River Extraction from High-Resolution Satellite Images Combining Deep Learning and Multiple Chessboard Segmentation

被引：0

作者：

Fang H. ^{[1
]}

Jiang Y. ^{[2
]}

Ye Y. ^{[2
]}

Cao Y. ^{[2
]}

机构：

[1] School of Mathematical Sciences, Peking University, Beijing

[2] Institute of Water Resources, China Institute of Water Resources and Hydropower Research, Beijing

来源：

Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis | 2019年 / 55卷 / 04期

关键词：

Convolution neural network (CNN); Deep learning; High resolution satellite images; Multiple chessboard segmentation; River extraction;

D O I：

10.13209/j.0479-8023.2019.045

中图分类号：

学科分类号：

摘要：

Using existing methods to extract rivers, especially the small river from remote sensing images, is liable to be interrupted. The combination of deep learning and multiple chessboard segmentation is applied to river extraction from high resolution remote sensing images. Three GF-2 satellite remote sensing images in mountain area, plain and city are used for experiment. The results show that compared with the existing methods, extracted river by proposed method is more continuous. The small rivers accounts for two pixel widths can also be extracted in GF-2 satellite remote sensing images. © 2019 Peking University.

引用

页码：692 / 698

页数：6

共 16 条

[1]

Schumann G., Hostache R., Puech C., Et al., High-resolution 3-D flood information from radar imagery for flood hazard management, IEEE Transactions on Geoscience and Remote Sensing, 45, 6, pp. 1715-1725, (2007)

[2]

Settle J.J., Briggs S.A., Fast maximum likelihood classification of remotely-sensed imagery, Interna-tional Journal of Remote Sensing, 8, 5, pp. 723-734, (1987)

[3]

McFeeters S.K., The use of normalized difference water index (NDWI) in the delineation of open water features, International Journal of Remote Sensing, 17, 7, pp. 1425-1432, (1996)

[4]

Hanqiu X., Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery, International Journal of Remote Sensing, 27, 14, pp. 3025-3033, (2006)

[5]

Sheng Y., Shah C.A., Smith L.C., Automated image registration for hydrologic change detection in the lake-rich Arctic, IEEE Geoscience & Remote Sen-Sing Letters, 5, 3, pp. 414-418, (2008)

[6]

Pal M., Mather P.M., Support vector machines for classification in remote sensing, International Journal of Remote Sensing, 26, 5, pp. 1007-1011, (2005)

[7]

Liu Y., Zhang B., Wang N., Et al., A self-trained semisupervised SVM approach to the remote sensing land cover classification, Computers & Geoscien-Ces, 59, 9, pp. 98-107, (2013)

[8]

Kavzoglu T., Mather P.M., The use of back propaga-ting artificial neural networks in land cover classi-fication, International Journal of Remote Sensing, 24, 23, pp. 4907-4938, (2003)

[9]

Gong B., Im J., Mountrakis G., An artificial immune network approach to multi-sensor land use/land cover classification, Remote Sensing of Environment, 115, 2, pp. 600-614, (2011)

[10]

Blaschke T., Object based image analysis for remote sensing, ISPRS Journal of Photogrammetry and Remote Sensing, 65, 1, pp. 2-16, (2010)

← 1 2 →