摘要
针对现有变化检测方法编解码过程中出现的噪声失准、物体边界模糊和小目标变化检测率低等问题,提出了一种变化检测方法HAPNet-CD.该方法编码器采用孪生分支,使用HRNetV2作为骨干网,并在其中嵌入对齐扰动辅助差异模块提取变化特征和差异信息,使提取特征过程中始终保持高分辨率特征表示,进而在空间上得到更精确的特征.HAPNet-CD解码器利用变化特征和差异信息构建混合解码器和差异解码器进行解码,通过设计一种基于标签平滑的损失函数,使网络更加关注物体边界和小目标的变化,提高了物体边界和小目标变化检测准确率.在公开数据集DSIFN-CD和LEVIR-CD上进行测试,实验结果表明,相较于其他9种主流方法,HAPNet-CD在DSIFN-CD数据集上,Precision、Recall、F1和IoU指标分别提升了 2.55％、4.58％、3.59％和 5.9％;在 LEVIR-CD 数据集上,Precision 指标提升了 0.54％,Recall、F1和IoU指标均接近最先进水平.
Abstract
The HAPNet-CD,a new change detection method,is proposed in this paper to solve the problems of noise misalignment,object boundary ambiguity and low change detection rate of small targets in the processes of encoding and decoding with the existing methods.On the one hand,the encoder of HAPNet-CD adopts siamese branches,in which HRNetV2 is used as the backbone network,and the align-ment-and-perturbation-aided difference module is embedded to extract the variation features and difference information.As a result,the high-resolution feature representation can always be maintained in the process of feature extraction,so that the obtained features are more accurate in space.On the other hand,the decoder of HAPNet-CD uses the change features and difference information to construct a hybrid de-coder and a differential decoder for decoding.By designing a loss function based on label smoothing,the network pays more attention to the variations of object boundaries and small targets,so that the change detection accuracy of object boundaries and small targets can be improved.Tests were carried out on the public data sets DSIFN-CD and LEVIR-CD,and the experimental results are as follows.Compared with the other 9 mainstream methods,the HAPNet-CD has improved the metrics of Precision,Recall,F1,and IoU by 2.55％,4.58％,3.59％,and 5.9％,respectively,on the DSIFN-CD dataset.On the LEVIR-CD dataset,the Precision metric is improved by 0.54％,while the metrics of Recall,F,,and IoU are all close to the most advanced level.
NETL
NSTL
万方数据