献中心

Zhao, Genping | Zhu, JiaSheng ... - 《Infrared physics and technology》 - 2025,147 - 共10页

摘要： approaches have limitation in local edge* detail learning* | , resulting in challenges like missed detection of edge | , an efficient Edge* Feature Enhanced Transformer* | -stream backbone transformer-based framework. Edge | Compared to RGB imaging, synchronous RGB and

关键词： Object detection | Image fusion | Multi-modality | Machine learning

4. Assessing China’s Hillside Urban Expansion and Its Urban Thermal Environmental Impacts Using Multisource Data NSTL国家科技图书文献中心

Junru Wang | Linlin Jiang ... - 《IEEE geoscience and remote sensing letters》 - 2025,22 - 1～5 - 共5页

摘要：, the identified HUE exhibits stronger edge detail | Global urban expansion presents a clear upward | trend, reshaping urban socioeconomic frameworks and | environmental dynamics. This study developed a multisource | classification framework to accurately identify hillside urban

关键词： Urban areas | Land surface | Land surface temperature | Socioeconomics | Spatial resolution | Remote sensing | Normalized difference vegetation index | Spatiotemporal phenomena | Soft sensors | Market research

5. CS U-NET: A Medical Image Segmentation Method Integrating Spatial and Contextual Attention Mechanisms Based on U-NET NSTL国家科技图书文献中心

Zhang Fanyang | Zhang Fan - 《International journal of imaging systems and technology》 - 2025,35(2) - e70072.1～e70072.10 - 共10页

摘要： improvements in prediction accuracy and edge detail | Medical image segmentation is a crucial | process in medical image analysis, with convolutional | neural network (CNN)-based methods achieving notable | success in recent years. Among these, U-Net has gained

关键词： CBAM | deep learning | medical image segmentation | Swin transformer | U-net

6. A Survey of Edge Caching Security: Framework, Methods, and Challenges NSTL国家科技图书文献中心

Zhang, Hang | Wang, Jinsong ... - 《Journal of systems architecture》 - 2025,158 - 共23页

摘要：Edge caching reduces the frequent | caching popular content at the network edge, which can | experience. However, the openness and vulnerability of edge | research work on edge* caching security only focuses on* | certain specific aspects and does not consider edge

关键词： Edge computing | Edge caching | Caching model | Security framework

7. A Road-Detail Preserving Framework for Urban Road Extraction From VHR Remote Sensing Imagery NSTL国家科技图书文献中心

Ziye Wang | Zheng Luo ... - 《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1～13 - 共13页

摘要： edge-constrained branch with a detail preservation | . In addition, the edge* is important topological* | results. Therefore, the Road-detail* Preserving Mapper* | reconstruct critical road detail* information. Second, a road* | Automatic road extraction has gained

关键词： Roads | Feature extraction | Transformers | Data mining | Image edge detection | Decoding | Convolution | Remote sensing | Sensors | Accuracy

8. CSCT: Channel–Spatial Coherent Transformer for Remote Sensing Image Super-Resolution NSTL国家科技图书文献中心

Kexin Zhang | Lingling Li ... - 《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1～14 - 共14页

摘要： restoring and preserving edge* and detail information are a* | ), which work synergistically to enhance edge and detail | that our approach excels in detail* restoration* | Remote sensing image super-resolution (RSISR | ) techniques are crucial in practice as an economical

关键词： Superresolution | Remote sensing | Image edge detection | Transformers | Frequency-domain analysis | Spatial resolution | Sensors | Image restoration | Attention mechanisms | Training

9. EBcGAN: An Edge-Based Conditional Generative Adversarial Network for Image Fusion NSTL国家科技图书文献中心

Mengshu Li | Zheyuan Yang ... - 《Knowledge Management and Acquisition for Intelligent Systems》 - Pacific Rim Knowledge Acquisition Workshop | Pacific Rim International Conference on Artificial Intelligence - 2025, - 120～135 - 共16页

摘要： challenges such as inadequate texture and thermal detail | discriminators. We perform edge* loss calculation on the* | structural details, enhances edge* sharpness, and* | accuracy in image fusion, better edge* and boundary* | Infrared and visible image fusion aims to

关键词： Image fusion | Generative adversarial network | Infrared image

10. High dynamic range image tone mapping based on variational image decomposition and color correction NSTL国家科技图书文献中心

Yang, Xuejie | Zheng, Huamiao ... - 《Optics & Laser Technology》 - 2025,181(Pt.B) - 共19页

摘要： detail layers and process them accordingly. Since the | detail layer is not refined again, these algorithms may | texture component, and a high-frequency detail* component* | function, while the texture and high-frequency detail | functions. This approach allows for better detail

摘要： source images efficiently. Initially, the proposed edge | detail preserving strategy is capable of retaining the | © 2024 Elsevier B.V.Information fusion by | utilization of visible and thermal images provides a more | comprehensive scene understanding in the resulting image

关键词： Edge detail | Image fusion | Infrared | Quantum computing | Visible | Weight map

摘要：-scale detail* feature fusion encoder-decoder network* | a detail* feature weight evaluation decoder to fuse* | each feature, thereby emphasizing critical edge | Currently available thermal image depth | estimation methods are difficult to efficiently extract

关键词： multi-scale features | edge detail | encoder-decoder | thermal image depth estimation

摘要： approaches have limitation in local edge* detail learning* | , resulting in challenges like missed detection of edge | , an efficient Edge* Feature Enhanced Transformer* | -stream backbone transformer-based framework. Edge | Compared to RGB imaging, synchronous RGB and

关键词： Object detection | Image fusion | Multi-modality | Machine learning

摘要：, the identified HUE exhibits stronger edge detail | Global urban expansion presents a clear upward | trend, reshaping urban socioeconomic frameworks and | environmental dynamics. This study developed a multisource | classification framework to accurately identify hillside urban

关键词： Urban areas | Land surface | Land surface temperature | Socioeconomics | Spatial resolution | Remote sensing | Normalized difference vegetation index | Spatiotemporal phenomena | Soft sensors | Market research

摘要： improvements in prediction accuracy and edge detail | Medical image segmentation is a crucial | process in medical image analysis, with convolutional | neural network (CNN)-based methods achieving notable | success in recent years. Among these, U-Net has gained

关键词： CBAM | deep learning | medical image segmentation | Swin transformer | U-net

摘要：Edge caching reduces the frequent | caching popular content at the network edge, which can | experience. However, the openness and vulnerability of edge | research work on edge* caching security only focuses on* | certain specific aspects and does not consider edge

关键词： Edge computing | Edge caching | Caching model | Security framework

摘要： edge-constrained branch with a detail preservation | . In addition, the edge* is important topological* | results. Therefore, the Road-detail* Preserving Mapper* | reconstruct critical road detail* information. Second, a road* | Automatic road extraction has gained

关键词： Roads | Feature extraction | Transformers | Data mining | Image edge detection | Decoding | Convolution | Remote sensing | Sensors | Accuracy

摘要： restoring and preserving edge* and detail information are a* | ), which work synergistically to enhance edge and detail | that our approach excels in detail* restoration* | Remote sensing image super-resolution (RSISR | ) techniques are crucial in practice as an economical

关键词： Superresolution | Remote sensing | Image edge detection | Transformers | Frequency-domain analysis | Spatial resolution | Sensors | Image restoration | Attention mechanisms | Training

摘要： challenges such as inadequate texture and thermal detail | discriminators. We perform edge* loss calculation on the* | structural details, enhances edge* sharpness, and* | accuracy in image fusion, better edge* and boundary* | Infrared and visible image fusion aims to

关键词： Image fusion | Generative adversarial network | Infrared image

摘要： detail layers and process them accordingly. Since the | detail layer is not refined again, these algorithms may | texture component, and a high-frequency detail* component* | function, while the texture and high-frequency detail | functions. This approach allows for better detail

关键词： HDR Image processing | Tone mapping | Variational image decomposition | Color correction

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： source images efficiently. Initially, the proposed edge | detail preserving strategy is capable of retaining the | © 2024 Elsevier B.V.Information fusion by | utilization of visible and thermal images provides a more | comprehensive scene understanding in the resulting image

关键词： Edge detail | Image fusion | Infrared | Quantum computing | Visible | Weight map

摘要：-scale detail feature fusion encoder-decoder network | a detail feature weight evaluation decoder to fuse | each feature, thereby emphasizing critical edge | Currently available thermal image depth | estimation methods are difficult to efficiently extract

关键词： multi-scale features | edge detail | encoder-decoder | thermal image depth estimation

摘要： approaches have limitation in local edge detail learning | , resulting in challenges like missed detection of edge | , an efficient Edge Feature Enhanced Transformer | -stream backbone transformer-based framework. Edge | Compared to RGB imaging, synchronous RGB and

关键词： Object detection | Image fusion | Multi-modality | Machine learning

摘要：, the identified HUE exhibits stronger edge detail | Global urban expansion presents a clear upward | trend, reshaping urban socioeconomic frameworks and | environmental dynamics. This study developed a multisource | classification framework to accurately identify hillside urban

关键词： Urban areas | Land surface | Land surface temperature | Socioeconomics | Spatial resolution | Remote sensing | Normalized difference vegetation index | Spatiotemporal phenomena | Soft sensors | Market research

摘要： improvements in prediction accuracy and edge detail | Medical image segmentation is a crucial | process in medical image analysis, with convolutional | neural network (CNN)-based methods achieving notable | success in recent years. Among these, U-Net has gained

关键词： CBAM | deep learning | medical image segmentation | Swin transformer | U-net

摘要：Edge caching reduces the frequent | caching popular content at the network edge, which can | experience. However, the openness and vulnerability of edge | research work on edge caching security only focuses on | certain specific aspects and does not consider edge

关键词： Edge computing | Edge caching | Caching model | Security framework

摘要： edge-constrained branch with a detail preservation | . In addition, the edge is important topological | results. Therefore, the Road-detail Preserving Mapper | reconstruct critical road detail information. Second, a road | Automatic road extraction has gained

关键词： Roads | Feature extraction | Transformers | Data mining | Image edge detection | Decoding | Convolution | Remote sensing | Sensors | Accuracy

摘要： restoring and preserving edge and detail information are a | ), which work synergistically to enhance edge and detail | that our approach excels in detail restoration | Remote sensing image super-resolution (RSISR | ) techniques are crucial in practice as an economical

关键词： Superresolution | Remote sensing | Image edge detection | Transformers | Frequency-domain analysis | Spatial resolution | Sensors | Image restoration | Attention mechanisms | Training

摘要： challenges such as inadequate texture and thermal detail | discriminators. We perform edge loss calculation on the | structural details, enhances edge sharpness, and | accuracy in image fusion, better edge and boundary | Infrared and visible image fusion aims to

关键词： Image fusion | Generative adversarial network | Infrared image

摘要： detail layers and process them accordingly. Since the | detail layer is not refined again, these algorithms may | texture component, and a high-frequency detail component | function, while the texture and high-frequency detail | functions. This approach allows for better detail

关键词： HDR Image processing | Tone mapping | Variational image decomposition | Color correction

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：-scale detail* feature fusion encoder-decoder network* | a detail* feature weight evaluation decoder to fuse* | each feature, thereby emphasizing critical edge | Currently available thermal image depth | estimation methods are difficult to efficiently extract

摘要： approaches have limitation in local edge* detail learning* | , resulting in challenges like missed detection of edge | , an efficient Edge* Feature Enhanced Transformer* | -stream backbone transformer-based framework. Edge | Compared to RGB imaging, synchronous RGB and

摘要：Edge caching reduces the frequent | caching popular content at the network edge, which can | experience. However, the openness and vulnerability of edge | research work on edge* caching security only focuses on* | certain specific aspects and does not consider edge

摘要： edge-constrained branch with a detail preservation | . In addition, the edge* is important topological* | results. Therefore, the Road-detail* Preserving Mapper* | reconstruct critical road detail* information. Second, a road* | Automatic road extraction has gained

摘要： restoring and preserving edge* and detail information are a* | ), which work synergistically to enhance edge and detail | that our approach excels in detail* restoration* | Remote sensing image super-resolution (RSISR | ) techniques are crucial in practice as an economical

摘要： challenges such as inadequate texture and thermal detail | discriminators. We perform edge* loss calculation on the* | structural details, enhances edge* sharpness, and* | accuracy in image fusion, better edge* and boundary* | Infrared and visible image fusion aims to

摘要： detail layers and process them accordingly. Since the | detail layer is not refined again, these algorithms may | texture component, and a high-frequency detail* component* | function, while the texture and high-frequency detail | functions. This approach allows for better detail