融合自注意力机制与生成对抗网络的DEM空洞填充

Void Filling of DEM in a Generative Adversarial Network Fused with Self-Attention Mechanism

针对现有数字高程模型(digital elevation model, DEM)数据空洞填充算法存在修复效果不连续、适用空值范围狭小以及细节重构丢失等问题,提出了一种融合自注意力机制的生成式对抗网络的DEM空洞填充方法。首先,构造自注意力机制提取DEM数据特征信息,改善DEM空洞填充结果高程值不连续和纹理细节缺失的问题。其次,在生成器中使用对称结构的卷积与反卷积网络结构,保证生成可靠度较高的数据以实现空洞区域填充,并利用判别器实现空洞填充结果的预分类。最后,结合重构损失函数进行训练,提升DEM空洞填充结果对异常值的鲁棒性,增强模型的回归能力。采用不同分辨率DEM数据进行空洞填充并与现有方法进行对比,结果表明:所提方法能够大幅提升填充精度,有效解决原始数据中存在的空洞问题。

Aiming at the problems of existing DEM data void filling algorithms,such as discontinuous repair effect,narrow applicable null value range and loss of detail reconstruc-tion,this paper proposes a DEM void flling method integrating self-attention mechanism with generative adjunctive network.Firstly,a self-attention mechanism is constructed to extract DEM data feature information to improve the elevation discontinuity and texture detail loss of DEM cavity filling results.Secondly,symmetric convolutional and deconvolu-tion network structures are used in the generator to ensure the generation of high reliability data to realize the flling of the void region,and the discriminator is used to realize the pre-classification of the flling results.Finally,combined with the reconstruction of loss function and the generation of adversarial loss function,the network training was carried out to improve the robustness of DEM cavity filling results to outliers and enhance the regression ability of the model.The experimental results show that compared with the flling results of spatial interpolation and deep learning,the proposed method can greatly improve the flling accuracy and effectively solve the problems of holes in the original data.