IRemoteSensingVLM<T>
Interfaces · AiDotNet.VisionLanguage.Interfaces
Interface for remote sensing vision-language models specializing in satellite and aerial imagery.
Implements: IGenerativeVisionLanguageModel<T>
Known implementations: GeoChat<T>, RSGPT<T>, SkyEyeGPT<T>
How It Works
Remote sensing VLMs understand satellite imagery, aerial photos, and geospatial data. They support tasks like scene classification, object detection in overhead imagery, change detection, and grounded visual question answering on geospatial data.
Properties
| Property | Summary |
|---|---|
string LanguageModelName { get; } |
Gets the name of the language model backbone. |
string SupportedBands { get; } |
Gets the supported image resolution bands (e.g., RGB, multispectral). |
Methods
| Method | Summary |
|---|---|
Tensor<T> AnswerRemoteSensingQuestion(Tensor<T> image, string question) |
Answers a question about a remote sensing image. |