The process of urbanization and industrialization always have an impact on the hydrological regime and alternate land use pattern of the area. The present study is being carried out for the upper Bhima basin in wester...
详细信息
ISBN:
(纸本)9781467311601
The process of urbanization and industrialization always have an impact on the hydrological regime and alternate land use pattern of the area. The present study is being carried out for the upper Bhima basin in western India. The basin has undergone various land use changes during last decade and before due to various anthropogenic activities. An object based image analysis approach along with rainfall and resulting stream flow records for last two decades (1985-2004) were analyzed to study the impact of land use on steam flow in the basin. The study revealed that rainfall pattern was nearly constant during study period, whereas a significant reduction in stream flow has been observed. Conversion of wasteland to agricultural land, construction of new dams/reservoirs in the high rainfall region, increase in domestic and industrial water demand are the major factors responsible for stream flow reduction in the basin.
Segmentation of satellite images using a novel adaptive non parametric mean-shift clustering algorithm is proposed in this paper. image segmentation refers to the process of splitting up an image into its constituent ...
详细信息
ISBN:
(纸本)9781467311601
Segmentation of satellite images using a novel adaptive non parametric mean-shift clustering algorithm is proposed in this paper. image segmentation refers to the process of splitting up an image into its constituent objects. It is also an important step in bridging the semantic gap between low level image interpretation and high level visual analysis. Mean-shift technique is based on the concept of kernel density estimation. It has been applied successfully in diverse vision related tasks including segmentation. The performance of the mean shift algorithm is greatly affected by the size of the parzen window and the terminating criteria. These two issues have been taken care of here in a purely statistical framework. The efficiency of this newly developed adaptive clustering has been judged for segmentation of any initially oversegmented satellite image. The notion of object based image analysis is preserved by initially over segmenting the image by watershed technique. Extensive experiments on several multispectral satellite images have confirmed the effectivity of this proposed approach in comparison to some widely used state of the art segmentation methods.
暂无评论