Improving the Efficiency of Land Cover Classification by Combining Segmentation, Hierarchical Clustering, and Active Learning

Keyphrases

• Active Learning 100%
• Land Cover Classification 100%
• Clustering Learning 100%
• Hierarchical Clustering 100%
• Training Samples 50%
• Local Density 50%
• Posterior Probability 25%
• Query Method 25%
• Learning Scheme 25%
• Segmentation Approach 25%
• Germany 25%
• State-of-the-art Techniques 25%
• Random Variables 25%
• Overall Accuracy 25%
• Remote Sensing Data 25%
• Potsdam 25%
• Three-state 25%
• Aerial Remote Sensing 25%
• Supervised Machine Learning 25%
• K-means 25%
• Euclidean Distance 25%
• Spectral Angle 25%
• Random Weights 25%
• Active Query 25%
• Active Learning Strategies 25%
• Information Density 25%
• Simple Linear Iterative Clustering 25%
• Remote Sensing Dataset 25%
• Bisecting K-means Algorithm 25%

Computer Science

• Active Learning 100%
• Hierarchical Clustering 100%
• Training Sample 40%
• Segmentation Approach 20%
• Random Variable 20%
• Remote Sensing Data 20%
• Mean Algorithm 20%
• Euclidean Distance 20%
• Learning Scheme 20%
• Clustering Algorithm 20%
• Posterior Probability 20%
• Machine Learning 20%
• Learning System 20%

Earth and Planetary Sciences

• Land Cover 100%
• Remote Sensing 66%
• State of the Art 33%
• Machine Learning 33%
• Germany 33%
• Clustering 33%