Multiple Classification
Feature Description
Performs multiple classification on imagery by analyzing spectral information and geographic features in remote sensing images. Assigns semantic category labels to pixels with semantic information for land cover classification, including buildings, woodland, grassland, paddy fields, agricultural land, etc. Compared to binary classification, multiple classification determines which category each pixel belongs to among multiple classes of interest through neural network models. It supports multi-class feature identification and calculates positional, boundary, and area information of target categories through pixel analysis.
Parameter Description
| Parameter Name | Default Value | Description | Type |
|---|---|---|---|
| File Type | Dataset | Specifies the input file type. Available options: dataset or folder. | Boolean |
| Model File | Specifies the model file (*.sdm) for multiple classification | String | |
| Tile Overlap (Pixel) | 0 | Defines overlapping pixels between tiles to mitigate edge prediction issues. Larger overlaps increase processing time | Integer |
| Batch Size | 1 | Specifies the number of images processed simultaneously during inference | Integer |
| Processor Type | GPU | Selects processor type for computation | String |
| GPU ID | 0 | Specifies GPU device ID(s) for multi-card inference. Multiple IDs should be comma-separated (e.g., "0,1,2" becomes "012") | String |
| Additional Parameter Settings (Optional) |
false | Enables configuration of bounds dataset/datasource parameters when checked | Boolean |
| Result Datasource | Specifies target datasource for storing output datasets | Datasource | |
| Result Dataset | multiclassify_result | Defines name for output dataset | String |
Output
| Parameter Name | Description | Type |
|---|---|---|
| Result Dataset | Output classification results | DatasetVector |