ABSTRACT
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.
Acknowledgement
The authors would like to acknowledge the support of His Highness Sheikh Mohamed bin Zayed Al Nahyan Program for Postgraduate Scholarships (Buhooth) under which the current research is conducted.
Disclosure statement
No potential conflict of interest was reported by the authors.