Building segmentation of remote sensing images using deep neural networks and domain transform CRF

Automatic building segmentation from remote sensing images is critical in the remote sensing image semantic segmentation. The success of deep neural networks has led to advances in using fully convolutional neural networks (FCN) to extract buildings from the high-resolution image. However, the downsampling processing inevitably leads to loss of details of the segmentation results. To solve this problem, some methods try to refine the results of FCN by using probability graph models such as fully connected CRF (Conditional Random Fields). Nevertheless, many fully connected CRF based methods are too time-consuming and not suitable for building segmentation tasks in some situations. In this paper, we propose a novel time-efficient end-to-end CRF model with the domain transform algorithm called DT-CRF. In the proposed model, in order to accelerate the message passing in the mean-field approximate inference algorithm, we take the edge maps as the joint image for DT-CRF and use the domain transformation algorithm to calculate the pair-wise potential instead of the Gaussian kernel function. Meanwhile, we design a multi-task network which can generate masks and edges simultaneously, and the network can make the DT-CRF to easily optimize the segmentation results using model information. The evaluation of remote sensing image datasets verifies the time and space efficiency of the proposed DTCRF and demonstrates a distinct improvement.