基于Landsat8数据的近海养殖区自动提取方法研究
|
摘要
利用遥感影像进行近海养殖区提取,是近海渔业资源监管的一种有效手段。然而由于近海养殖区受海水叶绿素和悬浮泥沙浓度差异分布的影响,海域水色背景往往较为复杂,使得传统近海养殖区提取方法很难取得理想效果。为了准确提取复杂水色背景下的近海养殖区,提出一种结合光谱和纹理信息的养殖区自动提取方法。首先,利用基于正交子空间投影的约束能量最小化(orthogonal subspace projection-weighted constrained energy minimization,OWCEM)方法增强近海养殖区信息;然后,利用近海养殖区的空间纹理信息,使用局部标准差自适应分割法(standard deviation adaptive segmentation,SDAS)对影像进行划分;最后,基于分割图像对近海养殖区进行自动提取。选取山东桑沟湾养殖海域和福建三都澳养殖海域为实验区,采用Landsat8数据对所提方法进行近海养殖区提取实验,结果表明:在复杂水色背景下,该方法能够准确快速地识别出近海养殖区的分布情况,在2个实验区都能达到93%以上的准确率,为近海养殖区自动提取提供了一种新的有效方法。
During coastal resource monitoring,it is an effective way to extract aquaculture region using remote sensing data,whereas the water color in coastal region is complexly influenced by the distribution difference of chlorophyll-a and total suspended sediment concentration. And it would be difficult to accurately extract the aquaculture region with complex background using traditional methods. In view of the above problem,the authors proposed an algorithm for automatic coastal aquaculture area extraction combined with spectral and spatial information of aquaculture. Firstly,orthogonal subspace projection-weighted constrained energy minization method(OWCEM) was used to enhance the information of coastal aquaculture area. Secondly,by using the spatial texture information of the coastal aquaculture area,standard deviation adaptive segmentation(SDAS) method was used to automatically extract the cultivation area. In order to verify the accuracy of the proposed algorithm,the authors selected Sanggou Bay in Shandong and Sanduao Bay in Fujian as test regions and conducted the area extraction using Landsat8 data. The experimental results show that the proposed method can rapidly and accurately identify the distribution of coastal aquaculture area in complex background color and can reach about 93% accuracy rate with a low missing rate. The method could provide a new and effective means for automatic extraction of offshore aquaculture area.
During coastal resource monitoring,it is an effective way to extract aquaculture region using remote sensing data,whereas the water color in coastal region is complexly influenced by the distribution difference of chlorophyll-a and total suspended sediment concentration. And it would be difficult to accurately extract the aquaculture region with complex background using traditional methods. In view of the above problem,the authors proposed an algorithm for automatic coastal aquaculture area extraction combined with spectral and spatial information of aquaculture. Firstly,orthogonal subspace projection-weighted constrained energy minization method(OWCEM) was used to enhance the information of coastal aquaculture area. Secondly,by using the spatial texture information of the coastal aquaculture area,standard deviation adaptive segmentation(SDAS) method was used to automatically extract the cultivation area. In order to verify the accuracy of the proposed algorithm,the authors selected Sanggou Bay in Shandong and Sanduao Bay in Fujian as test regions and conducted the area extraction using Landsat8 data. The experimental results show that the proposed method can rapidly and accurately identify the distribution of coastal aquaculture area in complex background color and can reach about 93% accuracy rate with a low missing rate. The method could provide a new and effective means for automatic extraction of offshore aquaculture area.
引文
[1]FAO. The State of World Fisheries and Aquaculture 2014[R].Rome:FAO,2014:40-41.
[2]程田飞,周为峰,樊伟.水产养殖区域的遥感识别方法进展[J].国土资源遥感,2012,24(3):1-5. doi:10. 6046/gtzyyg.2012. 03. 01.Cheng T F,Zhou W F,Fan W. Progress in the methods for extracting aquaculture areas from remote sensing data[J]. Remote Sensing for Land and Resources,2012,24(3):1-5. doi:10. 6046/gtzyyg. 2012. 03. 01.
[3]马艳娟,赵冬玲,王瑞梅,等.基于ASTER数据的近海水产养殖区提取方法[J].农业工程学报,2010,26(14):120-124.Ma Y J,Zhao D L,Wang R M,et al. Offshore aquatic farming areas extraction method based on ASTER data[J]. Transactions of the CSAE,2010,26(14):120-124.
[4]周小成,汪小钦,向天梁,等.基于ASTER影像的近海水产养殖信息自动提取方法[J].湿地科学,2006,4(1):64-68.Zhou X C,Wang X Q,Xiang T L,et al. Method of automatic extracting seaside aquaculture land based on ASTER remote sensing image[J]. Wetland Science,2006,4(1):64-68.
[5]林桂兰,孙飒梅,曾良杰,等.高分辨率遥感技术在厦门海湾生态环境调查中的应用[J].台湾海峡,2003,22(2):242-247.Lin G L,Sun S M,Zeng L J,et al. Application of high resolution satellite remote sensing in survey of ecological environment at Xiamen Bay[J]. Journal of Oceanography in Taiwan Strait,2003,22(2):242-247.
[6]孙晓宇,苏奋振,周成虎,等.基于RS与GIS的珠江口养殖用地时空变化分析[J].资源科学,2010,32(1):71-77.Sun X Y,Su F Z,Zhou C H,et al. Analyses on spatial-temporal changes in aquaculture land in coastal areas of the Pearl River Estuarine[J]. Resources Science,2010,32(1):71-77.
[7]卢业伟,李强子,杜鑫,等.基于高分辨率影像的近海养殖区的一种自动提取方法[J].遥感技术与应用,2015,30(3):486-494.Lu Y W,Li Q Z,Du X,et al. A method of coastal aquaculture area automatic extraction with high spatial resolution images[J]. Remote Sensing Technology and Application,2015,30(3):486-494.
[8]Ji L Y,Geng X R,Sun K,et al. Target detection method for water mapping using Landsat 8 OLI/TIRS imagery[J]. Water,2015,7(2):794-817.
[9]Chen J,Chen J,Liao A P,et al. Global land cover mapping at 30 m resolution:A POK-based operational approach[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,103:7-27.
[10]Farrand W H,Harsanyi J C. Mapping the distribution of mine tailings in the Coeur d’Alene River Valley,Idaho,through the use of a constrained energy minimization technique[J]. Remote Sensing of Environment,1997,59(1):64-76.
[11]Geng X R,Ji L Y,Sun K,et al. CEM:More bands,better performance[J]. IEEE Geoscience and Remote Sensing Letters,2014,11(11):1876-1880.
[12]Xu H Q. Modification of normalised difference water index(NDWI)to enhance open water features in remotely sensed imagery[J]. International Journal of Remote Sensing,2006,27(14):3025-3033.
[13]Feyisa G L,Meilby H,Fensholt R,et al. Automated water extraction index:A new technique for surface water mapping using Landsat imagery[J]. Remote Sensing of Environment,2014,140:23-35.
[14]邬明权,韩松,赵永清,等.应用Landsat TM影像估算渤海叶绿素a和总悬浮物浓度[J].遥感信息,2012,27(4):91-95.Wu M Q,Han S,Zhao Y Q,et al. Quantitative estimation of chlorophyll-a and total suspended matter concentration with Landsat TM[J]. Remote Sensing Information,2012,27(4):91-95.
[15]Chang C I. An information-theoretic approach to spectral variability,similarity,and discrimination for hyperspectral image analysis[J]. IEEE Transactions on Information Theory,2000,46(5):1927-1932.
[16]Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[2]程田飞,周为峰,樊伟.水产养殖区域的遥感识别方法进展[J].国土资源遥感,2012,24(3):1-5. doi:10. 6046/gtzyyg.2012. 03. 01.Cheng T F,Zhou W F,Fan W. Progress in the methods for extracting aquaculture areas from remote sensing data[J]. Remote Sensing for Land and Resources,2012,24(3):1-5. doi:10. 6046/gtzyyg. 2012. 03. 01.
[3]马艳娟,赵冬玲,王瑞梅,等.基于ASTER数据的近海水产养殖区提取方法[J].农业工程学报,2010,26(14):120-124.Ma Y J,Zhao D L,Wang R M,et al. Offshore aquatic farming areas extraction method based on ASTER data[J]. Transactions of the CSAE,2010,26(14):120-124.
[4]周小成,汪小钦,向天梁,等.基于ASTER影像的近海水产养殖信息自动提取方法[J].湿地科学,2006,4(1):64-68.Zhou X C,Wang X Q,Xiang T L,et al. Method of automatic extracting seaside aquaculture land based on ASTER remote sensing image[J]. Wetland Science,2006,4(1):64-68.
[5]林桂兰,孙飒梅,曾良杰,等.高分辨率遥感技术在厦门海湾生态环境调查中的应用[J].台湾海峡,2003,22(2):242-247.Lin G L,Sun S M,Zeng L J,et al. Application of high resolution satellite remote sensing in survey of ecological environment at Xiamen Bay[J]. Journal of Oceanography in Taiwan Strait,2003,22(2):242-247.
[6]孙晓宇,苏奋振,周成虎,等.基于RS与GIS的珠江口养殖用地时空变化分析[J].资源科学,2010,32(1):71-77.Sun X Y,Su F Z,Zhou C H,et al. Analyses on spatial-temporal changes in aquaculture land in coastal areas of the Pearl River Estuarine[J]. Resources Science,2010,32(1):71-77.
[7]卢业伟,李强子,杜鑫,等.基于高分辨率影像的近海养殖区的一种自动提取方法[J].遥感技术与应用,2015,30(3):486-494.Lu Y W,Li Q Z,Du X,et al. A method of coastal aquaculture area automatic extraction with high spatial resolution images[J]. Remote Sensing Technology and Application,2015,30(3):486-494.
[8]Ji L Y,Geng X R,Sun K,et al. Target detection method for water mapping using Landsat 8 OLI/TIRS imagery[J]. Water,2015,7(2):794-817.
[9]Chen J,Chen J,Liao A P,et al. Global land cover mapping at 30 m resolution:A POK-based operational approach[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,103:7-27.
[10]Farrand W H,Harsanyi J C. Mapping the distribution of mine tailings in the Coeur d’Alene River Valley,Idaho,through the use of a constrained energy minimization technique[J]. Remote Sensing of Environment,1997,59(1):64-76.
[11]Geng X R,Ji L Y,Sun K,et al. CEM:More bands,better performance[J]. IEEE Geoscience and Remote Sensing Letters,2014,11(11):1876-1880.
[12]Xu H Q. Modification of normalised difference water index(NDWI)to enhance open water features in remotely sensed imagery[J]. International Journal of Remote Sensing,2006,27(14):3025-3033.
[13]Feyisa G L,Meilby H,Fensholt R,et al. Automated water extraction index:A new technique for surface water mapping using Landsat imagery[J]. Remote Sensing of Environment,2014,140:23-35.
[14]邬明权,韩松,赵永清,等.应用Landsat TM影像估算渤海叶绿素a和总悬浮物浓度[J].遥感信息,2012,27(4):91-95.Wu M Q,Han S,Zhao Y Q,et al. Quantitative estimation of chlorophyll-a and total suspended matter concentration with Landsat TM[J]. Remote Sensing Information,2012,27(4):91-95.
[15]Chang C I. An information-theoretic approach to spectral variability,similarity,and discrimination for hyperspectral image analysis[J]. IEEE Transactions on Information Theory,2000,46(5):1927-1932.
[16]Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.