Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
复制标题
DOI：
--
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Jamie Sherrah
中科院分区：
文献类型：
--
作者：
Jamie Sherrah
朝向更高分辨率遥感图像的趋势促进了从土地使用分类向物体一级场景理解的过渡。而不是纯粹依赖于光谱内容，基于外观的图像特征发挥作用。在这项工作中，深度卷积神经网络（CNN）被应用于高分辨率遥感数据的语义标记。全卷积网络（FCN）的最新进展适用于开销数据，并与其他领域一样有效。使用深度FCN推断全分辨率标记，无需下采样，从而无需反卷积或插值。为了更好地利用图像特征，预先训练的CNN在混合网络环境中对遥感数据进行了微调，与从头开始训练的网络相比，结果上级。所提出的方法适用于高分辨率航空影像，精细的边界细节是很重要的标签的问题。密集的标签产生了ISPRS Vaihingen和波茨坦基准数据集的最先进的准确性。
The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding. Rather than relying purely on spectral content, appearance-based image features come into play. In this work, deep convolutional neural networks (CNNs) are applied to semantic labelling of high-resolution remote sensing data. Recent advances in fully convolutional networks (FCNs) are adapted to overhead data and shown to be as effective as in other domains. A full-resolution labelling is inferred using a deep FCN with no downsampling, obviating the need for deconvolution or interpolation. To make better use of image features, a pre-trained CNN is fine-tuned on remote sensing data in a hybrid network context, resulting in superior results compared to a network trained from scratch. The proposed approach is applied to the problem of labelling high-resolution aerial imagery, where fine boundary detail is important. The dense labelling yields state-of-the-art accuracy for the ISPRS Vaihingen and Potsdam benchmark data sets.