基于高分辨率影像的近海养殖区的一种自动提取方法  

A Method of Coastal Aquaculture Area Automatic Extraction with High Spatial Resolution Images

作　　者：卢业伟[1,2] 李强子[1] 杜鑫[1] 王红岩[1] 刘吉磊[1,3] 

机构地区：[1]中国科学院遥感与数字地球研究所再生资源研究室,北京100101 [2]中国矿业大学(北京),北京100083 [3]中国科学院大学,北京100049

出　　处：《遥感技术与应用》2015年第3期486-494,共9页Remote Sensing Technology and Application

基　　金：高分辨率对地观测系统重大专项(01-Y30A03-9001-12/13)

摘　　要：近海养殖调查在海岸带资源开发利用规划、环境保护与沿岸海上交通规划中处于重要地位。利用遥感技术开展近海养殖调查与分析,是当前的海岸带与湿地遥感的热点方向之一。以福建省宁德市三都澳海区为实验区,在分析近海养殖的渔排和海带/紫菜养殖区光谱特征的基础上,建立用于近海养殖区快速检测的光谱特征指数,在此基础上利用统计均值纹理与阈值检测算法设计,并结合近海养殖区的集合形状判断,实现了不同类型近海养殖区的高精度自动提取。实验结果表明:该方法能够快速准确地监测不同类型养殖区的分布情况,总体检测精度达到90%以上,可以为管理部门科学地规划管理海岸带养殖区提供有效的信息支持和辅助决策分析。It is significant to study on offshore aquaculture for development,utilization,planning and protecting of coastal zones.Nowadays,it becomes one effective measure to investigate inshore aquaculture with remote sensing image processing.In this study,index of spectral feature,addresses rapid detection of offshore aquaculture activities,were constructed by analyzing the spectral feature of the fish raft and the kelp/porphyra zone in area of Sanduao Sea around Ningde City in Fujian Province.Then an algorithm of threshold detection based on the texture of the index was proposed to identify the fish raft and the kelp/porphyra area.The model was selected to remove sea-background,and the Otsu was used to discriminate fish raft and kelp/porphyra area.The experimental results showed the proposed method can monitor the different aquaculture area in a fast and accurate way,and ensure the accuracy to reach higher than 90%.

关 键 词：遥感 近海养殖 指数 纹理 

分 类 号：S951.2[农业科学—水产养殖]