arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.01963cs.CV
收藏

多源土地覆盖制图的细粒度分类

Fine grained classification for multi-source land cover mapping

INRAE(法国国家农业、食品与环境研究院);University of Montpellier(蒙彼利埃大学);CIRAD(法国国际农业发展研究中心)

Yawogan Jean Eudes Gbodjo, Dino Ienco, Louise Leroux, Roberto Interdonato, Raffaelle Gaetano

摘要:

如今,人们普遍认为,需要更好地描述农业监测系统的特点,以应对全球变化。及时和准确的土地利用/土地覆盖物测绘可通过提供精细的有用信息来支持这一愿景。在此,提出了一种深度学习方法来处理对象级别的多源土地覆盖制图。该方法是基于一个扩展的循环神经网络丰富的注意力机制专用于多时态数据上下文。此外,介绍了一种新的层次化预训练策略,旨在利用特定的领域知识下的土地覆盖类的层次关系。在留尼汪岛-法国海外省-进行的实验表明,与土地覆盖制图的遥感标准方法相比,该建议具有重要意义。

英文摘要:

Nowadays, there is a general agreement on the need to better characterize agricultural monitoring systems in response to the global changes. Timely and accurate land use/land cover mapping can support this vision by providing useful information at fine scale. Here, a deep learning approach is proposed to deal with multi-source land cover mapping at object level. The approach is based on an extension of Recurrent Neural Network enriched via an attention mechanism dedicated to multi-temporal data context. Moreover, a new hierarchical pretraining strategy designed to exploit specific domain knowledge available under hierarchical relationships within land cover classes is introduced. Experiments carried out on the Reunion island - a french overseas department - demonstrate the significance of the proposal compared to remote sensing standard approaches for land cover mapping.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑