CMGFNet: A deep cross-modal gated fusion network for building extraction from very high-resolution remote sensing images

2022 ◽  
Vol 184 ◽  
pp. 96-115
Author(s):  
Hamidreza Hosseinpour ◽  
Farhad Samadzadegan ◽  
Farzaneh Dadrass Javan
2020 ◽  
Vol 12 (18) ◽  
pp. 2985 ◽  
Author(s):  
Yeneng Lin ◽  
Dongyun Xu ◽  
Nan Wang ◽  
Zhou Shi ◽  
Qiuxiao Chen

Automatic road extraction from very-high-resolution remote sensing images has become a popular topic in a wide range of fields. Convolutional neural networks are often used for this purpose. However, many network models do not achieve satisfactory extraction results because of the elongated nature and varying sizes of roads in images. To improve the accuracy of road extraction, this paper proposes a deep learning model based on the structure of Deeplab v3. It incorporates squeeze-and-excitation (SE) module to apply weights to different feature channels, and performs multi-scale upsampling to preserve and fuse shallow and deep information. To solve the problems associated with unbalanced road samples in images, different loss functions and backbone network modules are tested in the model’s training process. Compared with cross entropy, dice loss can improve the performance of the model during training and prediction. The SE module is superior to ResNext and ResNet in improving the integrity of the extracted roads. Experimental results obtained using the Massachusetts Roads Dataset show that the proposed model (Nested SE-Deeplab) improves F1-Score by 2.4% and Intersection over Union by 2.0% compared with FC-DenseNet. The proposed model also achieves better segmentation accuracy in road extraction compared with other mainstream deep-learning models including Deeplab v3, SegNet, and UNet.


2020 ◽  
Vol 12 (6) ◽  
pp. 1050 ◽  
Author(s):  
Zhenfeng Shao ◽  
Penghao Tang ◽  
Zhongyuan Wang ◽  
Nayyer Saleem ◽  
Sarath Yam ◽  
...  

Building extraction from high-resolution remote sensing images is of great significance in urban planning, population statistics, and economic forecast. However, automatic building extraction from high-resolution remote sensing images remains challenging. On the one hand, the extraction results of buildings are partially missing and incomplete due to the variation of hue and texture within a building, especially when the building size is large. On the other hand, the building footprint extraction of buildings with complex shapes is often inaccurate. To this end, we propose a new deep learning network, termed Building Residual Refine Network (BRRNet), for accurate and complete building extraction. BRRNet consists of such two parts as the prediction module and the residual refinement module. The prediction module based on an encoder–decoder structure introduces atrous convolution of different dilation rates to extract more global features, by gradually increasing the receptive field during feature extraction. When the prediction module outputs the preliminary building extraction results of the input image, the residual refinement module takes the output of the prediction module as an input. It further refines the residual between the result of the prediction module and the real result, thus improving the accuracy of building extraction. In addition, we use Dice loss as the loss function during training, which effectively alleviates the problem of data imbalance and further improves the accuracy of building extraction. The experimental results on Massachusetts Building Dataset show that our method outperforms other five state-of-the-art methods in terms of the integrity of buildings and the accuracy of complex building footprints.


2020 ◽  
Vol 86 (4) ◽  
pp. 235-245 ◽  
Author(s):  
Ka Zhang ◽  
Hui Chen ◽  
Wen Xiao ◽  
Yehua Sheng ◽  
Dong Su ◽  
...  

This article proposes a new building extraction method from high-resolution remote sensing images, based on GrabCut, which can automatically select foreground and background samples under the constraints of building elevation contour lines. First the image is rotated according to the direction of pixel displacement calculated by the rational function Model. Second, the Canny operator, combined with morphology and the Hough transform, is used to extract the building's elevation contour lines. Third, seed points and interesting points of the building are selected under the constraint of the contour line and the geodesic distance. Then foreground and background samples are obtained according to these points. Fourth, GrabCut and geometric features are used to carry out image segmentation and extract buildings. Finally, WorldView satellite images are used to verify the proposed method. Experimental results show that the average accuracy can reach 86.34%, which is 15.12% higher than other building extraction methods.


2017 ◽  
Vol 4 (2) ◽  
pp. 108 ◽  
Author(s):  
Yupeng Yan ◽  
Manu Sethi ◽  
Anand Rangarajan ◽  
Ranga Raju Vatsavai ◽  
Sanjay Ranka

Sign in / Sign up

Export Citation Format

Share Document