排序方式: 共有4条查询结果,搜索用时 15 毫秒
1
1.
Bovolo F. Bruzzone L. Capobianco L. Garzelli A. Marchesi S. Nencini S. 《Geoscience and Remote Sensing Letters, IEEE》2010,7(1):53-57
2.
Tyagi M. Bovolo F. Mehra A.K. Chaudhuri S. Bruzzone L. 《Geoscience and Remote Sensing Letters, IEEE》2008,5(1):21-25
This letter presents a multistage clustering technique for unsupervised classification that is based on the following: 1) a graph-cut procedure to produce initial segments that are made up of pixels with similar spatial and spectral properties; 2) a fuzzy c-means algorithm to group these segments into a fixed number of classes; 3) a proper implementation of the expectation-maximization (EM) algorithm to estimate the statistical parameters of classes on the basis of the initial seeds that are achieved at convergence by the fuzzy c-means algorithm; and 4) the Bayes rule for minimum error to perform the final classification on the basis of the distributions that are estimated with the EM algorithm. Experimental results confirm the effectiveness of the proposed technique. 相似文献
3.
A Multilevel Parcel-Based Approach to Change Detection in Very High Resolution Multitemporal Images 总被引:1,自引:0,他引:1
This letter presents a novel parcel-based context-sensitive technique for unsupervised change detection in very high geometrical resolution images. In order to improve pixel-based change-detection performance, we propose to exploit the spatial-context information in the framework of a multilevel approach. The proposed technique models the scene (and hence changes) at different resolution levels defining multitemporal and multilevel ldquoparcelsrdquo (i.e., small homogeneous regions shared by both original images). Change detection is achieved by applying a multilevel change vector analysis to each pixel of the considered images. This technique properly analyzes the multilevel and multitemporal parcel-based context information of the considered spatial position. The adaptive nature of multitemporal parcels and their multilevel representation allow one a proper modeling of complex objects in the investigated scene as well as borders and details of the changed areas. Experimental results confirm the effectiveness of the proposed approach. 相似文献
4.
A model‐based method is proposed for improving upon existing threshold relationships which define the rainfall conditions for triggering shallow landslides but do not allow the magnitude of landsliding (i.e. the number of landslides) to be determined. The SHETRAN catchment‐scale shallow landslide model is used to quantify the magnitude of landsliding as a function of rainfall return period, for focus sites of 180 and 45 km2 in the Italian Southern Alps and the central Spanish Pyrenees. Rainfall events with intensities of different return period are generated for a range of durations (1‐day to 5‐day) and applied to the model to give the number of landslides triggered and the resulting sediment yield for each event. For a given event duration, simulated numbers of landslides become progressively less sensitive to return period as return period increases. Similarly, for an event of given return period, landslide magnitude becomes less sensitive to event duration as duration increases. The temporal distribution of rainfall within an event is shown to have a significant impact on the number of landslides and the timing of their occurrence. The contribution of shallow landsliding to catchment sediment yield is similarly quantified as a function of the rainfall characteristics. Rainfall intensity–duration curves are presented which define different levels of landsliding magnitude and which advance our predictive capability beyond, but are generally consistent with, published threshold curves. The magnitude curves are relevant to the development of guidelines for landslide hazard assessment and forecasting. Copyright © 2011 John Wiley & Sons, Ltd. 相似文献
1