Feature Description
With the continuous improvement in resolution of satellite remote sensing images and aerial remote sensing images, more useful data and information can be obtained from these images. For different application scenarios, there are varying requirements for processing remote sensing images. To effectively analyze and manage these remote sensing image data, it is necessary to assign semantic labels based on image content. Scene classification serves as a crucial approach to address this challenge.
Scene classification involves categorizing image data based on specific ground object characteristics, distinguishing regions with similar features and assigning scene labels to each image. Therefore, the key to scene classification lies in feature extraction from images.
The scene classification result consists of uniformly sized (32*32 pixels) vector grids. Each grid carries the scene label corresponding to its image location, representing a coarse-grained classification method at a lower level than pixel-based classification. Scene classification is typically applied to large-scale classification tasks, such as urban local climate zone classification.
Parameter Description
| Parameter Name | Default Value | Description | Type |
|---|---|---|---|
| File Type | Dataset | Specifies the file type, selectable between dataset or folder type. | Boolean |
| Model File | Specifies the model file (*.sdm) for scene classification | String | |
| Batch Processing Quantity | 1 | Specifies the number of images processed in a single inference step | Integer |
| Processor Type | GPU | Specifies the processor type | String |
| GPU ID | 0 | Input GPU ID(s). Supports multi-GPU inference by entering multiple IDs (e.g., "0,1,2" will be converted to "012") | String |
| Other Parameter Settings (Optional) |
False | Check this box to configure bounds dataset/datasource parameters | Boolean |
| Result Datasource | Specifies the datasource containing the result dataset | Datasource | |
| Result Dataset | SceneClassificationResult | Specifies the name of the resulting dataset | String |
Output
| Parameter Name | Description | Type |
|---|---|---|
| Result Dataset | Result Dataset | DatasetVector |