摘要
提出一种融合Swin Transformer的道路变化检测方法STSNet。首先,该模型以Swin Transformer为主干网络,利用共享权重的双网络结构和窗口自注意力机制,高效地捕捉长程依赖关系。然后,设计梯度感知多尺度特征融合模块,将变化梯度信息与多尺度特征融合,进一步提升模型对全局变化信息的获取能力和对边缘特征的识别能力,从而改善变化目标轮廓模糊的问题。最后,通过尺度感知条带注意力模块自适应融合来自编码器和解码器的特征,对局部信息进行有效整合,降低模型漏检率。采用自制LNTU_RCD_GF和WRCD数据集进行训练测试。结果显示,STSNet变化检测方法在F1值、交并比、召回率上均高于5种对比方法,特别是在小尺度道路变化检测上具有良好的性能。
This study proposes a road-change detection method,STSNet,that integrates the Swin Transformer.First,the model utilizes the Swin Transformer as the backbone network and employs a dual network structure with shared weights and a window self-attention mechanism to efficiently capture long-range dependencies.A gradient-aware multiscale feature fusion module is next designed to merge changing gradient information with the multi-scale features,further enhancing the model’s ability to obtain global change information and recognize edge features,thereby addressing the issue of blurred contours of changing targets.Finally,the scale-aware stripe attention module adaptively integrates features from the encoder and decoder to effectively combine local information and reduce the model’s missed detection rate.This study used the self-made LNTU_SCD_GF and WRCD datasets for training and testing,respectively.The results demonstrate that the STSNet change detection method outperforms five comparative methods in terms of F1 value,intersection ratio,and recall,particularly excelling in small-scale road-change detection.
作者
贾雪婷
宋伟东
孙尚宇
Jia Xueting;Song Weidong;Sun Shangyu(School of Geomatics,Mapping and Geoscience,Liaoning University of Engineering and Technology,Fuxin 123000,Liaoning,China;Collaborative Innovation Research Institute of Geospatial Information Service,Liaoning University of Engineering and Technology,Fuxin 123000,Liaoning,China)
出处
《激光与光电子学进展》
北大核心
2025年第10期337-347,共11页
Laser & Optoelectronics Progress
基金
国家自然科学基金(42071343)。
