Sustainable development science satellite-1 (SDGSAT-1) is the first earth science satellite of the Chinese Academy of Sciences. It was successfully launched on November 5, 2021, aiming to achieve the global sustainable development goals and provide data for the study of interaction between humans and nature. Due to the poor penetration of visible light through cloud, many optical satellite remote sensing images are inevitably disturbed by cloud. Therefore, cloud mask production is an important processing step in optical remote sensing processing system. However, SDGSAT-1 multispectral images lack the short-wave infrared band required by the traditional cloud mask production algorithm, so the traditional cloud mask production algorithm is difficult to apply. Therefore, this paper proposes a cloud mask production method for SDGSAT-1 multispectral images based on fuzzy C-means (FCM) algorithm. The method selects the four spectral features of brightness, NDWI, NDVI, and HOT as input features. On this basis, the Mahalanobis distance is introduced, the results of K-means algorithm are used as the initial clustering center, and finally FCM algorithm is executed to obtain the final cloud mask. In the paper, the published SDGSAT-1 multispectral images are used to verify the performance of the proposed method and to compare it with other methods. The experimental results show that the average accuracy of the proposed method is 95.33%, which is higher than those of other methods.
为解决《联合国2030年可持续发展议程》实施过程中面临的数据量少与方法不完善的问题[7],中国科学院研制了可持续发展科学卫星1号(sustainable development science satellite-1,SDGSAT-1)。该卫星是全球首颗专门服务于该议程的卫星,也是中国科学院第一颗地球科学卫星,已于2021年11月5日成功发射升空,2021年12月20日正式发布首批影像。SDGSAT-1是一颗光学遥感卫星,其多光谱影像也会受到云层干扰,为减少资源浪费,精确提取影像中的目标地物,为实现可持续发展目标提供数据支撑,设计一套适合SDGSAT-1多光谱影像产品的云掩膜生成方法是至关重要的。
目前,遥感图像云掩膜生成算法主要可以分为光谱阈值法、纹理分析法、机器学习法等[8]。光谱阈值法是根据云和各地物在卫星传感器各波段下的反射率差异,设置多个检测阈值,进而将云与其他地物区分开。该方法简单易行,但是不同卫星的波段数量和波长不一致,不一定适用于每一颗卫星。Irish[9]针对Landsat 7影像提出自动云量评价算法,该算法以可见光、热红外等波段构造多个波段组合,得到精度较高的Landsat 7遥感图像云掩膜。Zhu和Woodcock[10]提出Fmask(function of mask)算法,该算法基于影像自身像元的光谱、温度特征构建云概率模型,动态计算云概率阈值来检测云像元,能够自适应不同的环境。
NguyenT T, HoangT D, PhamM T, et al. Monitoring agriculture areas with satellite images and deep learning[J]. Applied Soft Computing, 2020, 95: 106565. DOI: 10.1016/j.asoc.2020.106565 .
[2]
LvZ Y, LiuT F, BenediktssonJ A, et al. Land cover change detection techniques: very-high-resolution optical images: a review[J]. IEEE Geoscience and Remote Sensing Magazine, 2022, 10(1): 44-63. DOI: 10.1109/MGRS.2021.3088865 .
[3]
ZellwegerF, De FrenneP, LenoirJ, et al. Advances in microclimate ecology arising from remote sensing[J]. Trends in Ecology Evolution, 2019, 34(4): 327-341. DOI: 10.1016/j.tree.2018.12.012 .
[4]
LuX Z, ZengX, XuZ, et al. Improving the accuracy of near real-time seismic loss estimation using post-earthquake remote sensing images[J]. Earthquake Spectra, 2018, 34(3): 1219-1245. DOI: 10.1193/041417eqs072m .
[5]
AbdollahiM, IslamT, GuptaA, et al. An advanced forest fire danger forecasting system: integration of remote sensing and historical sources of ignition data[J]. Remote Sensing, 2018, 10(6): 923. DOI: 10.3390/rs10060923 .
[6]
BirkR, CamusW, ValentiE, et al. Synthetic aperture radar imaging systems[J]. IEEE Aerospace and Electronic Systems Magazine, 1995, 10(11): 15-23. DOI: 10.1109/62.473408 .
[7]
GuoH D. Big earth data: a new frontier in Earth and information sciences[J]. Big Earth Data, 2017, 1(1/2): 4-20. DOI: 10.1080/20964471.2017.1403062 .
IrishR R. Landsat 7 automatic cloud cover assessment[C]//Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VI. SPIE, 2000, 4049: 348-355. DOI:10.1117/12.410358 .
[10]
ZhuZ, WoodcockC E. Object-based cloud and cloud shadow detection in Landsat imagery[J]. Remote Sensing of Environment, 2012, 118: 83-94. DOI: 10.1016/j.rse.2011.10.028 .
[11]
ZhangX, CuiJ T, WangW S, et al. A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm[J]. Sensors (Basel, Switzerland), 2017, 17(7): 1474. DOI: 10.3390/s17071474 .
[12]
DongZ P, WangM, LiD R, et al. Cloud detection method for high resolution remote sensing imagery based on the spectrum and texture of superpixels[J]. Photogrammetric Engineering Remote Sensing, 2019, 85(4): 257-268. DOI: 10.14358/pers.85.4.257 .
[13]
DincS, RussellR, ParraL A C. Cloud region segmentation from all sky images using double K-means clustering[C]//2022 IEEE International Symposium on Multimedia (ISM), Italy. IEEE, 2022: 261-262. DOI: 10.1109/ISM55400.2022.00058 .
[14]
XiangP S. A cloud detection algorithm for MODIS images combining kmeans clustering and otsu method[J]. IOP Conference Series: Materials Science and Engineering, 2018, 392(6): 062199. DOI: 10.1088/1757-899x/392/6/062199 .
[15]
PingB, SuF Z, MengY S. A cloud and cloud shadow detection method based on fuzzy c-means algorithm[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 1714-1727. DOI: 10.1109/JSTARS.2020.2987844 .
[16]
PugazhenthiA, KumarL S. Cloud extraction from INSAT-3D satellite image by K-means and fuzzy C-means clustering algorithms[C]//2020 International Conference on System, Computation, Automation and Networking (ICSCAN). Pondicherry, India. IEEE, 2020: 1-4. DOI: 10.1109/ICSCAN49426.2020.9262330 .
GuoH D, ChenH Y, ChenL F, et al. Progress on CASEarth satellite development[J]. Chinese Journal of Space Science, 2020, 40(5): 707-717.DOI:10.11728/cjss2020.05.707 .
[19]
McFeetersS K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7): 1425-1432. DOI: 10.1080/01431169608948714 .
[20]
CarlsonT N, RipleyD A. On the relation between NDVI, fractional vegetation cover, and leaf area index[J]. Remote Sensing of Environment, 1997, 62(3): 241-252. DOI: 10.1016/S0034-4257(97)00104-1 .
[21]
ZhangY, GuindonB, CihlarJ. An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images[J]. Remote Sensing of Environment, 2002, 82(2/3): 173-187. DOI: 10.1016/S0034-4257(02)00034-2 .
YangC, BruzzoneL, SunF Y, et al. A fuzzy-statistics-based affinity propagation technique for clustering in multispectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(6): 2647-2659. DOI: 10.1109/TGRS.2010.2040035 .
[25]
CelebiM E, KingraviH A, VelaP A. A comparative study of efficient initialization methods for the K-means clustering algorithm[J]. Expert Systems with Applications, 2013, 40(1): 200-210. DOI: 10.1016/j.eswa.2012.07.021 .
[26]
BraatenJ D, CohenW B, YangZ Q. Automated cloud and cloud shadow identification in Landsat MSS imagery for temperate ecosystems[J]. Remote Sensing of Environment, 2015, 169: 128-138. DOI: 10.1016/j.rse.2015.08.006 .
[27]
XiongQ, WangY, LiuD Y, et al. A cloud detection approach based on hybrid multispectral features with dynamic thresholds for GF-1 remote sensing images[J]. Remote Sensing, 2020, 12(3): 450. DOI: 10.3390/rs12030450 .
[28]
DaviesD L, BouldinD W. A cluster separation measure[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979, PAMI-1(2): 224-227. DOI: 10.1109/TPAMI.1979.4766909 .
[29]
RousseeuwP J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20: 53-65. DOI: 10.1016/0377-0427(87)90125-7 .