Satellite data

Method name

Remarks

Landsat TM (30 m)

[114]

Object-oriented classification, Pixel-based supervised MXL.

MXL classification produced salt and pepper image, whereas the classified image derived from polygon-based classification is closer to human visual interpretation.

Landsat TM (30 m)

[115]

Supervised MXL classification, Unsupervised ISODATA classification.

Accuracy assessment showed that the ISODATA could multispectrally classify the urban water successfully.

Even smaller ponds or rivers (<30 m) can be extracted if the high resolution imagery is used.

Quickbird (0.61 m)

[116]

Statistical Regional Merging (SRM) for image segmentation, NDWI and Normalized Saturation-value Difference Index (NSVDI) for water extraction.

The results prove that the accuracy of the extracted water features can be significantly improved and shadows can be effectively eliminated.

Zi-Yuan 3 (ZY-3) (2.1 m sharpened)

[117]

Object oriented multi-resolution segmentation, Edge detection using Canny-edge detector.

The extraction results on the high resolution remotely sensed image are significant by taking into account the spectrum geometry and texture information of images. (Accuracy = 94.6%).

Landsat ETM+ (15 m), ERS SAR (26 m), SPOT (10 m sharpened) [19]

Knowledge-based DT method including spatial features as size, shape, position and multi-spectral characteristics.

The proposed algorithm is differentiated from other existing algorithms as it is independent of the image sensor. It can be applied on either PAN images or any spectral band of optical images. The proposed algorithm failed to extract small water areas.

WV2 (2 m)

Rapid Eye (2 m)

Pleiades (5 m) [103]

Hierarchical land-use classification, ISODATA unsupervised classification to extract additional subclasses.

RapidEye showed a higher overall accuracy of 78%, surpassing the result of Pleiades (74%). Pleiades showed the best classification accuracy compared to RapidEye and WV2.

WV2 proves to be more versatile to extract various sub-classes.

WV2 (0.5 m sharpened) [102]

Object-based image classification utilizing Nearest Neighbor decision rules.

The analysis found that object-based classification using scale parameter of 60 produced the best result of wetland delineation compared to scale 30 and 300.