中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data

文献类型：期刊论文

作者Jiang, Jingchao1; Qin, Cheng-Zhi2,3; Yu, Juan4; Cheng, Changxiu5; Liu, Junzhi6; Huang, Jingzhou1
刊名REMOTE SENSING
出版日期2020-03-02
卷号12期号:6页码:14
关键词urban flooding waterlogging depth video image synthetic image data reference object detection convolutional neural network
DOI10.3390/rs12061014
通讯作者Cheng, Changxiu(chengcx@bnu.edu.cn)
英文摘要Reference objects in video images can be used to indicate urban waterlogging depths. The detection of reference objects is the key step to obtain waterlogging depths from video images. Object detection models with convolutional neural networks (CNNs) have been utilized to detect reference objects. These models require a large number of labeled images as the training data to ensure the applicability at a city scale. However, it is hard to collect a sufficient number of urban flooding images containing valuable reference objects, and manually labeling images is time-consuming and expensive. To solve the problem, we present a method to synthesize image data as the training data. Firstly, original images containing reference objects and original images with water surfaces are collected from open data sources, and reference objects and water surfaces are cropped from these original images. Secondly, the reference objects and water surfaces are further enriched via data augmentation techniques to ensure the diversity. Finally, the enriched reference objects and water surfaces are combined to generate a synthetic image dataset with annotations. The synthetic image dataset is further used for training an object detection model with CNN. The waterlogging depths are calculated based on the reference objects detected by the trained model. A real video dataset and an artificial image dataset are used to evaluate the effectiveness of the proposed method. The results show that the detection model trained using the synthetic image dataset can effectively detect reference objects from images, and it can achieve acceptable accuracies of waterlogging depths based on the detected reference objects. The proposed method has the potential to monitor waterlogging depths at a city scale.
WOS关键词SOCIAL MEDIA ; FLOOD ; VISION ; FRAMEWORK
资助项目National Key Research and Development Plan of China[2019YFA0606901] ; National Natural Science Foundation of China[41601423] ; National Natural Science Foundation of China[41601413] ; National Natural Science Foundation of China[61702148]
WOS研究方向Remote Sensing
语种英语
WOS记录号WOS:000526820600116
出版者MDPI
资助机构National Key Research and Development Plan of China ; National Natural Science Foundation of China
源URL[http://ir.igsnrr.ac.cn/handle/311030/159850]  
专题中国科学院地理科学与资源研究所
通讯作者Cheng, Changxiu
作者单位1.Hangzhou Dianzi Univ, Sch Automat, Smart City Res Ctr, Hangzhou 310012, Peoples R China
2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
3.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Peoples R China
4.Zhejiang Normal Univ, Coll Math & Comp Sci, Jinhua 321004, Zhejiang, Peoples R China
5.Beijing Normal Univ, State Key Lab Earth Surface Proc & Resource Ecol, Beijing 100875, Peoples R China
6.Nanjing Normal Univ, Key Lab Virtual Geog Environm, Minist Educ, Nanjing 210023, Peoples R China
推荐引用方式
GB/T 7714		 Jiang, Jingchao,Qin, Cheng-Zhi,Yu, Juan,et al. Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data[J]. REMOTE SENSING,2020,12(6):14.
APA Jiang, Jingchao,Qin, Cheng-Zhi,Yu, Juan,Cheng, Changxiu,Liu, Junzhi,&Huang, Jingzhou.(2020).Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data.REMOTE SENSING,12(6),14.
MLA Jiang, Jingchao,et al."Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data".REMOTE SENSING 12.6(2020):14.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。