Patch-based deep learning architectures for sparse annotated very high resolution datasets
Patch-based deep learning architectures for sparse annotated very high resolution datasets
复制标题
DOI：
10.1109/jurse.2017.7924538
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
M. Papadomanolaki;M. Vakalopoulou;K. Karantzalos
中科院分区：
文献类型：
--
作者：
M. Papadomanolaki;M. Vakalopoulou;K. Karantzalos
在本文中，我们比较了基于补丁的框架下不同深度学习架构的性能，用于从非常高分辨率的图像中对稀疏注释的城市场景进行语义标记。特别是，简单的卷积网络ConvNet，AlexNet和VGG模型已经在公开的，多光谱，非常高分辨率的Summer苏黎世v1.0数据集上进行了训练和测试。不同尺寸的补丁进行了实验和比较，表明非常高分辨率的卫星数据的语义分割的最佳尺寸。整体验证和评估表明，使用所采用的深层架构计算的城市场景语义标记的高级别功能的鲁棒性。
In this paper, we compare the performance of different deep-learning architectures under a patch-based framework for the semantic labeling of sparse annotated urban scenes from very high resolution images. In particular, the simple convolutional network ConvNet, the AlexNet and the VGG models have been trained and tested on the publicly available, multispectral, very high resolution Summer Zurich v1.0 dataset. Experiments with patches of different dimensions have been performed and compared, indicating the optimal size for the semantic segmentation of very high resolution satellite data. The overall validation and assessment indicated the robustness of the high level features that are computed with the employed deep architectures for the semantic labeling of urban scenes.