基于多频率极化SAR影像的洪河国家级自然保护区植被信息提取
|
摘要
植被是湿地生态系统健康状况的"晴雨表",明晰湿地中植被的时空分布,是湿地修复与重建、保护与合理利用的前提和基础。以洪河国家级保护区为研究区,利用全极化C-band Radarsat-2和L-band PALSAR数据,根据极化合成孔径雷达(synthetic aperture radar,SAR)目标分解理论,提取了该保护区不同波长的极化分解参数和特征参量,整合为多源极化SAR数据集,利用多尺度迭代分割算法和Random Forest机器学习算法,构建了研究区中植被的遥感识别模型,实现了对研究区中植被的高精度分类,并对比分析了不同频率SAR数据集在植被识别精度上的差异。研究结果表明,利用整合PALSAR和Radarsat-2极化数据集,获取的植被遥感分类结果的总体分类精度为86.77%,比利用PALSAR极化数据集的分类结果精度提高了15%,但是其与利用Radarsat-2极化数据集的分类结果精度差异不显著;浅水草本沼泽的生产精度达到了90.91%,深水草本沼泽的用户精度为90.63%;C-band PALSAR数据比L-band PALSAR数据更适用于高精度识别洪河国家级自然保护区中的植被。
Vegetation is a"barometer"of health status of wetland ecosystem. Exploration of the spatial-temporal distribution of vegetation is the premise and foundation of wetland ecological restoration and reconstruction, wetland resource protection and rational utilization. This paper extracted different wavelength polarimetric decomposition parameters of Honghe National Nature Reserve based on polarimetric synthetic aperture radar(SAR) target decomposition theory, and integrated C-band Radarsat-2 with L-band PALSAR for multisource polarimetric parameters dataset. Multi-scale iterative segmentation algorithm and Random Forest machine-learning algorithm were utilized to classify land cover types in the reserve. This research further analyzed differences between multi-frequency SAR datasets in the identification accuracy of vegetation types in the reserve. The results showed that the integrating PALSAR and radarsat-2 polarization datasets achieved86.77% overall classification accuracy, which was 15% higher than that using PALSAR polarization images.However, there was no significant difference between classification result using radarsat-2 polarization images and that using combined SAR images. The production precision of shallow-water marshes achieved 90.91%.The user precision of deep-water marshes obtained 90.63%. C-band polarimetric SAR was more suitable than L-band polarimetric SAR for vegetation classification in Honghe National Nature Reserve.
Vegetation is a"barometer"of health status of wetland ecosystem. Exploration of the spatial-temporal distribution of vegetation is the premise and foundation of wetland ecological restoration and reconstruction, wetland resource protection and rational utilization. This paper extracted different wavelength polarimetric decomposition parameters of Honghe National Nature Reserve based on polarimetric synthetic aperture radar(SAR) target decomposition theory, and integrated C-band Radarsat-2 with L-band PALSAR for multisource polarimetric parameters dataset. Multi-scale iterative segmentation algorithm and Random Forest machine-learning algorithm were utilized to classify land cover types in the reserve. This research further analyzed differences between multi-frequency SAR datasets in the identification accuracy of vegetation types in the reserve. The results showed that the integrating PALSAR and radarsat-2 polarization datasets achieved86.77% overall classification accuracy, which was 15% higher than that using PALSAR polarization images.However, there was no significant difference between classification result using radarsat-2 polarization images and that using combined SAR images. The production precision of shallow-water marshes achieved 90.91%.The user precision of deep-water marshes obtained 90.63%. C-band polarimetric SAR was more suitable than L-band polarimetric SAR for vegetation classification in Honghe National Nature Reserve.
引文
[1]赵魁义,刘兴土.湿地研究的现状与展望[C]//陈宜瑜.中国湿地研究.长春:吉林科学技术出版社, 1995.
[2]那晓东,张树清,李晓峰,等. MODIS NDVI时间序列在三江平原湿地植被信息提取中的应用[J].湿地科学, 2007, 55(3):227-236.
[3]李春干,代华兵.红树林空间分布信息遥感提取方法[J].湿地科学, 2014, 1122(5):580-589.
[4]章恒,王世新,周艺,等.多源遥感影像红树林信息提取方法比较[J].湿地科学, 2015, 1133(2):145-152.
[5]张莹莹,蔡晓斌,宋辛辛,等.基于决策树的洪湖水生植物遥感信息提取[J].湿地科学, 2018, 1166(2):213-221.
[6]Moffett K B, Gorelick S M. Distinguishing wetland vegetation and channel features with object-based image segmentation[J]. International Journal of Remote Sensing, 2013, 3344(4):1332-1354.
[7]Dronova I. Object-based image analysis in wetland research:a review[J]. Remote Sensing, 2015, 7(5):6380-6413.
[8]Zhang C, Xie Z, Selch D. Fusing LIDAR and digital aerial photography for object-based forest mapping in the Florida Everglades[J]. GIScience&Remote Sensing, 2013, 500(5):562-573.
[9]la Cecilia D, Toffolon M, Woodcock C E, et al. Interactions between river stage and wetland vegetation detected with a Seasonality Index derived from LANDSAT images in the Apalachicola delta, Florida[J]. Advances in Water Resources, 2016, 899:10-23.
[10]Zhang C, Xie Z. Combining object-based texture measures with a neural network for vegetation mapping in the Everglades from hyperspectral imagery[J]. Remote Sensing of Environment,2012, 12244:310-320.
[11]Deng F, Wang X, Cai X, et al. Analysis of the relationship between inundation frequency and wetland vegetation in Dongting Lake using remote sensing data[J]. Ecohydrology, 2014, 7(2):717-726.
[12]Lane C R, Liu H, Autrey B C, et al. Improved wetland classification using eight-band high resolution satellite imagery and a hybrid approach[J]. Remote Sensing, 2014, 66(12):12187-12216.
[13]Whiteside T G, Bartolo R E. Mapping aquatic vegetation in a tropical wetland using high spatial resolution multispectral satellite imagery[J]. Remote Sensing, 2015, 77(9):11664-11694.
[14]Evans T L, Costa M, Tomas W M, et al. Large-scale habitat mapping of the Brazilian Pantanal wetland:A synthetic aperture radar approach[J]. Remote Sensing of Environment, 2014, 115555:89-108.
[15]Betbeder J, Rapinel S, Corpetti T, et al. Multitemporal classification of TerraSAR-X data for wetland vegetation mapping[J].Journal of Applied Remote Sensing, 2014, 88(1):83648.
[16]Koch M, Schmid T, Reyes M, et al. Evaluating full polarimetric C-and L-band data for mapping wetland conditions in a semi-arid environment in Central Spain[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012, 55(3):1033-1044.
[17]Gallant A L, Kaya S G, White L, et al. Detecting emergence,growth, and senescence of wetland vegetation with polarimetric Synthetic Aperture Radar(SAR)Data[J]. Water, 2014, 66(3):694-722.
[18]Hong S H, Wdowinski S. Multitemporal multitrack monitoring of wetland water levels in the Florida Everglades using ALOS PALSAR data with interferometric processing[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 111(8):1355-1359.
[19]De Almeida Furtado L F, Silva T S F, de Moraes Novo E M L.Dual-season and full-polarimetric C band SAR assessment for vegetation mapping in the Amazon várzea wetlands[J]. Remote Sensing of Environment, 2016, 117744:212-222.
[20]Pohl C, van Genderen J. Remote sensing image fusion:an update in the context of Digital Earth[J]. International Journal of Digital Earth, 2014, 77(2):158-172.
[21]Morandeira N S, Grings F, Facchinetti C, et al. Mapping plant functional types in floodplain wetlands:An analysis of C-band polarimetric SAR Data from RADARSAT-2[J]. Remote Sensing,2016, 88(3):174.
[22]Niculescu S, Lardeux C, Grigoras I, et al. Synergy Between LiDAR, RADARSAT-2, and Spot-5 Images for the Detection and Mapping of Wetland Vegetation in the Danube Delta[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 99(8):3651-3666.
[23]Fu B, Wang Y, Campbell A, et al. Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data[J]. Ecological Indicators, 2017, 7733:105-117.
[24]Franklin S E, Skeries E M, Stefanuk M A, et al. Wetland classification using Radarsat-2 SAR quad-polarization and Landsat-8OLI spectral response data:a case study in the Hudson Bay Lowlands Ecoregion[J]. International Journal of Remote Sensing,2018, 3399(6):1615-1627.
[25]Cloude S R. Application of the H/A/alpha polarimetric decomposition theorem for land classification[C]//Proceedings of SPIEThe International Society for Optical Engineering, 1997:3120.
[26]Allain S, FerroFamil L, Potier E. New eigenvalue-based parameters for natural media characterization[C]//Radar Conference,EURAD 2005, European, 2005:177-180.
[27]Réfrégier P, Morio J. Shannon entropy of partially polarized and partially coherent light with Gaussian fluctuations[J]. JOSA A,2006, 233(12):3036-3044.
[28]Lüneburg E. Final report phase I:Foundation of the mathematical theory of polarimetry[R]. ONR Contract,(0001400), M0152,2001.
[29]Ainsworth T L, Lee J S, Schuler D L. Multi-frequency polarimetric SAR data analysis of ocean surface features[C]//Geoscience and Remote Sensing Symposium, 2000, Proceedings, IGARSS2000, IEEE 2000 International, 33:1113-1115.
[30]Vanzyl J J. Application of Cloude's target decomposition theorem to polarimetric imaging radar data[C]//Proceedings of SPIEThe International Society for Optical Engineering, 1993:184-191.
[31]Durden S L, Vanzyl J J, Zebker H A. The unpolarized component in polarimetric radar observations of forested areas[J].IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(2):268-271.
[32]Breiman L. Random forests[J]. Machine Learning, 2001, 4455(1):5-32.
[2]那晓东,张树清,李晓峰,等. MODIS NDVI时间序列在三江平原湿地植被信息提取中的应用[J].湿地科学, 2007, 55(3):227-236.
[3]李春干,代华兵.红树林空间分布信息遥感提取方法[J].湿地科学, 2014, 1122(5):580-589.
[4]章恒,王世新,周艺,等.多源遥感影像红树林信息提取方法比较[J].湿地科学, 2015, 1133(2):145-152.
[5]张莹莹,蔡晓斌,宋辛辛,等.基于决策树的洪湖水生植物遥感信息提取[J].湿地科学, 2018, 1166(2):213-221.
[6]Moffett K B, Gorelick S M. Distinguishing wetland vegetation and channel features with object-based image segmentation[J]. International Journal of Remote Sensing, 2013, 3344(4):1332-1354.
[7]Dronova I. Object-based image analysis in wetland research:a review[J]. Remote Sensing, 2015, 7(5):6380-6413.
[8]Zhang C, Xie Z, Selch D. Fusing LIDAR and digital aerial photography for object-based forest mapping in the Florida Everglades[J]. GIScience&Remote Sensing, 2013, 500(5):562-573.
[9]la Cecilia D, Toffolon M, Woodcock C E, et al. Interactions between river stage and wetland vegetation detected with a Seasonality Index derived from LANDSAT images in the Apalachicola delta, Florida[J]. Advances in Water Resources, 2016, 899:10-23.
[10]Zhang C, Xie Z. Combining object-based texture measures with a neural network for vegetation mapping in the Everglades from hyperspectral imagery[J]. Remote Sensing of Environment,2012, 12244:310-320.
[11]Deng F, Wang X, Cai X, et al. Analysis of the relationship between inundation frequency and wetland vegetation in Dongting Lake using remote sensing data[J]. Ecohydrology, 2014, 7(2):717-726.
[12]Lane C R, Liu H, Autrey B C, et al. Improved wetland classification using eight-band high resolution satellite imagery and a hybrid approach[J]. Remote Sensing, 2014, 66(12):12187-12216.
[13]Whiteside T G, Bartolo R E. Mapping aquatic vegetation in a tropical wetland using high spatial resolution multispectral satellite imagery[J]. Remote Sensing, 2015, 77(9):11664-11694.
[14]Evans T L, Costa M, Tomas W M, et al. Large-scale habitat mapping of the Brazilian Pantanal wetland:A synthetic aperture radar approach[J]. Remote Sensing of Environment, 2014, 115555:89-108.
[15]Betbeder J, Rapinel S, Corpetti T, et al. Multitemporal classification of TerraSAR-X data for wetland vegetation mapping[J].Journal of Applied Remote Sensing, 2014, 88(1):83648.
[16]Koch M, Schmid T, Reyes M, et al. Evaluating full polarimetric C-and L-band data for mapping wetland conditions in a semi-arid environment in Central Spain[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012, 55(3):1033-1044.
[17]Gallant A L, Kaya S G, White L, et al. Detecting emergence,growth, and senescence of wetland vegetation with polarimetric Synthetic Aperture Radar(SAR)Data[J]. Water, 2014, 66(3):694-722.
[18]Hong S H, Wdowinski S. Multitemporal multitrack monitoring of wetland water levels in the Florida Everglades using ALOS PALSAR data with interferometric processing[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 111(8):1355-1359.
[19]De Almeida Furtado L F, Silva T S F, de Moraes Novo E M L.Dual-season and full-polarimetric C band SAR assessment for vegetation mapping in the Amazon várzea wetlands[J]. Remote Sensing of Environment, 2016, 117744:212-222.
[20]Pohl C, van Genderen J. Remote sensing image fusion:an update in the context of Digital Earth[J]. International Journal of Digital Earth, 2014, 77(2):158-172.
[21]Morandeira N S, Grings F, Facchinetti C, et al. Mapping plant functional types in floodplain wetlands:An analysis of C-band polarimetric SAR Data from RADARSAT-2[J]. Remote Sensing,2016, 88(3):174.
[22]Niculescu S, Lardeux C, Grigoras I, et al. Synergy Between LiDAR, RADARSAT-2, and Spot-5 Images for the Detection and Mapping of Wetland Vegetation in the Danube Delta[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 99(8):3651-3666.
[23]Fu B, Wang Y, Campbell A, et al. Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data[J]. Ecological Indicators, 2017, 7733:105-117.
[24]Franklin S E, Skeries E M, Stefanuk M A, et al. Wetland classification using Radarsat-2 SAR quad-polarization and Landsat-8OLI spectral response data:a case study in the Hudson Bay Lowlands Ecoregion[J]. International Journal of Remote Sensing,2018, 3399(6):1615-1627.
[25]Cloude S R. Application of the H/A/alpha polarimetric decomposition theorem for land classification[C]//Proceedings of SPIEThe International Society for Optical Engineering, 1997:3120.
[26]Allain S, FerroFamil L, Potier E. New eigenvalue-based parameters for natural media characterization[C]//Radar Conference,EURAD 2005, European, 2005:177-180.
[27]Réfrégier P, Morio J. Shannon entropy of partially polarized and partially coherent light with Gaussian fluctuations[J]. JOSA A,2006, 233(12):3036-3044.
[28]Lüneburg E. Final report phase I:Foundation of the mathematical theory of polarimetry[R]. ONR Contract,(0001400), M0152,2001.
[29]Ainsworth T L, Lee J S, Schuler D L. Multi-frequency polarimetric SAR data analysis of ocean surface features[C]//Geoscience and Remote Sensing Symposium, 2000, Proceedings, IGARSS2000, IEEE 2000 International, 33:1113-1115.
[30]Vanzyl J J. Application of Cloude's target decomposition theorem to polarimetric imaging radar data[C]//Proceedings of SPIEThe International Society for Optical Engineering, 1993:184-191.
[31]Durden S L, Vanzyl J J, Zebker H A. The unpolarized component in polarimetric radar observations of forested areas[J].IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(2):268-271.
[32]Breiman L. Random forests[J]. Machine Learning, 2001, 4455(1):5-32.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |