中国空间科学技术 ›› 2021, Vol. 41 ›› Issue (2): 71-76.doi: 10.16708/j.cnki.1000-758X.2021.0024

• 技术交流 • 上一篇    下一篇

基于结构化特征的遥感影像道路智能提取方法

王文庆,胡若同,贺浩,杨东方, 马晓华   

  1. 1 西安邮电大学 自动化学院,西安710121
    2 火箭军工程大学 导弹工程学院,西安710025
    3 火箭军装备部驻南京地区第二军事代表室 南京210023
  • 出版日期:2021-04-25 发布日期:2021-04-07

Structural road extraction method for remote sensing image

WANG Wenqing,HU Ruotong,HE Hao,YANG Dongfang,MA Xiaohua   

  1. 1 School of Automation, Xi′an University of Posts & Telecommunications,Xi′an 710121,China
    2 The Department of Control Engineering,The Rocket Force University of Engineering,Xi′an 710025,China
    3 The Second Military Representative Office of the Rocket Army Equipment Department in Nanjing, Nanjing 210023, China
  • Online:2021-04-25 Published:2021-04-07

摘要: 遥感影像道路提取是空基平台对地智能理解的重要内容。利用道路网络特有的结构特点,从道路网络结构相似性损失函数和结构化特征算子两个方面,提出了一种结构化特征表示的道路提取方法。首先,针对遥感图像中道路目标占比较小的特点,设计了深度较浅、分辨率较高的编解码网络结构;其次,引入道路网络的结构相似性(SSIM)损失,并提出一种道路结构化特征描述子,对道路提取结果进行优化;最后,在道路数据集上进行了对比试验,所提出的结构化特征提取方法的精度和F1score分别达到了85.3%和84.6%。

关键词: 深度学习, 遥感, 道路提取, 结构化特征描述子, 语义分割

Abstract: The road extraction of the remote sensing image plays an important role in the intelligent understanding of the ground. According to the structural characteristics of the road features, a road extraction method with structure similarity loss function and structural descriptor was proposed. Firstly, the proportion of the road is usually small in the remote sensing image, a shallow encoder-decoder based segment network with high resolution was proposed. Secondly, the structural similarity(SSIM) was introduced to the loss function and as the existing methods of road extraction network are mostly based on the comparison of the prediction and ground truth of each pixel value, the structural descriptor joined the task of road extraction as an optimization step which improves the ability of the network to make use of the structural information. Lastly, experiments on Massachusetts road dataset show that the proposed network gets the precision and F1-score up to 85.3% and 84.6%.

Key words: deep learning, remote sensing , road extraction, structural descriptor, semantic segmentation