Yang Junjie, Wan Haibo, Shang Zhihai
School of Geographical Sciences, Lingnan Normal University, Zhanjiang, 524048, China.
Sci Rep. 2025 Mar 24;15(1):10161. doi: 10.1038/s41598-025-94544-7.
Remote sensing (RS) change detection incurs a high cost because of false negatives, which are more costly than false positives. Existing frameworks, struggling to improve the Precision metric to reduce the cost of false positive, still have limitations in focusing on the change of interest, which leads to missed detections and discontinuity issues. This work tackles these issues by enhancing feature learning capabilities and integrating the frequency components of feature information, with a strategy to incrementally boost the Recall value. We propose an enhanced hybrid of CNN and Transformer network (EHCTNet) for effectively mining the change information of interest. Firstly, a dual branch feature extraction module is used to extract the multi-scale features of RS images. Secondly, the frequency component of these features is exploited by a refined module I. Thirdly, an enhanced token mining module based on the Kolmogorov-Arnold Network is utilized to derive semantic information. Finally, the semantic change information's frequency component, beneficial for final detection, is mined from the refined module II. Extensive experiments validate the effectiveness of EHCTNet in comprehending complex changes of interest. The visualization outcomes show that EHCTNet detects more intact and continuous changed areas and perceives more accurate neighboring distinction than state-of-the-art models.
由于存在假阴性，遥感（RS）变化检测成本高昂，而假阴性的成本比假阳性更高。现有的框架在努力提高精确率指标以降低假阳性成本时，在关注感兴趣的变化方面仍存在局限性，这导致了漏检和不连续问题。这项工作通过增强特征学习能力和整合特征信息的频率成分来解决这些问题，并采用一种策略逐步提高召回率值。我们提出了一种增强的卷积神经网络（CNN）与Transformer网络的混合网络（EHCTNet），用于有效地挖掘感兴趣的变化信息。首先，使用双分支特征提取模块来提取RS图像的多尺度特征。其次，通过一个细化模块I来利用这些特征的频率成分。第三，利用基于柯尔莫哥洛夫 - 阿诺德网络的增强令牌挖掘模块来推导语义信息。最后，从细化模块II中挖掘出对最终检测有益的语义变化信息的频率成分。大量实验验证了EHCTNet在理解复杂感兴趣变化方面的有效性。可视化结果表明，与现有最先进的模型相比，EHCTNet能检测到更完整、连续的变化区域，并能感知到更准确的相邻差异。
