Road segmentation of cross-modal remote sensing images using deep segmentation network and transfer learning
Purpose: The purpose of this paper is to study the road segmentation problem of cross-modal remote sensing images. Design/methodology/approach: First, the baseline network based on the U-net is trained under a large-scale dataset of remote sensing imagery. Then, the cross-modal training data are used to fine-tune the first two convolutional layers of the pre-trained network to achieve the adaptation to the local features of the cross-modal data. For the cross-modal data of different band, an autoencoder is designed to achieve data conversion and local feature extraction. Findings: The experimental results show the effectiveness and practicability of the proposed method. Compared with the ordinary method, the proposed method gets much better metrics. Originality/value: The originality is the transfer learning strategy that fine-tunes the low-level layers for the cross-modal data application. The proposed method can achieve satisfied road segmentation with a small amount of cross-modal training data, so that is has a good application value. Still, for the similar application of cross-modal data, the idea provided by this paper is helpful.
Year of publication: |
2019
|
---|---|
Authors: | He, Hao ; Yang, Dongfang ; Wang, Shicheng ; Wang, Shuyang ; Liu, Xing |
Published in: |
Industrial Robot: the international journal of robotics research and application. - Emerald, ISSN 0143-991X, ZDB-ID 2025337-0. - Vol. 46.2019, 3 (20.05.), p. 384-390
|
Publisher: |
Emerald |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Si, Jiajia, (2022)
-
Wang, Fang, (2018)
-
Cost-effectiveness of bariatric surgical procedures for the treatment of severe obesity
Wang, Bruce C. M., (2014)
- More ...