收稿：2017-11-16，
录用：2018-2-6，
纸质出版：2018-11
移动端阅览
湿地专题图的更新无论是对湿地研究还是湿地管理和保护都具有重要价值。但是由于湿地本身具有显著的时空动态性和空间异质性特征，使得大空间范围湿地专题图的更新面临着周期长、时效性差的挑战。为应对这一挑战，实现大空间范围湿地地图的快速更新，本文提出一种通过提取历史湿地专题图中的信息，对新遥感影像进行自动化的湿地分类制图方法——“迭代解译再组织” IIR (Iterative Interpretation and Reorganization)。针对湿地空间异质性强、稳定样本获取困难等特点，IIR方法通过分别获取不同湿地类型的空间信息和类别属性两个步骤完成湿地的自动更新。为验证该方法在大空间范围湿地图更新中的应用效果，随机选取了位于高海拔地区、高纬度地区、低纬度地区和滨海地区等不同自然地理环境的4个湿地保护区(若尔盖湿地保护区、莫莫格湿地保护区、鄱阳湖湿地保护区和黄河三角洲湿地保护区)进行验证。结果表明IIR方法的湿地制图的总体精度在70%—90%，总体上优于传统监督分类方法。IIR方法对于大的时空尺度背景下湿地专题图更新面临的高时空动态特征具有较好的解决能力。
Timely updating of wetland map is vital to wetland research and management. However
the highly hydro-dynamic characteristics and great spatial heterogeneity of wetlands pose challenges in updating large-scale wetland thematic maps in a timely manner. General mapping methods
such as supervised or object-oriented classification
are time consuming and can be easily affected by cognitive differences. To address this issue
we propose an automatic updating method of wetland map
namely
iterative interview and reorganization. We aim to design a method that can transfer the knowledge from existing wetland thematic maps into the classification of a new remote sensing image. At the same time
the method should be robust for different geographical conditions. Rather than adapting samples between different domains
Iterative Interview and reorganization (IIR) tries to obtain the precise spatial distribution of ground objects first and then defines the properties of the spatial distributions by matching their spatial features. The method can tackle complex situations caused by changes of ground objects. This automatic method achieves an overall accuracy ranging from 70% to 90%
similar to the results of general supervised classification. In some cases
IIR has better performance in the identification of detailed information than that the support vector machine or maximum likelihood classification
such as for boundaries of ground objects and slender targets. To examine the performance of this method
we choose four wetland reserves with various geographical environments across China
including the Momoge Nature Reserve in high latitude
the Zoige Reserve in high altitude
Poyang Lake in a hot-humid area
and Yellow River Delta along a coastal area. Both overall and individual accuracies of various wetland classes in the four study areas are higher than those of the general supervised classification. Furthermore
IIR can automatically detect new classes such as paddy field. Without extra samples
IIR achieves better classification in four study areas of different landscapes. This method is not only adaptable for eliminating unfavorable factors
such as terrain or clouds
but also more flexible and robust when dealing with different wetlands and phenological changes
demonstrating that the IIR method can be applied in large-scale thematic map updating. IIR can have a consistent interpretation of the same wetland class because all procedures are carried out without expert knowledge. In conclusion
IIR can meet the needs of automatic updating of large-scale wetland thematic maps.
Armenakis C, Leduc F, Cyr I, Savopol F and Cavayas F. 2003. A comparative analysis of scanned maps and imagery for mapping applications. ISPRS Journal of Photogrammetry and Remote Sensing, 57(5/6): 304–314
Aydav P S S and Minz S. 2015. Modified self-learning with clustering for the classification of remote sensing images. Procedia Computer Science, 58: 97–104
Bernadez F G, Benayas J M R and Martinez A. 1993. Ecological impact of groundwater extraction on wetlands (Douro Basin, Spain). Journal of Hydrology, 141(1/4): 219–238
Black M, Riley T R, Ferrier G, Fleming A H and Fretwell P T. 2016. Automated lithological mapping using airborne hyperspectral thermal infrared data: a case study from Anchorage Island, Antarctica. Remote Sensing of Environment, 176: 225–241
Bruzzone L, Chi M and Marconcini M. 2006. A novel transductive SVM for semisupervised classification of remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing, 44(11): 3363–3373
Bruzzone L and Cossu R. 2002. A multiple-cascade-classifier system for a robust and partially unsupervised updating of land-cover maps. IEEE Transactions on Geoscience and Remote Sensing, 40(9): 1984–1996
Bruzzone L, Cossu R and Vernazza G. 2002. Combining parametric and non-parametric algorithms for a partially unsupervised classification of multitemporal remote-sensing images. Information Fusion, 3(4): 289–297
Bruzzone L and Prieto D F. 2001. Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 39(2): 456–460
Bruzzone L and Prieto D F. 2002. A partially unsupervised cascade classifier for the analysis of multitemporal remote-sensing images. Pattern Recognition Letters, 23(9): 1063–1071
Burges C J C. 1998. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2): 121–167
Carter V. 1986. An overview of the hydrologic concerns related to wetlands in the United States. Canadian Journal of Botany, 64(2): 364–374
陈江平, 张瑶, 余远剑. 2011. 空间自相关的可塑性面积单元问题效应. 地理学报, 66(12): 1597–1606
Chen J P, Zhang Y and Yu Y J. 2011. Effect of MAUP in spatial autocorrelation. Acta Geographica Sinica, 66(12): 1597–1606 (
Chen X H, Chen J, Shi Y S and Yamaguchi Y. 2012. An automated approach for updating land cover maps based on integrated change detection and classification methods. ISPRS Journal of Photogrammetry and Remote Sensing, 71: 86–95
Davidson N C. 2014. How much wetland has the world lost? Long-term and recent trends in global wetland area. Marine and Freshwater Research, 65(10): 934–941
Demir B, Bovolo F and Bruzzone L. 2013. Updating land-cover maps by classification of image time series: a novel change-detection-driven transfer learning approach. IEEE Transactions on Geoscience and Remote Sensing, 51(1): 300–312
Feyisa G L, Meilby H, Fensholt R and Proud S R. 2014. Automated water extraction index: a new technique for surface water mapping using Landsat imagery. Remote Sensing of Environment, 140: 23–35
Frazier P S and Page K J. 2000. Water body detection and delineation with Landsat TM data. Photogrammetric Engineering and Remote Sensing, 66(12): 1461–1468
傅伯杰, 陈利顶, 刘国华. 1999. 中国生态区划的目的、任务及特点. 生态学报, 19(5): 591–595
Fu B J, Chen L D and Liu G H. 1999. The objectives, tasks and characteristics of China ecological regionalization. Acta Ecologica Sinica, 19(5): 591–595 (
Gan H T, Sang N, Huang R, Tong X J and Dan Z P. 2013. Using clustering analysis to improve semi-supervised classification. Neurocomputing, 101: 290–298
宫兆宁, 张翼然, 宫辉力, 赵文吉. 2011. 北京湿地景观格局演变特征与驱动机制分析. 地理学报, 66(1): 77–88
Gong Z N, Zhang Y R, Gong H L and Zhao W J. 2011. Evolution of wetland landscape pattern and its driving factors in Beijing. Acta Geographica Sinica, 66(1): 77–88 (
Grinand C, Arrouays D, Laroche B and Martin M P. 2008. Extrapolating regional soil landscapes from an existing soil map: sampling intensity, validation procedures, and integration of spatial context. Geoderma, 143(1/2): 180–190
Hoffmann A, Van der Vegt J W and Lehmann F. 2000. Towards automated map updating: is it feasible with new digital data-acquisition and processing techniques//International Archives of Photogrammetry and Remote Sensing XXXIII, Part B2. Amsterdam, The Netherlands: ISPRS: 295–302
Hong S and Vatsavai R R. 2016. Sliding window-based probabilistic change detection for remote-sensed images. Procedia Computer Science, 80: 2348–2352
Hu S J, Niu Z G and Chen Y F. 2017. Global wetland datasets: a review. Wetlands, 37(5): 807–817
Hussain M, Chen D M, Cheng A, Wei H and Stanley D. 2013. Change detection from remotely sensed images: from pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 80: 91–106
Janez F, Goretta O and Michel A. 2000. Automatic map updating by fusion of multispectral images in the Dempster-Shafer framework//Proceedings of SPIE 4115, Applications of Digital Image Processing XXIII. San Diego, CA: SPIE [DOI: 10.1117/12.411549 http://dx.doi.org/10.1117/12.411549 ]
Jung F. 2004. Detecting building changes from multitemporal aerial stereopairs. ISPRS Journal of Photogrammetry and Remote Sensing, 58(3/4): 187–201
Knudsen T and Olsen B P. 2003. Automated change detection for updates of digital map databases. Photogrammetric Engineering and Remote Sensing, 69(11): 1289–1296
Leduc F, Solaiman B and Cavayas F. 2001. Combination of fuzzy sets and Dempster-Shafer theories in forest map updating using multispectral data//Proceedings of SPIE 4385, Sensor Fusion: Architectures, Algorithms, and Applications V. Orlando, FL: SPIE [DOI: 10.1117/12.421120 http://dx.doi.org/10.1117/12.421120 ]
Leichtle T, Geiß C, Wurm M, Lakes T and Taubenböck H. 2017. Unsupervised change detection in VHR remote sensing imagery – an object-based clustering approach in a dynamic urban environment. International Journal of Applied Earth Observation and Geoinformation, 54: 15–27
刘桂林, 张落成, 刘剑, 李广宇. 2013. 基于Landsat TM影像的水体信息提取. 中国科学院大学学报, 30(5): 644–650
Liu G L, Zhang L C, Liu J and Li G Y. 2013. Water body information extraction based on Landsat TM remote sensing imagery. Journal of University of Chinese Academy of Sciences, 30(5): 644–650 (
Lu S L, Wu B F, Yan N N and Wang H. 2011. Water body mapping method with HJ-1A/B satellite imagery. International Journal of Applied Earth Observation and Geoinformation, 13(3): 428–434
McFeeters S K. 1996. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7): 1425–1432
Nauman T W and Thompson J A. 2014. Semi-automated disaggregation of conventional soil maps using knowledge driven data mining and classification trees. Geoderma, 213: 385–399
Niederöst M. 2001. Automated update of building information in maps using medium-scale imagery. Baltsavias E P, ed. Automatic Extraction of Man-Made Objects from Aerial and Space Images (III). Lisse: Swets and Zeitlinger: 161–170
牛振国, 张海英, 王显威, 姚文博, 周德民, 赵魁义, 赵惠, 李娜娜, 黄华兵, 李丛丛, 杨军, 柳彩霞, 刘爽, 王琳, 李展, 杨镇钟, 乔飞, 郑姚闽, 陈炎磊, 盛永伟, 高小红, 朱卫红, 王文卿, 王红, 翁永玲, 庄大方, 刘纪远, 罗志才, 程晓, 郭子琪, 宫鹏. 2012. 1978~2008年中国湿地类型变化. 科学通报, 57(16): 1400–1411
Niu Z G, Zhang H Y, Wang X W, Yao W B, Zhou D M, Zhao K Y, Zhao H, Li N N, Huang H B, Li C C, Yang J, Liu C X, Liu S, Wang L, Li Z, Yang Z Z, Qiao F, Zheng Y M, Chen Y L, Sheng Y W, Gao X H, Zhu W H, Wang W Q, Wang H, Weng Y L, Zhuang D F, Liu J Y, Luo Z C, Cheng X, Guo Z Q and Gong P. 2012. Mapping wetland changes in China between 1978 and 2008. Chinese Science Bulletin, 57(16): 1400–1411 (
Pásztor L, Laborczi A, Bakacsi Z, Szabó J and Illés G. 2018. Compilation of a national soil-type map for Hungary by sequential classification methods. Geoderma, 311: 93–108
Qi F and Zhu A X. 2003. Knowledge discovery from soil maps using inductive learning. International Journal of Geographical Information Science, 17(8): 771–795
Rathore M M U, Ahmad A, Paul A and Wu J J. 2016. Real-time continuous feature extraction in large size satellite images. Journal of Systems Architecture, 64: 122–132
Rosenberg C, Hebert M and Schneiderman H. 2005. Semi-supervised self-training of object detection models//Proceedings of the 7th IEEE Workshops on Application of Computer Vision. Breckenridge, CO, USA: IEEE: 29–36 [DOI: 10.1109/ACVMOT.2005.107 http://dx.doi.org/10.1109/ACVMOT.2005.107 ]
Rouse Jr W J, Haas R H, Schell J A and Deering D W. 1974. Monitoring vegetation systems in the Great Plains with ERTS. PAPER-A20, Washington DC: NASA: 309–317
Saito A and Yamazaki T. 1999. Characteristics of spectral reflectance for vegetation ground surfaces with snow-cover; vegetation indices and snow indices. Journal of Japan Society of Hydrology and Water Resources, 12(1): 28–38
Tebbs E J, Remedios J J, Avery S T and Harper D M. 2013. Remote sensing the hydrological variability of Tanzania’s Lake Natron, a vital Lesser Flamingo breeding site under threat. Ecohydrology and Hydrobiology, 13(2): 148–158
Walter V. 2004. Object-based classification of remote sensing data for change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 58(3/4): 225–238
王宗明, 张树清, 张柏. 2004. 土地利用变化对三江平原生态系统服务价值的影响. 中国环境科学, 24(1): 125–128
Wang Z M, Zhang S Q and Zhang B. 2004. Effects of land use change on values of ecosystem services of Sanjiang Plain, China. China Environmental Science, 24(1): 125–128 (
Wright C and Gallant A. 2007. Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data. Remote Sensing of Environment, 107(4): 582–605
吴绍洪, 杨勤业, 郑度. 2003. 生态地理区域系统的比较研究. 地理学报, 58(5): 686–694
Wu S H, Yang Q Y and Zheng D. 2003. Comparative study on Eco-geographic regional systems between China and USA. Acta Geographica Sinica, 58(5): 686–694 (
谢花林, 刘黎明, 李波, 张新时. 2006. 土地利用变化的多尺度空间自相关分析——以内蒙古翁牛特旗为例. 地理学报, 61(4): 389–400
Xie H L, Liu L M, Li B and Zhang X S. 2006. Spatial autocorrelation analysis of multi-scale land-use changes: a case study in Ongniud Banner, Inner Mongolia. Acta Geographica Sinica, 61(4): 389–400 (
闫霈, 张友静, 张元. 2007. 利用增强型水体指数(EWI)和GIS去噪音技术提取半干旱地区水系信息的研究. 遥感信息, 22(6): 62–67
Yan P, Zhang Y J and Zhang Y. 2007. A study on information extraction of water system in semi-arid regions with the Enhanced Water Index (EWI) and GIS based noise remove techniques. Remote Sensing Information, 22(6): 62–67 (
张海英, 周德民, 王一涵. 2009. 三江平原洪河自然保护区及周边地区湿地景观变化过程研究. 遥感技术与应用, 24(1): 57–62
Zhang H Y, Zhou D M and Wang Y H. 2009. The changing process of wetland landscape in Honghe national nature reserve and surrounding farms in Sanjiang Plain. Remote Sensing Technology and Application, 24(1): 57–62 (
张松林, 张昆. 2007. 全局空间自相关Moran指数和G系数对比研究. 中山大学学报(自然科学版), 46(4): 93–97
Zhang S L and Zhang K. 2007. Comparison between general Moran’s index and getis-ord general G of spatial autocorrelation. Acta Scientiarum Naturalium Universitatis Sunyatseni, 46(4): 93–97 (
Zhang X L, Xiao P F, Feng X Z and Yuan M. 2017. Separate segmentation of multi-temporal high-resolution remote sensing images for object-based change detection in urban area. Remote Sensing of Environment, 201: 243–255
相关作者
相关机构
京公网安备11010802024621
