WANG Tingyun,CUI Linlin,WANG Yongqian,et al.Information Extraction of Small and Micro-Wetlands based on GF-1[J].Journal of Chengdu University of Information Technology,2025,40(05):731-738.[doi:10.16836/j.cnki.jcuit.2025.05.023]
基于GF-1的小微湿地信息提取研究——以重庆市梁平区为例
- Title:
- Information Extraction of Small and Micro-Wetlands based on GF-1
- 文章编号:
- 2096-1618(2025)05-0731-08
- 分类号:
- X171.4
- 文献标志码:
- A
- 摘要:
- 湿地对人们的生活有重要意义,湿地变化监测对保护生态系统起着重要作用。为研究小微湿地的监测,以重庆市梁平区为研究区,基于两期GF-1数据采用分层分类法进行湿地信息提取,包括湖泊、河流、库塘、水田、泥滩地、草滩地等6种湿地类型。利用最佳指数OIF指标确定最佳波段组合方式为4(R)3(G)2(B),采用最大似然法进行对比和无人机实地影像进行检验。结果表明分层分类法比最大似然法分类的精度高,总分类精度达89.27%,Kappa系数为0.8017,比最大似然法精度高7.72个百分点,Kappa系数高0.0756,取得较好的分类效果,GF-1各波段可以为湿地变化检测提供有效的信息。研究结果可为了解以小微湿地为代表的湿地系统提供参考,促进生态平衡,对维护湿地生态系统平衡有重要意义。
- Abstract:
- Wetlands are of great significance to people’s lives,and wetland change monitoring plays an important role in protecting ecosystems.To study the monitoring of small and micro wetlands,Liangping District of Chongqing was taken as the study area,and the hierarchical classification method was used to extract wetland information based on the GF-1 data of two phases,including six wetland types,including lakes,rivers,reservoirs,paddy fields,mudflats,and grasslands.The optimal band combination was determined by using the best index OIF index as 4(R)3(G)2(B),and the maximum likelihood method was used for comparison and UAV field images for verification.The results show that the hierarchical classification method has higher classification accuracy than the maximum likelihood method,with a total classification accuracy of 89.27%,a Kappa coefficient of 0.8017,which is 7.72 percentage points higher than that of the maximum likelihood method,and a Kappa coefficient of 0.0756.The results of this study can provide a reference for understanding the wetland system represented by small and micro wetlands,promote the ecological balance,and are of great significance for maintaining the balance of wetland ecosystems.
参考文献/References:
[1] 钱建超,陈孟文.全域治水·湿地润城——梁平区小微湿地的探索与实践[J]. 绿色中国,2022(19):16-21.
[2] 唐廷元,付波霖,何素云,等.基于GF-1和Sentinel-1A的漓江流域典型地物信息提取[J]. 遥感技术与应用,2020,35(2):448-457.
[3] Wang L,Ma H,Li J,et al.An automated extraction of small and middle-sized rice fields under complex terrain based on SAR time series:A case study of Chongqing[J]. Computers and Electronics in Agriculture,2022,200:107232.
[4] 杨黎黎,黎元杰,袁兴中,等.湿地生态修复与城市空间设计协同研究——重庆市梁平双桂城区湿地城市设计[J]. 中国园林,2022,38(11):70-75.
[5] 陈磊士,高霞霞,廖玉芳,等.基于CART决策树的高分二号洞庭湖区湿地分类方法[J]. 测绘通报,2021(6):12-15.
[6] Zhang M,Lin H.Wetland classification using parcel-level ensemble algorithm based on Gaofen-6 multispectral imagery and Sentinel-1 dataset[J]. Journal of Hydrology,2022,606:127462.
[7] 余先怀,袁兴中,蒋启波,等.重庆市梁平区湿地保护修复实践[J]. 三峡生态环境监测,2022,7(3):66-72.
[8] 陈书卿,刁承泰.三峡库区生态经济区用地结构演变及驱动机制——以梁平县为例[J]. 长江流域资源与环境,2009,18(12):1125-1131.
[9] 和晓风,林辉,孙华,等.基于GF-1卫星东洞庭湖湿地类型信息提[J]. 中南林业科技大学报,2015,35(11):1015.
[10] 全胜,杨华.基于TM影像的重庆市县域石漠化变化研究——以彭水县为例[J]. 旅游纵览,2017(2):217-219.
[11] Du Y,Bai Y,Wan L.Wetland information extraction based on UAVmultispectral and oblique images[J]. Arabian Journal of Geosciences,2020,13(23).
[12] Chris Wright,Alisa Gallant.Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data[J]. Remote Sensing of Environment,2007,107(4):582-605.
[13] 常文涛,王浩,宁晓刚,等.融合Sentinel-2红边波段和Sentinel-1雷达波段影像的扎龙湿地信息提取[J]. 湿地科学,2020,18(1):10-19.
[14] 张帅旗,周秉荣,史飞飞,等.基于高分一号卫星遥感数据的青藏高原高寒湿地信息提取方法研究——以玛多县为例[J]. 高原气象,2020,39(6):1309-1317.
[15] Qiangqiang S,Ping Z,DanfengS,et al.Desert vegetation-habitat complexes mapping using Gaofen-1 WFV(wide field of view)time series images in Minqin County,China[J]. International Journal of Applied Earth Observations and Geoinformation,2018,73.
[16] Shang W,Gao Z,Jiang X,et al.The extraction of wetland vegetation information based on UAV remote sensing images[P]. Optical Engineering + Applications,2018.
[17] 费鲜芸,何鑫坤,谢宏璇,等.基于GF-1卫星影像的临洪河口湿地遥感分类[J]. 江苏海洋大学学报(自然科学版),2021,30(2):50-57.
[18] Pan Y,Xu X.Change detection of wetland restoration in China’s Sanjiang National Nature Reserve using STANET method based on GF-1 and GF-6 images[J]. Ecological Indicators,2022,145:109612.
[19] 王艳琦,秦福莹,银山,等.基于GF-1卫星数据与面向对象分类的达里诺尔湿地自然保护区土地覆盖信息提取[J]. 中国农学通报,2019,35(10):137-141.
[20] 王建步,张杰,马毅,等.基于GF-1 WFV影像的黄河口湿地植被盖度估测及分析[J]. 海洋学报,2018,40(6):40-50.
[21] Tang Y T,Fu L B,Lou Q P,et al.Segnet-based Extraction of WetlanVegetation Information From Uav Images[J]. ISPRS-International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2020.
[22] Cao Jiahui,Chen Siyu.The Tibetan Plateau as dust aerosol transit station in middle troposphere over northern East Asia:A case study[J]. Atmospheric Research,2022,280.
备注/Memo
收稿日期:2024-02-01
基金项目:国家科技支撑计划资助项目(2019QZKK020612-02)
通信作者:王永前.E-mail:wyqq@cuit.edu.cn