使用深度学习网络U-Net进行道路提取的研究与讨论  

Research and discussion on road extraction with deep learning network U-Net

作　　者：杨宁 金生[1] YANG Ning;JIN Sheng(College of Hydraulics Engineering,Dalian University of Technology,Dalian 116000,Liaoning,China)

机构地区：[1]大连理工大学水利工程学院,辽宁大连116000

出　　处：《黑龙江大学工程学报》2020年第4期1-8,共8页Journal of Engineering of Heilongjiang University

基　　金：国家自然科学基金项目(51739011)。

摘　　要：道路提取在许多领域都有重要的应用,是一个非常必要并且活跃的研究课题。在以往的道路提取任务中通常采用人工标注的方法,但人工标注是一项复杂的工作,而且不能保证结果的准确和精度。随着计算机计算能力的提升,形态学算法、计算机视觉、机器学习等方法开始被用于道路提取和标记任务中。讨论了道路提取过程中常见的问题和可行的解决方案。并利用马萨诸塞道路数据集数据库进行了U-Net道路提取任务的实验。在缺乏训练样本和训练时间较短的情况下,证明了二元交叉熵损失和IoU损失函数的组合是完成该任务的可能方法。Road extraction has important applications in many aspects,which is a very necessary and active research topic.In the past,manual marking of road extraction was laborious and could not guarantee accuracy.With the development of computer computing power,morphological algorithm,computer vision,machine learning and other methods began to be used to extract and mark road chaos.Common issues and feasible solutions in the road extraction process are discussed.We also conducted the experiment of road extraction task via U-Net with the database of Massachusetts Roads Dataset.Under the lack of training samples and short training time the combination of two loss functions,Binary Cross entropy loss and IoU loss,is the possible way to complete the task.

关 键 词：深度学习 计算机视觉 道路提取 神经网络 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]