基于波段-位置自适应选择的多光谱遥感图像语义分割

Semantic Segmentation of Multispectral Remote Sensing Images Based on Band-Location Adaptive Selection

多光谱遥感图像(MSIs)包含大量的地物信息,这些信息蕴含在图像的多个光谱波段中。不同波段或者同一波段不同空间位置所含信息量差异很大,如何从MSIs中捕获有效信息是遥感图像语义分割中一项具有挑战性的任务。基于此,提出一种基于波段-位置自适应选择的端到端语义分割网络(BLASeNet)。所提网络采用编码器-解码器结构,在编码阶段,提出波段-位置自适应选择机制来自适应学习不同波段和同一波段不同空间位置权重,增强有效特征表达。为了利用MSIs的波段相关性,进一步提出三维残差块编码图像的光谱-空间特征。在解码阶段,提出自适应特征融合模块,通过网络学习自适应调整低级细节特征与高级语义特征的融合比例,并探究加法(BLASeNet-A)、元素乘法(BLASeNet-M)和串联(BLASeNet-C)等3种融合策略对模型性能增益的影响。此外,将通道注意力扩展到三维数据上,对融合后的特征图在通道维度上进行特征重标定,得到更准确的多级交互特征图。在ISPRS Potsdam、Qinghai和Tibet Plateau等3个数据集上的实验结果证明了BLASeNet的有效性。

Multispectral remote sensing images(MSIs)provide a substantial amount of ground object information spread over various spectral bands of the image.The quantity of information contained in different bands or different spatial locations within the same band varies significantly.How to capture useful information from MSIs is a challenging task in semantic segmentation of remote sensing images.An end-to-end semantic segmentation network(BLASeNet)based on band-location adaptive selection is proposed here.The proposed network adopts an encoder-decoder structure.In the coding phase,a band-location adaptive selection mechanism is proposed to adaptively learn the weights of different bands and different spatial locations within the same band,enhancing the effective features expression.The spectral-spatial features of 3D residual block-coded images are further proposed to make use of the band correlation of MSIs.During the decoding phase,an adaptive feature fusion module is proposed to adaptively adjust the fusion ratio of low-level detail features and high-level semantic features via network learning,as well as investigate the impact of three fusion strategies,namely,addition(BLASeNet-A),element multiplication(BLASeNet-M),and concatenation(BLASeNet-C),on the model’s performance gain.Furthermore,channel attention is extended to 3D data,and the fused feature map is recalibrated on the channel dimension to produce a more accurate multi-level interactive feature map.The effectiveness of BLASeNet has been demonstrated by experimental results on ISPRS Potsdam,Qinghai and Tibet Plateau datasets.