摘要
深度估计作为三维重建、自动驾驶和视觉SLAM等领域中的关键环节,一直是计算机视觉领域研究的热点方向,其中无监督学习的单目深度估计技术由于具有方便部署、计算成本低等优点,受到了学术界和工业界的广泛关注.首先梳理了深度估计的基本知识及研究现状,简要介绍了基于参数学习、基于非参数学习、基于有监督学习、基于半监督学习和基于无监督学习的深度估计的优势与不足;其次全面总结了基于无监督学习的单目深度估计研究进展,按照结合可解释性掩膜、结合视觉里程计、结合先验辅助信息、结合生成式对抗网络和实时轻量级网络这五大类对无监督学习的单目深度估计进行归纳和总结,对典型的框架模型进行了介绍和分析;然后,介绍了基于无监督学习的单目深度估计在医学、自动驾驶、农业、军事等领域的应用;最后,简单介绍了用于无监督深度估计的常用数据集,提出了基于无监督学习的单目深度估计未来研究方向,并对这个快速发展领域中的各方向研究进行了展望.
Abstract
As the key point of 3D reconstruction,automatic driving and visual SLAM,depth estimation has always been a hot re-search direction in the field of computer vision,among which,monocular depth estimation technology based on unsupervised learning has been widely concerned by academia and industry because of its advantages of convenient deployment,low computa-tional cost and so on.Firstly,this paper reviews the basic knowledge and research actuality of depth estimation and briefly intro-duces the advantages and disadvantages of depth estimation based on parametric learning,non-parametric learning,supervised learning,semi-supervised learning and unsupervised learning.Secondly,the research progress of monocular depth estimation based on unsupervised learning is summarized comprehensively.The monocular depth estimation based on unsupervised learning is sum-marized according to five categories:combination of interpretable mask,combination of visual odometer,combination of prior auxi-liary information,combination of generated adversarial network and real-time lightweight network,and the typical framework model is introduced and compared.Then,the application of monocular depth estimation based on unsupervised learning in medi-cine,autonomous driving,agriculture,military and other fields is introduced.Finally,the common data sets used for unsupervised depth estimation are briefly introduced,and the future research direction of monocular depth estimation based on unsupervised learning is proposed,while the prospects of various research directions in this rapidly growing field are also prospected.
维普
万方数据