Encoder-decoder structure based on conditional random field for building extraction in remote sensing images

Building extraction is a binary classification task that separates the building area from the background in remote sensing images. The conditional random field (CRF) is directly modelled by the maximum posterior probability, which can make full use of the spatial neighbourhood information of both labelled and observed images. CRF is widely used in building footprint extraction. However, edge oversmoothing still exists when CRF is directly used to extract buildings from high spatial resolution (HSR) remote sensing images. Based on a computer vision multi-scale semantic segmentation network (D-LinkNet), a novel building extraction framework is proposed, named multiscale-aware and segmentation-prior conditional random fields (MSCRF). To solve the problem of losing building details in the downsampling process, D-LinkNet connecting the encoder and decoder is correspondingly used to generate the unary potential. By integrating multi-scale building features in the central module, D-LinkNet can integrate multiscale contextual information without loss of resolution. For the pairwise potential, the segmentation prior is fused to alleviate the influence of spectral diversity between the building and the background area. Moreover, the local class label cost term is introduced. The clear boundaries of the buildings are obtained by using the larger-scale context information. The experimental results demonstrate that the proposed MSCRF framework is superior to the state-of-the-art methods and performs well for building extraction of complex scenes.

Download Full-text

Remote Sensing Image Ship Detection under Complex Sea Conditions Based on Deep Semantic Segmentation

Remote Sensing ◽

10.3390/rs12040625 ◽

2020 ◽

Vol 12 (4) ◽

pp. 625 ◽

Cited By ~ 3

Author(s):

Yantong Chen ◽

Yuyang Li ◽

Junsheng Wang ◽

Weinan Chen ◽

Xianzhong Zhang

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Random Field ◽

Conditional Random Field ◽

Remote Sensing Image ◽

Convolution Neural Network ◽

Remote Sensing Images ◽

Ship Detection ◽

Deep Convolution Neural Network ◽

End To End

Under complex sea conditions, ship detection from remote sensing images is easily affected by sea clutter, thin clouds, and islands, resulting in unreliable detection results. In this paper, an end-to-end convolution neural network method is introduced that combines a deep convolution neural network with a fully connected conditional random field. Based on the Resnet architecture, the remote sensing image is roughly segmented using a deep convolution neural network as the input. Using the Gaussian pairwise potential method and mean field approximation theorem, a conditional random field is established as the output of the recurrent neural network, thus achieving end-to-end connection. We compared the proposed method with other state-of-the-art methods on the dataset established by Google Earth and NWPU-RESISC45. Experiments show that the target detection accuracy of the proposed method and the ability of capturing fine details of images are improved. The mean intersection over union is 83.2% compared with other models, which indicates obvious advantages. The proposed method is fast enough to meet the needs for ship detection in remote sensing images.

Download Full-text

MULTI-SOURCE MULTI-SCALE HIERARCHICAL CONDITIONAL RANDOM FIELD MODEL FOR REMOTE SENSING IMAGE CLASSIFICATION

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsannals-ii-3-w4-293-2015 ◽

2015 ◽

Vol II-3/W4 ◽

pp. 293-300 ◽

Cited By ~ 2

Author(s):

Z. Zhang ◽

M. Y. Yang ◽

M. Zhou

Keyword(s):

Remote Sensing ◽

Random Field ◽

Image Classification ◽

Conditional Random Field ◽

Remote Sensing Images ◽

Cloud Data ◽

Multi Scale ◽

Sensing Applications ◽

Remote Sensing Image Classification ◽

Conditional Random Field Model

Fusion of remote sensing images and LiDAR data provides complimentary information for the remote sensing applications, such as object classification and recognition. In this paper, we propose a novel multi-source multi-scale hierarchical conditional random field (MSMSH-CRF) model to integrate features extracted from remote sensing images and LiDAR point cloud data for image classification. MSMSH-CRF model is then constructed to exploit the features, category compatibility of multi-scale images and the category consistency of multi-source data based on the regions. The output of the model represents the optimal results of the image classification. We have evaluated the precision and robustness of the proposed method on airborne data, which shows that the proposed method outperforms standard CRF method.

Download Full-text