Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis

1 Introduction With the rapid development of remotely sensed (RS) information collection, transfer and storage in the last two decades, the limitation of RS application is becom- ing weaker because of availability of multiple RS data sources of increasingly finer spatial, temporal, spectral and radiant dimensions. In the high spatial-resolution RS imagery, characteristics of land-cover are fairly clear such as spatial shape, structure, texture, etc., so the mixture of different land covers …

Review of remotely sensed imagery classification patterns based on object-oriented image analysis

With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.