Self-taught learning for land cover mapping of large areas, using multispectral remote sensing data

使用多光谱遥感数据进行大面积土地覆盖绘图的自学学习

• 批准号: 240015646
• 负责人: Professor Dr. Björn Waske
• 金额: --
• 依托单位: Institut für Informatik
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2013
• 资助国家: 德国
• 起止时间: 2012-12-31 至 2017-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/240015646?language=en
• 关键词: Self; taught; learning; land; cover

Earth Observation data play a major role in supporting decision-support systems and monitoring compliance of several multilateral environmental treaties. Land cover maps of remote sensing data are the most commonly used product in this context and the development of feasible and accurate classification strategies is an ongoing research field. Particularly the classification of larger areas is often challenging, e.g., due to the lack of adequate amount of training and validation data. This research project aims on the development of a Self-taught Learning framework for the land cover classification of remote sensing data. The approach enables the use of labeled pixels (i.e., with reference information) and unlabeled pixels from arbitrary scenes and different acquisitions dates. In contrast to semi-supervised frameworks, the unlabeled data can contain unknown and irrelevant classes. Moreover, the classes need not to be explicitly modeled. The developed framework will be used for classifying multispectral remote sensing data from different study sites, e.g., which are characterized by (i) cropland, (ii) forests and (iii) urban land use. The performance of the Self-taught learning framework will be assessed and compared to other methods in term of accuracy and computational complexity.

地球观测数据在支持决策支持系统和监测若干多边环境条约的遵守情况方面发挥着重要作用。遥感数据的土地覆盖图是这方面最常用的产品，制定可行和准确的分类战略是一个正在进行的研究领域。特别是较大区域的分类通常具有挑战性，例如，由于缺乏足够的训练和验证数据。本研究项目旨在为遥感数据的土地覆盖分类开发一个自学框架。该方法使得能够使用标记的像素（即，具有参考信息）和来自任意场景和不同采集日期的未标记像素。与半监督框架相比，未标记数据可能包含未知和不相关的类。此外，类不需要显式建模。所开发的框架将用于对来自不同研究地点的多光谱遥感数据进行分类，其特点是（一）耕地，（二）森林和（三）城市土地使用。将评估自学框架的性能，并在准确性和计算复杂性方面与其他方法进行比较。

项目成果

Shapelet-based sparse image representation for landcover classification of hyperspectral data

• DOI: 10.1109/prrs.2014.6914277
• 发表时间: 2014-10
• 期刊: 2014 8th IAPR Workshop on Pattern Reconition in Remote Sensing
• 作者: R. Roscher;B. Waske

Discriminative archetypal self-taught learning for multispectral landcover classification

• DOI: 10.1109/prrs.2016.7867022
• 发表时间: 2016-12
• 期刊: 2016 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS)
• 作者: R. Roscher;Susanne Wenzel;B. Waske

Shapelet-Based Sparse Representation for Landcover Classification of Hyperspectral Images

基于 Shapelet 的高光谱图像土地覆盖分类的稀疏表示

• DOI: 10.1109/tgrs.2015.2484619
• 发表时间: 2016
• 期刊: IEEE Transactions on Geoscience and Remote Sensing
• 影响因子: 8.2
• 作者: Roscher

Landcover classification with self-taught learning on archetypal dictionaries

• DOI: 10.1109/igarss.2015.7326282
• 发表时间: 2015-07
• 期刊: 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
• 作者: R. Roscher;Christoph Römer;B. Waske;L. Plümer