Water-Body types identification in urban areas from radarsat-2 fully polarimetric SAR data
详细信息 查看全文
- 作者：Lei Xiea ; b ; Hong Zhanga ; zhanghong@radi.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Chao Wanga ; Fulong Chena
- 关键词：PolSAR ; Supervised classification ; Water-body extraction ; Water-body types identification
- 刊名：International Journal of Applied Earth Observation and Geoinformation
- 出版年：2016
- 出版时间：August 2016
- 年：2016
- 卷：50
- 期：Complete
- 页码：10-25
- 全文大小：10761 K
文摘
- •
Spatial contextual information help removing false alarms in built-up areas from the water-body extraction result using Wishart-ML classifier.
- •
Shape features are useful in classifying different water-body type but fail in distinguishing several other objects from water-body.
- •
Polarimetric features eliminate the misclassifications between water-body and other objects.
- •
20">The proposed water-body type classification framework provides satisfactory results both at the object level and the pixel level using different datasets.