文献类型：期刊文献

中文题名：Monocular depth estimation based on deep learning:An overview

英文题名：Monocular depth estimation based on deep learning: An overview

作者：Zhao, ChaoQiang[1];Sun, QiYu[1];Zhang, ChongZhen[1];Tang, Yang[1];Qian, Feng[1]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2020

卷号：63

期号：9

起止页码：1612

中文期刊名：Science China(Technological Sciences)

外文期刊名：SCIENCE CHINA-TECHNOLOGICAL SCIENCES

收录：;EI(收录号：20202508838960);Scopus;WOS:【SCI-EXPANDED(收录号:WOS:000539932800002)】；CSCD:【CSCD2019_2020】；

基金：This work was supported by the National Key Research and Development Program of China (Grant No. 2018YFC0809302), the National Natural Science Foundation of China (Grant Nos. 61988101, 61751305 and 61673176), the Fundamental Research Funds for the Central Universities (Grant No. JKH012016011), and the Programme of Introducing Talents of Discipline to Universities (the 111 Project) (Grant No. B17017).

语种：英文

中文关键词：autonomous systems;monocular depth estimation;deep learning;unsupervised learning

外文关键词：autonomous systems; monocular depth estimation; deep learning; unsupervised learning

摘要：Depth information is important for autonomous systems to perceive environments and estimate their own state.Traditional depth estimation methods,like structure from motion and stereo vision matching,are built on feature correspondences of multiple viewpoints.Meanwhile,the predicted depth maps are sparse.Inferring depth information from a single image(monocular depth estimation)is an ill-posed problem.With the rapid development of deep neural networks,monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy.Meanwhile,dense depth maps are estimated from single images by deep neural networks in an end-to-end manner.In order to improve the accuracy of depth estimation,different kinds of network frameworks,loss functions and training strategies are proposed subsequently.Therefore,we survey the current monocular depth estimation methods based on deep learning in this review.Initially,we conclude several widely used datasets and evaluation indicators in deep learning-based depth estimation.Furthermore,we review some representative existing methods according to different training manners:supervised,unsupervised and semi-supervised.Finally,we discuss the challenges and provide some ideas for future researches in monocular depth estimation.
Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and stereo vision matching, are built on feature correspondences of multiple viewpoints. Meanwhile, the predicted depth maps are sparse. Inferring depth information from a single image (monocular depth estimation) is an ill-posed problem. With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy. Meanwhile, dense depth maps are estimated from single images by deep neural networks in an end-to-end manner. In order to improve the accuracy of depth estimation, different kinds of network frameworks, loss functions and training strategies are proposed subsequently. Therefore, we survey the current monocular depth estimation methods based on deep learning in this review. Initially, we conclude several widely used datasets and evaluation indicators in deep learning-based depth estimation. Furthermore, we review some representative existing methods according to different training manners: supervised, unsupervised and semi-supervised. Finally, we discuss the challenges and provide some ideas for future researches in monocular depth estimation.