Table 3. Data processing time of DJI-Phantom-2 drone and Pleiades-1B satellite images.
For the drone, the accuracy analysis of pixel-based classification was conducted twice due to there being two different training sites–one representing dominant land-use/cover classes, and another representing both dominant and non-dominant classes visible on the ground.
| Time taken for drone imagery(h) |
Time taken forsatellite imagery.(h) | |
|---|---|---|
| Image preparation | ||
| Geotagging | 2 | - |
| Mosaicking | 8 | - |
| Joining | 6 | - |
| Pansharpening | - | 0.5 |
| Cropping | 0.5 | 0.1 |
| ROI creation | ||
| Data interpretation | 1 | 1 |
| Creating random polygons | 2 | 1 |
| Creating random sets | 2 | 1 |
| Object-based classification | ||
| Segmentation | 4 | 1 |
| Object based automatic classification (10 iterations) | 2 | 1 |
| Manual rule-set classification (1 iteration) | 2 | 1 |
| Dissolve segment | 6 | 1 |
| Convert to raster | 2 | 1 |
| Accuracy analysis (10 iterations) | 2 | 1 |
| Total time | 18 | 6 |
| Pixel-based classification | ||
| Maximum Likelihood (10 iterations) | 10 | 1 |
| Spectral Angle Mapping (10 iterations) | 10 | 1 |
| Accuracy Analysis (20 iterations) | 30 | 3 |
| Total time | 50 | 5 |
| Total time for entire analyses | 89.5 | 14.6 |