共 198 条
Application of Deep Learning in Multitemporal Remote Sensing Image Classification
被引:25
作者:
Cheng, Xinglu
[1
,2
,3
,4
]
Sun, Yonghua
[1
,2
,3
,4
]
Zhang, Wangkuan
[1
,2
,3
,4
]
Wang, Yihan
[1
,2
,3
,4
]
Cao, Xuyue
[1
,2
,3
,4
]
Wang, Yanzhao
[1
,2
,3
,4
]
机构:
[1] Capital Normal Univ, Beijing Lab Water Resources Secur, Beijing 100048, Peoples R China
[2] Capital Normal Univ, Coll Resources Environm & Tourism, Beijing 100048, Peoples R China
[3] Capital Normal Univ, State Key Lab Urban Environm Proc & Digital Simula, Beijing 100048, Peoples R China
[4] Minist Educ, Key Lab Informat Acquisit & Applicat 3D, Beijing 100048, Peoples R China
关键词:
deep learning;
multitemporal remote sensing images;
remote sensing classification;
LAND-COVER CLASSIFICATION;
CONVOLUTIONAL NEURAL-NETWORK;
SUPPORT VECTOR MACHINE;
TIME-SERIES;
ATMOSPHERIC CORRECTION;
SEMANTIC SEGMENTATION;
SPARTINA-ALTERNIFLORA;
RANDOM FOREST;
SENTINEL-1;
ALGORITHMS;
D O I:
10.3390/rs15153859
中图分类号:
X [环境科学、安全科学];
学科分类号:
08 ;
0830 ;
摘要:
The rapid advancement of remote sensing technology has significantly enhanced the temporal resolution of remote sensing data. Multitemporal remote sensing image classification can extract richer spatiotemporal features. However, this also presents the challenge of mining massive data features. In response to this challenge, deep learning methods have become prevalent in machine learning and have been widely applied in remote sensing due to their ability to handle large datasets. The combination of remote sensing classification and deep learning has become a trend and has developed rapidly in recent years. However, there is a lack of summary and discussion on the research status and trends in multitemporal images. This review retrieved and screened 170 papers and proposed a research framework for this field. It includes retrieval statistics from existing research, preparation of multitemporal datasets, sample acquisition, an overview of typical models, and a discussion of application status. Finally, this paper discusses current problems and puts forward prospects for the future from three directions: adaptability between deep learning models and multitemporal classification, prospects for high-resolution image applications, and large-scale monitoring and model generalization. The aim is to help readers quickly understand the research process and application status of this field.
引用
收藏
页数:39
相关论文