An approach to the interpretation of aerial image

This paper presents an aerial image parsing approach. Firstly, scene categories of aerial image is extracted based on global feature-Spatial Envelope in the top-down step; secondly, the candidate proposals of object categories is classified in bottom-up step; finally, the bottom-up proposals are verified by top-down cues, and the parsing graph of the whole aerial image is obtained. The test on the aerial image dataset shows that the proposed approach can effectively segment the object categories from the aerial image in complex scene compared with the Bottom-Up detectors.