The paper proposes a method for recognition of earth surface types according to space images using object-oriented classification. The classification is conducted in two stages: Markov stochastic segmentation for object extraction and supervised classification of the objects. The method is tested on space imagery of the Russian Arctic in comparison with point-oriented classification.
|Number of pages||12|
|Journal||Herald of the Bauman Moscow State Technical University, Series Natural Sciences|
|Publication status||Published - 2017|
- Ecosystem monitoring
- Image segmentation
- Object-oriented classification