红外与毫米波学报2025，Vol.44Issue(2)：265-276,12.DOI:10.11972/j.issn.1001-9014.2025.02.014
融合密集连接与多注意力机制的星载红外遥感图像超分辨率网络
Infrared remote sensing image super-resolution network by integration of dense connection and multi-attention mechanism
摘要
Abstract
Space-borne infrared remote sensing images have significant applications in environmental monitoring and military reconnaissance.Nonetheless,due to technological limitations,atmospheric disturbances,and sensor noise,these images suffer from insufficient resolution and blurred texture details,severely restricting the accuracy of subse-quent analysis and processing.To address these issues,a new super-resolution generative adversarial network model is proposed.This model integrates dense connections with the Swin Transformer architecture to achieve effective cross-lay-er feature transmission and contextual information utilization while enhancing the model's global feature extraction capa-bilities.Furthermore,the traditional residual connection is improved with multi-scale channel attention-based feature fu-sion,allowing the network to more flexibly integrate multi-scale features,thereby enhancing the quality and efficiency of feature fusion.A joint loss function is constructed to comprehensively optimize the performance of the generator.Com-parative tests on different datasets demonstrate significant improvements with the proposed algorithm.Furthermore,the super-resolved images exhibit higher performance in downstream tasks such as object detection,confirming the effective-ness and application potential of the algorithm in space-borne infrared remote sensing image super-resolution.关键词
星载红外遥感/超分辨率重建/注意力机制/生成对抗网络/联合损失函数Key words
space-borne infrared remote sensing/super-resolution/attention mechanism/generative adversarial network/joint loss分类
信息技术与安全科学引用本文复制引用
徐新昊,王俊,王峰,孙胜利..融合密集连接与多注意力机制的星载红外遥感图像超分辨率网络[J].红外与毫米波学报,2025,44(2):265-276,12.基金项目
国家自然科学基金(61991421)Supported by the National Natural Science Foundation of China(61991421) （61991421）
