首頁 > 論文 > 紅外與毫米波學報 > 39卷 > 1期(pp:128-136)

融合高分夜光和Landsat OLI影像的不透水面自動提取方法

An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images

  • 摘要
  • 論文信息
  • 參考文獻
  • 被引情況
  • PDF全文
分享:

摘要

針對監督分類提取不透水面需要人工獲取大量訓練樣本的制約,提出了一種亞米級高空間分辨率夜光遙感影像引導下的不透水面自動提取方法。以夜光強度信息作為先驗知識,判別對應地理位置的Landsat8 OLI影像像元為不透水面正負訓練樣本后,提取OLI影像的光譜和紋理特征構建特征集,利用集成ELM分類器提取不透水面。選擇全球4個具有代表性的城市作為試驗區進行驗證,結果顯示,該方法在4個試驗區的不透水面提取精度均超過93%,Kappa系數均在0.87以上。對比BCI指數與人工選取訓練樣本的不透水面提取結果,發現該方法在4個試驗區的總體精度均優于指數法,主要原因是該方法相較于BCI指數法可以更有效地區分裸土和不透水面。提出的自動提取方法在3個試驗區的總體精度高于或接近人工樣本分類方法,但在哈爾濱試驗區的總體精度略低,主要是因為在自動選擇樣本過程中燈光強度弱的不透水面未被選為正樣本導致部分漏提。研究表明,高分辨率夜光數據可以作用遙感影像解譯與地物提取的先驗知識,引導自動分類提取模型的構建,具有較高的實用性。

Abstract

Supervised classification is a vital approach to extract impervious surface areas (ISA) from satellite images, but the training samples need to be provided through heavy manual work. To address it, this study proposed an automatic method to generate training samples from high-resolution night light data, considering that nighttime lights generated by human activities is strongly correlated with impervious surface. First, positive and negative samples for ISA were located according to the distribution of nighttime lights. Second, the feature sets were constructed by calculating the spectral and texture feature from the OLI images. Third, an ensemble ELM classifier was selected for ISA classification and extraction. Four large cities were selected as study areas to examine the performance of the proposed method in different environment. The results show that the proposed method can automatically and accurately acquire ISA with an overall accuracy higher than 93% and Kappa coefficient higher than 0.87. Furthermore, comparative experiments by biophysical composition index (BCI)and classification by manual sample were conducted to evaluate its superiority. The results show that our method has better separability for ISA and soil than the BCI. In general, the proposed method is superior to manual methods, except Harbin mostly because some impervious surfaces with weak light intensity are selected as negative samples.

Newport宣傳-MKS新實驗室計劃
補充資料

DOI:10.11972/j.issn.1001-9014.2020.01.017

所屬欄目:Remote Sensing Technology and Application

基金項目:國家自然科學基金重點項目; the National Natural Science Foundation of China;

收稿日期:2019-08-16

修改稿日期:--

網絡出版日期:2020-03-12

作者單位    點擊查看

Peng-Fei TANG:School of Geography and Ocean Science, Nanjing University, Nanjing20023,ChinaJiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing1003,ChinaKey Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, Nanjing21002,China
Ze-Lang MIAO:School of Geoscience and Info-Physics, Central South University, Changsha10083, China
Cong LIN:School of Geography and Ocean Science, Nanjing University, Nanjing20023,ChinaJiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing1003,ChinaKey Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, Nanjing21002,China
Pei-Jun DU:School of Geography and Ocean Science, Nanjing University, Nanjing20023,ChinaJiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing1003,ChinaKey Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, Nanjing21002,China
Shan-Chuan GUO:School of Geography and Ocean Science, Nanjing University, Nanjing20023,ChinaJiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing1003,ChinaKey Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, Nanjing21002,China

聯系人作者:Ze-Lang MIAO(zelang.miao@csu.edu.cn); Pei-Jun DU(dupjrs@126.com);

備注:國家自然科學基金重點項目; the National Natural Science Foundation of China;

【1】. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment. 117, 34-49(2012).

【2】Z. Liu, C. He and Q. Zhang. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Landscape and Urban Planning,. 106, 62-72(2012).

【3】C. L. and C. J. GibbonsC. L. and C. J. Gibbons. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Journal of the American Planning Association. 62(2), 243-258(1996).

【4】Q WengQ Weng. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Environmental Management. 28(6), 737-748(2014).

【5】J D Hurd and D L Civco. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. (2004).

【6】S. E. Brun and L Band. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Environment and Urban Systems,. 24, 5-22(2000).

【7】L. Yang, C. Huang and C. G. Homer. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Canadian Journal of Remote Sensing,. 29, 230-240(2003).

【8】F Yuan and M Bauer. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment,. 106, 375-386(2007).

【9】H Xu and M Wang. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. 王美雅.地表不透水面信息遙感的主要方法分析.遙感學報). 20(5), 1270-89(2016).

【10】R. R. Gillies and J. B. Box. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment,. 86, 411-422(2003).

【11】T CarlsonT Carlson. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Journal of the American Water Resources Association. 40(4), 1087-1098(2004).

【12】E. Boegh, R. N. Poulsen and M. Butts. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Journal of Hydrology. 3(4), 300-316(377).

【13】. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Global and Planetary Change. 25(1/2), 49-65(2000).

【14】Y. ZhaY. Zha. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. International Journal of Remote Sensing. 24(3), 583-594(2003).

【15】H Q XuH Q Xu. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Photogrammetric Engineering and Remote Sensing. 76(5), 557-565(2010).

【16】C S Deng C B and WuC S Deng C B and Wu. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment. 127, 247-259(2012).

【17】C Li, J Wang and L Wang. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote sensing. 6(2), 964-983(2014).

【18】V. F. Rodriguez-GalianoV. F. Rodriguez-Galiano. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. ISPRS Journal of Photogrammetry and Remote Sensing. 67, 93-104(2012).

【19】S. and A. GunluS. and A. Gunlu. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Kastamonu University Journal of Forestry Faculty. 16(2), 528-535(2016).

【20】P. SuttonP. Sutton. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. International Journal of Remote Sensing. 22(16), 3061-3076(2001).

【21】Y. XieY. Xie. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment. 225, 160-174(2019).

【22】J. OuJ. Ou. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. International Journal of Applied Earth Observation and Geoinformation. 81, 1-12(2019).

【23】Q. L. ZhangQ. L. Zhang. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing. 7(9), 11887-11913(2015).

【24】X Cheng, W Wu and L Xia. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. 地球信息科學學報. 19(10), 1364-74(2017).

【25】X. MaX. Ma. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing. 9(3), (2017).

【26】X. and P. LiX. and P. Li. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. ISPRS Journal of Photogrammetry and Remote Sensing. 135, 93-111(2018).

【27】. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. In Journal of SCIENTIA SINICA Terrae (匡文慧.全球城市人居環境不透水面與綠地空間特征制圖.中國科學:地球科學). 49(07), 1151-1168(2019).

【28】M. DuM. Du. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing. 10(12), (2018).

【29】D. C. ElvidgeD. C. Elvidge. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing. 7(3), (2015).

【30】M. and N. A. DodgsonM. and N. A. Dodgson. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Pattern Recognition. 40(11), 2891-2896(2007).

【31】C.D. Elvidge, K.E. Baugh and M. Zhizhin. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Proc. Asia Pac. Adv. Netw. 35(0), (2013).

【32】Q. ZhengQ. Zheng. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment. 215, 300-312(2018).

【33】N OhtsuN Ohtsu. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. IEEE Transactions on Systems Man & Cybernetics. 9(1), 62-66(2007).

【34】G B Huang, Q Y Zhu and C K Siew. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Budapest,Hungary: IEEE, 985-990(2004).

【35】Chee-Kheong SiewChee-Kheong Siew. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Neurocomputing. 70(1), (2005).

【36】A Stumpf and N Kerle. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. Remote Sensing of Environment. 115(10), 2564-2577(2011).

【37】J J Rodriguez, L I Kuncheva and C J Alonso. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. IEEE Transactions on Pattern Analysis and Machine Intelligence. 28(10), 1619-1630(2006).

【38】P GongP Gong. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. International Journal of Remote Sensing. 34(7), 2607-2654(2013).

【39】M Han and B Liu. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images. 劉賁.一種改進的旋轉森林分類算法.電子與信息學報). 35(12), 2896-900(2013).

引用該論文

Peng-Fei TANG,Ze-Lang MIAO,Cong LIN,Pei-Jun DU,Shan-Chuan GUO. An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images[J]. Journal of Infrared and Millimeter Waves, 2020, 39(1): 128-136

Peng-Fei TANG,Ze-Lang MIAO,Cong LIN,Pei-Jun DU,Shan-Chuan GUO. 融合高分夜光和Landsat OLI影像的不透水面自動提取方法[J]. 紅外與毫米波學報, 2020, 39(1): 128-136

您的瀏覽器不支持PDF插件,請使用最新的(Chrome/Fire Fox等)瀏覽器.或者您還可以點擊此處下載該論文PDF

TLC官网 <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <蜘蛛词>| <文本链> <文本链> <文本链> <文本链> <文本链> <文本链>