电讯技术2025，Vol.65Issue(9)：1404-1412,9.DOI:10.20079/j.issn.1001-893x.240401004
一种面向星载的遥感图像场景分类域泛化算法
A Satellite-oriented Domain Generalization Algorithm for Remote Sensing Image Scene Classification
摘要
Abstract
To address the problems of existing remote sensing image scene classification algorithms handling single data types and the lack of on-board deployment studies,the domain generalization algorithm is applied to multimodal remote sensing image scene classification tasks.A scene classification algorithm with task-relevant feature weighting is proposed and deployment and testing on Commercial Off-The-Shelf(COTS)devices is carried out.The algorithm weights the features extracted from the backbone network based on the channel and spatial attention mechanism to enhance the task-relevant features.Additionally,the decoder module is introduced to reconstruct the high-frequency features of the image,which assists in the training process and enhances the learning of task-related features.The above improvements can enhance the model's learning of cross-domain invariant features and improve the model's generalization ability.Experimental results demonstrate that the proposed algorithm achieves a cross-domain average classification accuracy of 82.95%,surpassing five comparative algorithms including ERM,MixStyle,V-Rex,POEM,and SNSC by a margin of at least 3.09%.Furthermore,the algorithm's deployment on COTS devices using TensorRT demonstrates an execution speed of over 200 frames per second with an overall device power consumption of 7 W,which meets the requirements for on-orbit applications.关键词
遥感图像/场景分类/域泛化/在轨部署/COTS器件Key words
remote sensing image/scene classification/domain generalization/on-orbit deployment/COTS device分类
信息技术与安全科学引用本文复制引用
杜安安,周晴..一种面向星载的遥感图像场景分类域泛化算法[J].电讯技术,2025,65(9):1404-1412,9.基金项目
中国科学院空间科学战略性科技先导专项基金(XDA04060300) （XDA04060300）
