用于遥感图像变化检测的全尺度特征聚合网络

A full-scale feature aggregation network for remote sensing image change detection

变化检测(CD)是遥感的一项重要任务,通常面临许多伪变化和较大的尺度变化。目前的方法主要侧重于对差异特征的建模,忽略了从原始图像中提取足够的信息,影响了特征的识别能力,难以稳定地区分出变化区域。针对以上问题,提出了一种全尺度特征聚合网络(FFANet)来更充分地利用原始图像特征,促使生成的特征表示在语义上更丰富、在空间上更准确,从而提高了网络对小目标和目标边缘的检测性能。同时,拓展了深监督来结合多尺度的预测图,以促使不同对象在更合适的尺度上进行检测,从而提升了网络对对象尺度变化的鲁棒性。在CDD数据集上,相比于基线网络,所提方法仅增加了1.01×10~6的参数量,就将F分数提升了0.034。

Change detection(CD)is an important task of remote sensing,always facing many pseudo changes and large scale variations.However,existing methods mainly focus on modeling difference features and neglect extracting sufficient information from the original images,which affects feature discrimination and makes it difficult to distinguish change regions stably.To address these problems,a full-scale feature aggregation network(FFANet)is proposed to make fuller use of the original image features,which drives the generated feature representations to be semantically richer and spatially more precise,thus improving the network’s detection performance for small targets and target edges.Deep supervision is also extended to combine multi-scale prediction maps to drive the detection of different objects at more appropriate scales,thus improving the robustness of the network to object scale variations.On the CDD dataset,our proposed method improves the F-score by 0.034 compared to the baseline network by increasing the number of parameters by only 1.01×10~6.