Lab 1: Introduction to eCognition.
· Describe what image segmentation is and why it is important for OBIA? (maximum 150 words)
· Briefly describe what is multi-resolution segmentation? (maximum 150 words)
· Provide seven screenshots of the segmentation parameters tried above (and label each screenshot with a suitable caption so that the blog reader easily understands).
Figure 1: Segmentation scale factor: , shape/compactness:
Figure 2: Segmentation scale factor: , shape/compactness:
· Discuss which segmentation parameters provided you the best output for segmentation. Discuss what criteria did you consider to select the optimal segmentation outputs? (maximum 150 words)
· Experiment with different sets of features within the standard NN feature space. (Classification > Nearest Neighbor > Edit Standard NN feature space…). First do a NN classification with mean of spectral bands and produce a classified output map. Second time, also include the standard deviation of each spectral band and produce a new classification. Make maps of both outputs in ArcGIS, upload them on your course blog webpage and properly label them.
No comments:
Post a Comment