Road Extraction from High Resolution Image with Deep Convolution Network—A Case Study of GF-2 Image

Proceedings

Luo, Lun¹  Zhang, Yu-Ze²  Xia, Wei³  Liu, Jian⁴ 

[1] Available online: https://sciforum.net/conference/ecrs-2;Author to whom correspondence should be addressed.;National Engineering Laboratory for Transportation Safety and Emergency Informatics, China Transport Telecommunications & Information Center, Beijing 100011, China;Presented at the 2nd International Electronic Conference on Remote Sensing, 22 March–5 April 2018

关键词: big data h;    ling;    road extraction;    deep convolution network;    remote sensing imagery;   

DOI  :  10.3390/ecrs-2-05138

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

Recently, with the development of remote sensing and computer techniques, automatic and accurate road extraction is becoming feasible for practical usage. Nowadays, accurate extraction of road information from satellite data has become one of the most popular topics in both remote sensing and transportation fields. It is very useful for applying this technique to fast map updating, construction supervision, and so on. However, as there is usually a huge volume of information provided by remote sensing data, an efficient method to refine the big volume of data is important in corresponding applications. We apply deep convolution network to perform an image segmentation approach, as a solution for extracting road networks from high resolution images. In order to take advantage of deep learning, we study the methods of generating representative training and testing datasets, and develop semi-supervised leaning skills to enhance the data scale. The extraction of the satellite images that are affected by color distortion is also studied, in order to make the method more robust for more applicational fields. The GF-2 satellite data is used for experiments, as its images may show optical distortion in small pieces. Experiments in this paper showed that, the proposed solution successfully identifies road networks from complex situations with a total accuracy of more than 80% in discriminable areas.

【 授权许可】

CC BY