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.
Yitian WU,Fu CHEN,Yong MA, et al. Research on automatic extraction method for coastal aquaculture area using Landsat8 data[J]. Remote Sensing for Land & Resources,
2018, 30(3): 96-105.
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.
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.
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.
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.
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.
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.
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.
doi: 10.1109/18.857802
url: http://ieeexplore.ieee.org/document/857802/