Land cover is an important variable of the terrestrial ecosystem that provides information for natural resources management, urban sprawl detection, and environment research. To classify land cover with high-spatial-resolution multispectral remote sensing imagery is a difficult problem due to heterogeneous spectral values of the same object on the ground. Fully convolutional networks (FCNs) are a state-of-the-art method that has been increasingly used in image segmentation and classification. However, a systematic quantitative comparison of FCNs on high-spatial-multispectral remote imagery was not yet performed. In this paper, we adopted the three FCNs (FCN-8s, Segnet, and Unet) for Gaofen-2 (GF2) satellite imagery classification. Two scenes of GF2 with a total of 3329 polygon samples were used in the study area and a systematic quantitative comparison of FCNs was conducted with red, green, blue (RGB) and RGB+near infrared (NIR) inputs for GF2 satellite imagery. The results showed that: (1) The FCN methods perform well in land cover classification with GF2 imagery, and yet, different FCNs architectures exhibited different results in mapping accuracy. The FCN-8s model performed best among the Segnet and Unet architectures due to the multiscale feature channels in the upsampling stage. Averaged across the models, the overall accuracy (OA) and Kappa coefficient (Kappa) were 5% and 0.06 higher, respectively, in FCN-8s when compared with the other two models. (2) High-spatial-resolution remote sensing imagery with RGB+NIR bands performed better than RGB input at mapping land cover, and yet the advantage was limited; the OA and Kappa only increased an average of 0.4% and 0.01 in the RGB+NIR bands. (3) The GF2 imagery provided an encouraging result in estimating land cover based on the FCN-8s method, which can be exploited for large-scale land cover mapping in the future.

中文翻译：

---

完全深度卷积神经网络用于土地覆盖分类与高空间分辨率高分2图像的比较

土地覆盖是陆地生态系统的重要变量，可为自然资源管理，城市蔓延探测和环境研究提供信息。由于地面上同一物体的光谱值存在异质性，因此要用高空间分辨率多光谱遥感影像对土地覆盖物进行分类是一个难题。完全卷积网络（FCN）是一种先进的方法，已越来越多地用于图像分割和分类中。但是，尚未对高空间多光谱遥感影像上的FCN进行系统的定量比较。在本文中，我们采用了三个FCN（FCN-8，Segnet和Unet）进行高分2号（GF2）卫星图像分类。在研究区域中使用了两个场景的GF2，共3329个多边形样本，并使用红色，绿色，蓝色（RGB）和RGB +近红外（NIR）输入对GF2卫星图像进行了FCN的系统定量比较。结果表明：（1）FCN方法在用GF2图像进行土地覆盖分类中表现良好，但是，不同的FCN体系结构在制图精度方面表现出不同的结果。由于上采样阶段的多尺度特征通道，FCN-8s模型在Segnet和Unet架构中表现最佳。各个模型的平均值，总体准确性（不同的FCN架构在制图精度方面表现出不同的结果。由于上采样阶段的多尺度特征通道，FCN-8s模型在Segnet和Unet架构中表现最佳。各个模型的平均值，总体准确性（不同的FCN架构在制图精度方面表现出不同的结果。由于上采样阶段的多尺度特征通道，FCN-8s模型在Segnet和Unet架构中表现最佳。各个模型的平均值，总体准确性（与其他两个模型相比，FCN-8s的OA值和Kappa系数（Kappa）分别高5％和0.06。（2）RGB + NIR波段的高空间分辨率遥感影像在制图用地上表现优于RGB输入，但优势有限；的OA和卡伯仅在RGB + NIR谱带增加平均0.4％和0.01。（3）GF2影像在基于FCN-8s方法的土地覆盖率估算中提供了令人鼓舞的结果，将来可用于大规模的土地覆盖图制图。