Answer:
Explanation:The objectives of hyperspectral image classification are as follows:
Feature extraction: Hyperspectral image classification aims to extract relevant features from the hyperspectral data to represent different land cover or target classes. This involves identifying spectral patterns or signatures that distinguish one class from another.
Classification accuracy: The primary objective is to achieve accurate and reliable classification results. Hyperspectral image classification algorithms strive to assign each pixel or spatial unit in the image to the most appropriate class or category based on its spectral characteristics.
Discrimination of classes: Hyperspectral image classification aims to differentiate and discriminate between different classes or land cover types present in the scene. It should be able to accurately distinguish and assign pixels to their respective classes, such as vegetation, water, buildings, roads, etc.
Mapping and monitoring: Another objective is to generate maps or spatial representations of the classified image, which provide information about the spatial distribution of different land cover classes. This enables monitoring and analysis of changes in land cover over time.
Application-specific objectives: Hyperspectral image classification can have specific objectives based on the application or domain. For example, in agriculture, the objective might be to identify and monitor crop types or detect disease-infected areas. In environmental monitoring, it could involve identifying pollution sources or mapping habitats.
Overall, the objectives of hyperspectral image classification include accurate classification, discrimination of land cover classes, mapping and monitoring, and addressing specific application needs.