检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:夏桂林[1] 尹勇[1] 神和龙[1] 刘春雷[1]
机构地区:[1]大连海事大学航海动态仿真与控制实验室,辽宁大连116026
出 处:《大连海事大学学报》2014年第4期85-88,共4页Journal of Dalian Maritime University
基 金:国家高技术研究发展计划(863)资助项目(2011AA110201)
摘 要:为提高船舶在雾天航行的安全性,将图像去雾算法应用于船舶实际营运中.建立雾天退化物理模型,采用暗黑通道先验知识初步估计海上图像的透射率,利用引导图像滤波对初步估计的透射率进行细化.针对海上图像大面积天空的特点,对全局大气光的估计进行改进,最后,根据雾天成像的物理模型恢复出无雾图像.采用MatLab2012平台对实船采集的有雾图像进行去雾,去雾后图像色彩失真度较小,海上目标能够得到清晰的恢复,且去雾所用时间短,说明该算法可应用于雾天船舶航行.In order to improve ship navigation safety in the fog,an image haze removal algorithm was applied to the actual operation of the ship. The fog degraded physical model was established,and dark channel prior knowledge was preliminarily used to estimate sea image transmission map,then the guided image filtering was used to refine the preliminary transmission map. The characteristics of a large area of sky light of sea image were considered to improve the estimation of global atmospheric. Finally,the haze removal sea image is recovered based on the above physical mode. Haze removal algorithm is applied to foggy image acquired by real ship on Mat Lab2012 platform. The haze removal images have a smaller degree of color distortion,and sea targets can be clearly recovered and the cost time of haze removal is short,which indicate that the algorithm applying to ship sailing in fog is feasible.
关 键 词:海上图像 去雾 暗黑通道 全局大气光 引导图像滤波
分 类 号:U698[交通运输工程—港口、海岸及近海工程] TP391.41[交通运输工程—船舶与海洋工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15