Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping
Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping
复制标题
DOI：
10.1109/bigdata52589.2021.9671974
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Rahul Ghosh;Praveen Ravirathinam;X. Jia;Chenxi Lin;Zhenong Jin;Vipin Kumar
中科院分区：
文献类型：
--
作者：
Rahul Ghosh;Praveen Ravirathinam;X. Jia;Chenxi Lin;Zhenong Jin;Vipin Kumar
大量地球观察卫星数据的可用性为土地使用和土地覆盖地图提供了巨大的机会。但是，由于存在各种土地覆盖类别，嘈杂的数据以及缺乏适当的标签，因此这种映射工作是具有挑战性的。同样，每个土地覆盖类通常都有自己独特的时间模式，只能在某些时期内识别。在本文中，我们介绍了一种新颖的结构，该结构将UNET结构与双向LSTM和注意力机制结合在一起，以共同利用卫星数据的空间和时间性质，并更好地确定每个土地覆盖类别的独特时间模式。我们将我们的方法与其他涉及多个土地覆盖类别的现实世界数据集进行了定量和质量上的其他最先进方法。我们还可以看到注意力重量，以研究其在缓解噪声和识别不同类别的歧视时间段的有效性。这项工作中使用的代码和数据集可公开可用于可重复性。
The availability of massive earth observing satellite data provides huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, noisy data, and the lack of proper labels. Also, each land cover class typically has its own unique temporal pattern and can be identified only during certain periods. In this article, we introduce a novel architecture that incorporates the UNet structure with Bidirectional LSTM and Attention mechanism to jointly exploit the spatial and temporal nature of satellite data and to better identify the unique temporal patterns of each land cover class. We compare our method with other state-of-the-art methods both quantitatively and qualitatively on two real-world datasets which involve multiple land cover classes. We also visualise the attention weights to study its effectiveness in mitigating noise and in identifying discriminative time periods of different classes. The code and dataset used in this work are made publicly available for reproducibility.