A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks

This paper presents a supervised, hierarchical remote-sensing image segmentation technique using a committee of multi-scale convolutional neural networks. With existing techniques, segmentation is achieved through fine-tuning a set of predefined feature detectors. However, such a solution is not robust since the introduction of new sensors or applications would require novel features and techniques to be developed. Conversely, the proposed method achieves segmentation through a set of learnt feature detectors. In order to learn feature detectors, the proposed method exploits a committee of convolutional neural networks that perform multi-scale analysis on each band in order to derive individual confidence maps on region boundaries. Confidence maps are then inter-fused in order to produce a fused confidence map. Furthermore, the fused map is intra-fused using a morphological scheme into a hierarchical segmentation map. The proposed method is quantitatively compared to baseline techniques on a publicly available data set. The results presented in this paper highlight the improved accuracy of the proposed method.