Design of a Spectral–Spatial Pattern Recognition Framework for Risk Assessments Using Landsat Data—A Case Study in Chile
Design of a Spectral–Spatial Pattern Recognition Framework for Risk Assessments Using Landsat Data—A Case Study in Chile
复制标题
DOI：
10.1109/jstars.2013.2293421
复制
发表时间：
2014-03
影响因子：
5.5
通讯作者：
A. Braun;C. Rojas;Cristian Echeverri;F. Rottensteiner;Hans-Peter Bähr;Joachim Niemeyer;M. Arias;S. Kosov;S. Hinz;U. Weidner
中科院分区：
文献类型：
--
作者：
A. Braun;C. Rojas;Cristian Echeverri;F. Rottensteiner;Hans-Peter Bähr;Joachim Niemeyer;M. Arias;S. Kosov;S. Hinz;U. Weidner
对于许多生态遥感应用，必须使用空间分辨率和光谱分辨率适中的传统多光谱数据。典型的例子是土地利用变化或森林砍伐评估。研究地点往往太大，覆盖的时间跨度太长，假设有非常高分辨率或高光谱数据等现代数据集的可用性。然而，在陆地卫星数据等传统数据集中，相关类的可分性是有限的。一种很有前途的方法是描述被整合的景观背景像素。为此，计算多尺度上下文特征。然后，采用光谱-空间分类方法。然而，这种方法需要复杂的处理技术。这项研究通过设计一个完整的框架来利用语境特征来举例说明这些问题。该框架使用基于核的分类器，由多分类器系统统一，并通过条件随机场进行进一步改进。在三个场景上的准确率提高了19.0%到26.6%。虽然该框架是针对智利的应用程序而设计的，但通常足以应用于类似的场景。
For many ecological applications of remote sensing, traditional multispectral data with moderate spatial and spectral resolution have to be used. Typical examples are land-use change or deforestation assessments. The study sites are frequently too large and the timespan covered too long assumes the availability of modern datasets such as very high resolution or hyperspectral data. However, in traditional datasets such as Landsat data, separability of the relevant classes is limited. A promising approach is to describe the landscape context pixels that are integrated. For this purpose, multiscale context features are computed. Then, spectral-spatial classification is employed. However, such approaches require sophisticated processing techniques. This study exemplifies these issues by designing an entire framework for exploiting context features. The framework uses kernel-based classifiers which are unified by a multiple classifier system and further improved by conditional random fields. Accuracy on three scenarios is raised between 19.0%pts and 26.6%pts. Although the framework is designed, focusing an application in Chile, it is generally enough to be applied to similar scenarios.