A deep learning approach for unsupervised domain adaptation in multitemporal remote sensing images

摘要

In this paper, we propose a novel deep convex network method for domain adaptation in multitemporal remote sensing imagery. We fuse the capabilities of the extreme learning machine (ELM) classifier and local feature descriptor techniques to boost the classification accuracy. We use the Affine Scale Invariant Feature Transform (ASIFT) to extract the key points from the image pair, i.e. source and target domain images. The neural network consist of two layers, one layer uses the keypoints extracted by ASIFT to map the training points of the source image to the target image, while layer 2 is used for the purpose of classification. Experimental results obtained on multitemporal VHR images acquired by the IKONOS2 confirm the promising capability of the proposed method.