Title | ||
---|---|---|
Fully Convolutional Network-Based Ensemble Method for Road Extraction From Aerial Images |
Abstract | ||
---|---|---|
This letter proposed a road extraction method based on fully convolutional networks (FCNs) with an ensemble strategy in order to solve the imbalance of road and background areas in aerial images. By utilizing the FCN, we consider road extraction as a semantic segmentation problem. In the network, the weight of the loss function is modified because of the imbalance between the roads and backgrounds, and there will be a larger punishment if roads are wrongly classified as background. Since it is difficult to determine an appropriate weight of the loss function for a given image, an ensemble method based on spatial consistency (SC) is proposed. The result maps that are obtained from the FCNs with different loss functions are fused in our proposed ensemble strategy, which also avoids the determination of weights. Our method is tested using the Massachusetts road data set, and it was proven to be effective compared with the base fully convolutional model according to our experimental result. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/LGRS.2019.2953523 | IEEE Geoscience and Remote Sensing Letters |
Keywords | DocType | Volume |
Roads,Mathematical model,Image segmentation,Semantics,Convolution,Data mining,Neural networks | Journal | 17 |
Issue | ISSN | Citations |
10 | 1545-598X | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiangrong Zhang | 1 | 493 | 48.70 |
Wenkang Ma | 2 | 0 | 0.34 |
Chen Li | 3 | 7 | 7.15 |
Jie Wu | 4 | 0 | 0.34 |
Xu Tang | 5 | 22 | 10.14 |
Licheng Jiao | 6 | 5698 | 475.84 |