基于人类视觉系统区域分裂的图割遥感图像分割算法研究  

Remote Sensing Image Segmentation Based on Human Visual System Region Splitting and Graph Cut

作　　者：蒋华[1] 温静[2] 王玉斌[2] 

机构地区：[1]桂林电子科技大学网络中心,桂林541004 [2]桂林电子科技大学计算机与控制学院,桂林541004

出　　处：《遥感信息》2011年第6期13-17,共5页Remote Sensing Information

基　　金：广西自然科学基金(0991071)

摘　　要：针对传统Normalized Cut(NC)在分割图像过程中实时性差的特点,提出一种使用人类视觉系统(HVS)区域分裂的图割方法。根据HVS特性用区域分裂算法将遥感图像分割成多个小区域,再结合各个小区域的灰度和空间信息从全局角度用NC方法在区域间进行划分,完成图像的最终分割。实验表明,相对于传统的NC方法,该算法在获得相近分割质量的同时,分割速度有了显著提高,是一种有效的图像分割方法。Aiming at the problem of poor real-time ability of Normalized Cut（NC）,this paper suggests a remote sensing image segmentation algorithm based on region splitting and graph within human visual system（HVS）.According to the features of HVS,the algorithm uses region splitting method to segment the remote sensing image into a large number of small regions.By integrating gray feature and spatial location of each region,NC is used to segment the image among regions from global view,by which the final segmented image can be generated.Experimental result shows that compared with the traditional NC,operating speed is significantly improved as getting close to the segmentation quality,and this is a kind of effective method of image segmentation.

关 键 词：遥感图像分割 区域分裂 图割 NormalizedCut 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]