Deep Relearning in the Geospatial Domain for Semantic Remote Sensing Image Segmentation
Deep Relearning in the Geospatial Domain for Semantic Remote Sensing Image Segmentation
复制标题
地理空间领域的深度再学习用于语义遥感图像分割
DOI：
10.1109/lgrs.2020.3031339
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
H. Taubenböck
中科院分区：
文献类型：
--
作者：
C. Geiss;Yue Zhu;C. Qiu;Lichao Mou;Xiaoxiang Zhu;H. Taubenböck
我们提出了一种基于全卷积神经网络（CNN）的分类后处理（CPP）技术，用于语义遥感图像分割。传统的CPP技术旨在通过在图像域施加平滑先验来提高分类精度。与此相反，这里提出了一种再学习策略，即通过扩展输入空间将CNN模型的初始分类结果提供给后续的CNN模型，以端到端的方式引导判别性特征表示的学习。这种深度再学习CNN（DRCNN）通过考虑初步类别标签的空间对齐，明确考虑了地理空间域。在此，我们评估以累积和非累积的方式学习DRCNN，即在迭代过程中，分别基于所有先前的或仅基于前一个模型的输出扩展输入空间。此外，DRCNN还可以方便地与其他CPP技术（如基于对象的投票（OBV））相结合。从WorldView - II影像的两个测试地点获得的实验结果突显了DRCNN模型的良好性能。就$\kappa$统计量而言，它们可以将初始CNN模型的准确率从平均72.64%提高到76.01%，从92.43%提高到94.52%。当将DRCNN模型与OBV策略相结合时，还可以额外提高1.65和2.84个百分点。从认识论的角度来看，我们的结果强调CNN可以从考虑初步模型结果中受益，并且传统的CPP技术可以从上游再学习策略中获益。
We present a classification postprocessing (CPP) technique based on fully convolutional neural networks (CNNs) for semantic remote sensing image segmentation. Conventional CPP techniques aim to enhance the classification accuracy by imposing smoothness priors in the image domain. Contrary to that, here, a relearning strategy is proposed where the initial classification outcome of a CNN model is provided to a subsequent CNN model via an extended input space to guide the learning of discriminative feature representations in an end-to-end fashion. This deep relearning CNN (DRCNN) explicitly accounts for the geospatial domain by taking the spatial alignment of preliminary class labels into account. Hereby, we evaluate to learn the DRCNN in a cumulative and noncumulative way, i.e., extending the input space based on all previous or solely preceding model outputs, respectively, during an iterative procedure. Besides, the DRCNN can also be conveniently coupled with alternative CPP techniques such as object-based voting (OBV). The experimental results obtained from two test sites of WorldView-II imagery underline the beneficial performance properties of the DRCNN models. They can increase the accuracies of the initial CNN models on average from 72.64% to 76.01% and from 92.43% to 94.52% in terms of $\kappa $ statistic. An additional increase of 1.65 and 2.84 percentage points can be achieved when combining the DRCNN models with an OBV strategy. From an epistemological point of view, our results underline that CNNs can benefit from the consideration of preliminary model outcomes and that conventional CPP techniques can profit from an upstream relearning strategy.