An automatic interpretation approach for high resolution urban remote sensing image using objects-based boosting model

For the purpose of interpreting urban remote sensing images more effectively and comprehensively, this paper proposes a new automatic approach using objects-based boosting model. The approach associates segmentation with recognition by constructing a hierarchical objects network at first, which effectively improves the problem of detecting targets with a modifiable sliding window existed in other methods. Then the probabilistic learning integrating multiple features including color, texture, shape and location is performed to train a multi-class classifier, and label all of the objects according to their classification values. The approach also applies spatial smoothing which incorporates contextual information to eliminate the adverse effects caused by background disturbance, occlusion and so on. After vectorization procedure, final result is given. Experiments demonstrate that proposed approach achieve high exactness and robustness in interpreting manifold urban remote sensing images.