Précédent|Prochain

Automatic updating method for large-scale wetland mapping based on existing thematic map

  • role： First author第一作者
  • Affiliation：

    Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

    University of Chinese Academy of Sciences, Beijing 100049, China

  • Email：lidc@radi.ac.cn
  • Introduction：李大冲，1989年生，男，硕士研究生，研究方向为湿地遥感分类。E-mail：lidc@radi.ac.cn
Dachong LI12,  
  • Affiliation：

    Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

Panpan XU1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

  • Email：niuzg@radi.ac.cn
  • Introduction：牛振国，1972年生，男，研究员，研究方向为湿地遥感。E-mail：niuzg@radi.ac.cn
Zhenguo NIU1*,  
  • Affiliation：

    Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

Haiying ZHANG1

résumé

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.

mots-clés

automatic updating;wetland;thematic map;large scale

References

  1. 1.
    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
  2. 2.
    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
  3. 3.
    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
  4. 4.
    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
  5. 5.
    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
  6. 6.
    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
  7. 7.
    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
  8. 8.
    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
  9. 9.
    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
  10. 10.
    Burges C J C. 1998. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2): 121–167
  11. 11.
    Carter V. 1986. An overview of the hydrologic concerns related to wetlands in the United States. Canadian Journal of Botany, 64(2): 364–374
  12. 12.
    Chen J P, Zhang Y and Yu Y J. 2011. Effect of MAUP in spatial autocorrelation. Acta Geographica Sinica, 66(12): 1597–1606 (
  13. 13.
    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
  14. 14.
    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
  15. 15.
    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
  16. 16.
    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
  17. 17.
    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
  18. 18.
    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 (
  19. 19.
    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
  20. 20.
    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 (
  21. 21.
    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
  22. 22.
    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
  23. 23.
    Hong S and Vatsavai R R. 2016. Sliding window-based probabilistic change detection for remote-sensed images. Procedia Computer Science, 80: 2348–2352
  24. 24.
    Hu S J, Niu Z G and Chen Y F. 2017. Global wetland datasets: a review. Wetlands, 37(5): 807–817
  25. 25.
    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
  26. 26.
    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
  27. 27.
    Jung F. 2004. Detecting building changes from multitemporal aerial stereopairs. ISPRS Journal of Photogrammetry and Remote Sensing, 58(3/4): 187–201
  28. 28.
    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
  29. 29.
    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
  30. 30.
    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
  31. 31.
    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 (
  32. 32.
    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
  33. 33.
    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
  34. 34.
    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
  35. 35.
    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
  36. 36.
    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 (
  37. 37.
    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
  38. 38.
    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
  39. 39.
    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
  40. 40.
    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
  41. 41.
    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
  42. 42.
    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
  43. 43.
    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
  44. 44.
    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
  45. 45.
    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 (
  46. 46.
    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
  47. 47.
    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 (
  48. 48.
    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 (
  49. 49.
    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 (
  50. 50.
    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 (
  51. 51.
    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 (
  52. 52.
    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

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website