TY - JOUR
T1 - Deep-Learning-Based Semantic Segmentation of Remote Sensing Images
T2 - A Survey
AU - Huang, Liwei
AU - Jiang, Bitao
AU - Lv, Shouye
AU - Liu, Yanbo
AU - Fu, Ying
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Semantic segmentation of remote sensing images (SSRSIs), which aims to assign a category to each pixel in remote sensing images, plays a vital role in a broad range of applications, such as environmental monitoring, urban planning, and land resource utilization. Recently, with the successful application of deep learning in remote sensing, a substantial amount of work has been aimed at developing SSRSI methods using deep learning models. In this survey, we provide a comprehensive review of SSRSI. First, we review the current mainstream semantic segmentation models based on deep learning. Next, we analyze the main challenges faced by SSRSI and comprehensively summarize the current research status of deep-learning-based SSRSI, especially some new directions in SSRSI are outlined, including semisupervised and weakly-supervised SSRSI, unsupervised domain adaption in SSRSI, multimodal data-fusion-based SSRSI, and pretrained models for SSRSI. Then, we examine the most widely used datasets and metrics and review the quantitative results and experimental performance of some representative methods of SSRSI. Finally, we discuss promising future research directions in this area.
AB - Semantic segmentation of remote sensing images (SSRSIs), which aims to assign a category to each pixel in remote sensing images, plays a vital role in a broad range of applications, such as environmental monitoring, urban planning, and land resource utilization. Recently, with the successful application of deep learning in remote sensing, a substantial amount of work has been aimed at developing SSRSI methods using deep learning models. In this survey, we provide a comprehensive review of SSRSI. First, we review the current mainstream semantic segmentation models based on deep learning. Next, we analyze the main challenges faced by SSRSI and comprehensively summarize the current research status of deep-learning-based SSRSI, especially some new directions in SSRSI are outlined, including semisupervised and weakly-supervised SSRSI, unsupervised domain adaption in SSRSI, multimodal data-fusion-based SSRSI, and pretrained models for SSRSI. Then, we examine the most widely used datasets and metrics and review the quantitative results and experimental performance of some representative methods of SSRSI. Finally, we discuss promising future research directions in this area.
KW - Deep learning
KW - multimodal fusion
KW - pretrained models
KW - remote sensing images
KW - semantic segmentation
KW - semisupervised
KW - unsupervised domain adaptation
KW - weakly-supervised
UR - http://www.scopus.com/inward/record.url?scp=85179029615&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2023.3335891
DO - 10.1109/JSTARS.2023.3335891
M3 - Article
AN - SCOPUS:85179029615
SN - 1939-1404
VL - 17
SP - 8370
EP - 8396
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ER -