|
将自然变化纳入时间序列的土地覆盖变化检测
Incorporating Natural Variation into Time Series-Based Land Cover Change Detection |
|
| |
| 课程网址: |
http://videolectures.net/cidu2011_mithal_detection/
|
| 主讲教师: |
Varun Mithal
|
| 开课单位: |
明尼苏达大学
|
| 开课时间: |
2012-06-27
|
| 课程语种: |
英语
|
| 中文简介: |
监测森林相关变化事件的能力, 如森林资源、农业集约化的毁林和伐木, 对森林资源至关重要。 有效的森林管理。可以利用 modis 增强植被指数等时间序列遥感数据集来确定这些变化。大多数现有方法都适用于跨越均匀植被类型的特定地理区域的小型数据集。此外, 其中大多数需要培训样本或分别为每个地理区域设置参数。这些限制使得算法不可扩展, 并限制了它们的全局适用性。在本文中, 我们提出了一个可扩展的基于时间序列的更改检测框架, 克服了现有方法的这些局限性。我们引入了特定位置的 evi 中的自然变化概念, 并将其纳入变更检测范式。我们使用加利福尼亚州和加拿大的森林重新验证数据来评估我们的方法所确定的更改事件。这项研究的结果表明, 纳入自然变异性的测量值提高了检测精度, 并使范式在植被类型和区域中更加稳健。
|
| 课程简介: |
The ability to monitor forest related change events like forest res, deforestation for agriculture intensi fication, and logging is critical for e ffective forest management. Time series remote sensing data sets such as MODIS Enhanced Vegetation Index (EVI) can be used to identify these changes. Most existing approaches work on small data sets spanning over a specifi c geographic region of a homogeneous vegetation type. Also, most of these need training samples or require setting of parameters for each geographic region individually. These limitations make the algorithms unscalable and restrict their global applicability. In this paper, we present a scalable time series based change detection framework that overcomes these limitations of the existing methods. We introduce the concept of natural variation in EVI for a given of location and incorporate it into the change detection paradigm. We evaluate the change events identifi ed by our approach using forest re validation data in California and Canada. The results of this study demonstrate that the inclusion of a measure of natural variability improves detection accuracy, and makes the paradigm more robust across vegetation types and regions.
|
| 关 键 词: |
计算机科学; 数据挖掘; 时间序列分析
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2020-06-03：张荧(课程编辑志愿者)
|
| 阅读次数: |
33
|
|
图 书 馆