Hierarchical fusion of optical and dual-polarized SAR on impervious surface mapping at city scale

Sun, Guifan; Ji, Cheng; Zhang, Aizhu; Jia, Xiuping; Yao, Yanjuan; Jiao, Zhijun

doi:10.1016/j.isprsjprs.2021.12.008

Cited by 27 publications

(12 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, additional information is required to improve the mapping accuracy of impervious surfaces. SAR data can provide complementary information for optical images due to its all-day and all-weather capabilities at high spatial resolution and low cost [88][89][90]. Zhang et al [80] combined multi-source and multi-sensor remote sensing datasets (i.e., Landsat ETM+, SPOT-5 and ASAR and ALOS PALSAR, SPOT-5, and TerraSAR-X) to estimate impervious surfaces in Pearl River Delta.…”

Section: Cloud and Snow Contaminationsmentioning

confidence: 99%

Emerging Issues in Mapping Urban Impervious Surfaces Using High-Resolution Remote Sensing Images

Shao

Cheng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Urban impervious surface (UIS) is a key parameter in climate change, environmental change, and sustainability. UIS extraction has been evolving rapidly in the past decades. However, high-resolution impervious surface mapping is a long-term need. There is an urgent requirement for impervious surface mapping from high-resolution remote sensing imagery. In this paper, we compare current extraction methods in terms of extraction units and extraction models and summarize their strengths and limitations. We discuss the challenges in impervious surface estimation from high spatial resolution remote sensing imagery in terms of selection of spatial resolution, spectral band, and extraction method. The uncertainties caused by clouds and snow, shadows, and vegetation occlusion are also analyzed. Automated sample labeling and remote sensing domain knowledge are the main directions in impervious surface extraction using deep learning methods. We should also focus on using continuous time series of high-resolution imagery and multi-source satellite imagery for dynamic monitoring of impervious surfaces.

show abstract

Section: Cloud and Snow Contaminationsmentioning

confidence: 99%

Emerging Issues in Mapping Urban Impervious Surfaces Using High-Resolution Remote Sensing Images

Shao

Cheng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…And it provides limited information compared to rich spectral information of optical remote sensing. Therefore, researchers have proposed various methods for fusing optical and SAR data for ULC classification, primarily at three different levels: pixel level, feature level, and decision level [11]. Without feature extraction, pixel-level fusion refers to the overlay of optical and SAR data at the pixel level [12].…”

Section: Introductionmentioning

confidence: 99%

“…The combination of characteristics obtained from optical and SAR data is known as a feature-level fusion [10,13]. Support vector machine (SVM), random forest (RF), and deep network methods are common approaches used for feature-level fusion [11,14]. Decision-level fusion refers to making decisions based on the classification results from both optical and SAR sources.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

WCDL: A Weighted Cloud Dictionary Learning Method for Fusing Cloud-Contaminated Optical and SAR Images

Ling

Zhang

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Abstract-Cloud cover hinders accurate and timely monitoring of urban land cover (ULC). The combination of synthetic aperture radar (SAR) and optical data without cloud contamination has demonstrated promising performance in previous research. However, ULC studies on cloud-prone areas are scarce despite the inevitability of cloud cover, especially in the tropics and subtropics. This study proposes a novel weighted cloud dictionary learning method (WCDL) for fusing optical and SAR data for the ULC classification in cloud-prone areas. We innovatively propose a cloud probability weighting model and a pixel-wise cloud dictionary learning method that take the interference disparities at various cloud probability levels into account to mitigate cloud interference. Experiments reveal that the overall accuracy (OA) of fused data rises by more than 6% and 20% compared to single SAR and optical data, respectively. This method considerably improved by 3% in OA compared with other methods that directly stitch optical and SAR data together regardless of cloud interference. It improves almost all land covers producer's accuracy (PA) and user's accuracy (UA) by up to 9%. Ablation studies further show the cloud probability weighting model improves the OA of all classifiers by up to 5%. And the pixel-wise cloud dictionary learning model improves by more than 2% in OA for all cloud conditions, and the UA and PA are enhanced by up to 9% and 10%. The proposed WCDL method will serve as a reference for fusing cloud-contaminated optical and SAR data and timely, continuous, and accurate land surface monitoring in cloudy areas.

show abstract

“…For example, Zhang et al [13] extracted UIS by fusing texture features of optical and SAR images, and achieved better results than using optical data alone. Then in order to reduce the influence of shadows on Sentinel-2 image on the extraction accuracy of UIS, Sun et al [14] fused the polarization features of Sentinel-1 and the multispectral features of Sentinel-2, and proposed a hierarchical UIS extraction framework. And with the open source of Sentinel-1 data, SAR data has gradually become another important data source for UIS extraction, which has been verified in largescale UIS extraction [15], [16].…”

mentioning

confidence: 99%

Urban Impervious Surface Extraction Using Seasonal Time Series SAR Images

Shao

Teng

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Urban impervious surface (UIS) is an essential indicator to measure urban ecology, and understanding its temporal and spatial distribution is of great significance for alleviating urban diseases such as heat island. Although remote sensing techniques have been widely used to extract UIS, the capability of synthetic aperture radar (SAR) technology in UIS extraction has not been thoroughly investigated. Accordingly, this study systematically analyzed the role of the backscattering and interferometric coherence features of dual polarized (VH/VV) SAR in UIS extraction, taking Tianjin city, China, as a study case. Specifically, we used seasonal time series Sentinel-1B backscattering and coherence images to extract UIS via two object-based classifiers. We further investigated the seasonal, polarization, and precipitation effects on UIS extraction using SAR images. Our findings suggested that, for coherence images, the extraction accuracy of UIS in summer is the highest, while for backscattering, that in spring and winter are the highest. Our results also suggested that VH polarization is more suitable for UIS extraction compared with VV polarization. These findings of this study confirmed the utility and effectiveness of time series SAR backscattering and coherence images in UIS extraction, providing an essential reference for UIS extraction in other places with a similar climate. We encourage more efforts to be made towards UIS extraction using SAR images and towards designing a filling scheme for the UIS extraction in a continuous manner, especially in cloudy and rainy areas.Index Terms-Time series SAR images, coherence images, SAR backscattering, urban impervious surface (UIS), seasonal effect. I. INTRODUCTIONC HINA has experienced rapid urbanization in the past 40 years since the implementation of the reform and opening-up policy in 1978 [1]. In 2021, the urbanization rate of China has reached 63.89% and is expected to reach 75% Manuscript

show abstract

Hierarchical fusion of optical and dual-polarized SAR on impervious surface mapping at city scale

Cited by 27 publications

References 48 publications

Emerging Issues in Mapping Urban Impervious Surfaces Using High-Resolution Remote Sensing Images

Emerging Issues in Mapping Urban Impervious Surfaces Using High-Resolution Remote Sensing Images

WCDL: A Weighted Cloud Dictionary Learning Method for Fusing Cloud-Contaminated Optical and SAR Images

Urban Impervious Surface Extraction Using Seasonal Time Series SAR Images

Contact Info

Product

Resources

About