閬ユ劅鎶�鏈笌搴旂敤 鈥衡�� 2022, Vol. 37 鈥衡�� Issue (1): 17-23.DOI: 10.11873/j.issn.1004-0323.2022.1.0017

鈥� 闈掍績浼氬崄鍛ㄥ勾涓撴爮 鈥� 涓婁竴绡�    涓嬩竴绡�

鍩轰簬NDVI鍙樺寲妫�娴嬬殑婊戝潯閬ユ劅绮剧粏璇嗗埆

閮搸1(),鏈变附濞�1,2,鏉庡畨1,椤鹃搩鐕�1,2   

  1. 1.涓浗绉戝闄㈢┖澶╀俊鎭垱鏂扮爺绌堕櫌锛屽寳浜� 100094
    2.鍗椾含澶у 閲戦櫟瀛﹂櫌锛屾睙鑻� 鍗椾含 210000
  • 鏀剁鏃ユ湡:2020-08-10 淇洖鏃ユ湡:2021-06-15 鍑虹増鏃ユ湡:2022-02-20 鍙戝竷鏃ユ湡:2022-04-08
  • 浣滆�呯畝浠�:閮搸(1980-)锛屽コ锛屾渤鍗楅┗椹簵浜猴紝鍗氬+锛岀爺绌跺憳锛屼富瑕佷粠浜嬮仴鎰熶俊鎭彁鍙栦笌婊戝潯鐏惧鐩戞祴鐮旂┒銆侲?mail锛�guoqing@aircas.ac.cn
  • 鍩洪噾璧勫姪:
    鍥藉鑷劧绉戝鍩洪噾闈笂椤圭洰鈥滃婧愬鏃剁浉閬ユ劅鍥惧儚鍏夎氨鐗瑰緛椴佹鎬ц瀺鍚堢爺绌垛��(61771470)

Landslide Identification Method based on NDVI Change Detection

Qing Guo1(),Liya Zhu1,2,An Li1,Lingyan Gu1,2   

  1. 1.Aerospace Information Research Institute锛孋hinese Academy of Sciences锛孊eijing 100094锛孋hina
    2.Jinling College锛孨anjing University锛孨anjing 210000锛孋hina
  • Received:2020-08-10 Revised:2021-06-15 Online:2022-02-20 Published:2022-04-08

鎽樿锛�

闅忕潃閬ユ劅鎶�鏈殑鍙戝睍锛岄珮鍒嗚鲸鐜囩殑鍗槦褰卞儚鏁版嵁閫愭笎涓板瘜锛屾粦鍧$伨瀹崇殑淇℃伅鎻愬彇琚繘涓�姝ユ帹杩涳紝褰撳墠婊戝潯鐏惧搴旀�ヨ皟鏌ヤ富瑕佷互鐩瑙h瘧鍜岄噹澶栬皟鏌ヤ负涓伙紝璐规椂璐瑰姏锛岄毦浠ユ弧瓒崇伨鍚庢晳鎻寸殑杩垏闇�姹傘�傞潰鍚戝儚鍏冨拰闈㈠悜瀵硅薄鐨勫崟鏃剁浉婊戝潯閬ユ劅淇℃伅鎻愬彇鏂规硶绛夊瓨鍦ㄧ潃婊戝潯杩囪瘑鍒�佽璇嗗埆鐨勯棶棰樸�傚洜姝わ紝鍦ㄦ鎻愬嚭浠ユ粦鍧″墠鍚庡鏃剁浉閬ユ劅褰卞儚涓烘暟鎹簮鐨勫彉鍖栨娴嬫粦鍧¤瘑鍒柟娉曪紝棣栧厛鏍规嵁褰掍竴鍖栨琚寚鏁帮紙NDVI锛夎繘琛屽熀浜庡儚鍏冪殑鍙樺寲妫�娴嬬‘瀹氭粦鍧¢閫夊尯锛屽啀缁撳悎闈㈠悜瀵硅薄鐨勫嚑浣曡鍒欏畬鎴愭粦鍧$殑绮剧粏璇嗗埆锛岃繖绉嶅熀浜庡彉鍖栨娴嬪拰鍑犱綍瑙勫垯鐩哥粨鍚堢殑鏂规硶鑳芥湁鏁堟帓闄ら亾璺�佸缓绛戙�佽8鍦扮瓑鍏夎氨鐗瑰緛涓庢粦鍧$浉浼肩殑闈炴粦鍧¢儴鍒嗐�備互涔濆娌熸粦鍧′负渚嬶紝閲囩敤楂樺垎涓�鍙�8 m 鍒嗚鲸鐜囧鍏夎氨鐩告満2015骞�8鏈�1鏃ョ殑褰卞儚锛堟粦鍓嶏級浠ュ強2017骞�8鏈�16鏃ョ殑褰卞儚锛堟粦鍚庯級浣滀负鏁版嵁婧愶紝杩涜婊戝潯璇嗗埆瀹為獙銆傜粨鏋滆〃鏄庯紝鍜岄潰鍚戝璞$殑鍗曟椂鐩告柟娉曠浉姣旓紝鍩轰簬鍙樺寲妫�娴嬪拰鍑犱綍瑙勫垯鐩哥粨鍚堢殑澶氭椂鐩告柟娉曟粦鍧℃彁鍙栫殑绮惧害杈冮珮锛屽埗鍥剧簿搴﹂珮杈�88.80%锛岀敤鎴风簿搴﹂珮杈�81.19%锛岄兘澶у箙瓒呰繃闈㈠悜瀵硅薄鍗曟椂鐩告硶鐨勭簿搴︼紝婕忓垎璇樊鍙婇敊鍒嗚宸垎鍒笅闄�23.22%鍜�11.72%锛屽彲涓烘湁鏁堢粍缁囨粦鍧$伨鍚庢晳鎻翠笌閲嶅缓宸ヤ綔鎻愪緵鍙潬渚濇嵁銆�

鍏抽敭璇�: 鐏惧淇℃伅鎻愬彇, 涔濆娌熸粦鍧�, 褰掍竴鍖栨琚寚鏁�, 婊戝潯璇嗗埆, 澶氭椂鐩搁仴鎰�, 鍙樺寲妫�娴�

Abstract:

With the development of the remote sensing technology锛� the high-resolution satellite data is gradually enriched锛� and the information extraction of landslide disaster is further promoted. The current emergency investigation of the landslide disaster mainly focuses on the visual interpretation and field investigation锛� which is time-consuming锛� laborious锛� and difficult to meet the urgent need of the rescue after disaster. The single-phase landslide information extraction methods by using remote sensing based on the pixel-oriented or object-oriented have problems of over-recognition or mis-recognition of landslides. Therefore锛� the multi-temporal landslide information extraction method is worth studying and is expected to achieve good results锛� especially through the notable NDVI change in landslide. First锛� multi-temporal remote sensing images before and after the landslide are used as the data source. The landslide pre-selection area is determined using the pixel-oriented NDVI change detection. Then锛� the object-oriented geometric rules are used to complete the fine identification of landslides. This method based on the combination of the change detection and geometric rules effectively eliminates non-landslide parts which are with the spectral characteristics similar to landslides锛� such as roads锛� buildings锛� and bare land. Taking Jiuzhaigou landslide as the study case锛� the Gaofen-1 multi-spectral images of August 1锛� 2015 锛坆efore Jiuzhaigou earthquake锛� and the images of August 16锛� 2017 锛坅fter the earthquake锛� are used as data sources to conduct landslide identification experiments. The experimental results show that the multi-phase method has high accuracy in landslide identification. Compared with the object-oriented single-phase method锛� the former method has a mapping accuracy of up to 88.80% and the user accuracy up to 81.19%锛� both of which greatly exceed the accuracy of the object-oriented single-phase method. Moreover锛� the omission error and the mis-classification error decreased by 23.22% and 11.72%锛� respectively. This method determines landslides through the change of NDVI and has high timeliness in landslide identification锛� which does not need to consider the restrictions of excessive topographic and geomorphic factors and can be applied to most areas. It is believed that our method can provide a reliable basis for the effective organization of rescue and reconstruction work after landslide disaster.

Key words: Disaster information extraction, Jiuzhaigou landslide, NDVI, Landslide identification, Multi-temporal remote sensing, Change detection

涓浘鍒嗙被鍙�: