Abstract:

Taking Nanning County of Jilin Province as the research area锛� using Sentinel-1B dual polarization data as data source锛� multiple texture eigenvalues of typical crops such as corn锛� soybean and rice were extracted锛� and the best crop identification parameters were selected. Combined with eCognition software The rule base in the model fully mines the attribute information contained in the texture features of crops in SAR data锛� constructs a decision tree锛� extracts typical crops based on object-oriented classification methods锛� and obtains the optimal classification phase of crops in the study area through the analysis of SAR crop extraction results. And the best crop identification texture information combination锛� classify and map each typical crop锛� and explore the feasibility of improving the accuracy of crop identification based on the back-scattering characteristics of SAR images. The results show that SAR data can provide richer crop texture information than optical data. Selecting suitable texture information as auxiliary data for classification can effectively solve the phenomenon of "foreign matter homology" in optical data and improve the accuracy of crop identification. The three SAR texture features that contribute the most to crop extraction are锛� mean锛� variance锛� and dissimilarity.

Key words: Sentinel-1B, Dual polarization SAR, Object-oriented classification, Decision tree, Texture feature

鎽樿锛�

浠ュ悏鏋楃渷鍐滃畨鍘夸负鐮旂┒鍖猴紝浠entinel-1B鍙屾瀬鍖栨暟鎹负鏁版嵁婧愶紝鎻愬彇鍑哄吀鍨嬪啘浣滅墿鐜夌背銆佸ぇ璞嗐�佹按绋荤殑澶氫釜绾圭悊鐗瑰緛鍊硷紝绛涢�夊嚭鏈�浣冲啘浣滅墿璇嗗埆绾圭悊淇℃伅鍙傛暟锛岀粨鍚坋Cognition杞欢涓殑瑙勫垯搴擄紝鍏呭垎鎸栨帢SAR鏁版嵁涓啘浣滅墿绾圭悊鐗瑰緛鍖呭惈鐨勫睘鎬т俊鎭紝鏋勫缓鍐崇瓥鏍戯紝鍩轰簬闈㈠悜瀵硅薄鍒嗙被鏂规硶瀵瑰吀鍨嬪啘浣滅墿杩涜鎻愬彇锛岄�氳繃SAR鍐滀綔鐗╂彁鍙栫粨鏋滅殑鍒嗘瀽锛岃幏寰楃爺绌跺尯鍐滀綔鐗╂渶浣冲垎绫绘椂鐩稿強鏈�浣冲啘浣滅墿璇嗗埆绾圭悊淇℃伅缁勫悎锛屽鍚勫吀鍨嬪啘浣滅墿杩涜鍒嗙被鍒跺浘锛屾帰璁ㄥ熀浜嶴AR褰卞儚鍚庡悜鏁ｅ皠鐗瑰緛鎻愰珮鍐滀綔鐗╄瘑鍒簿搴︾殑鍙鎬с�傜粨鏋滆〃鏄庯細SAR鏁版嵁鐩稿浜庡厜瀛︽暟鎹紝鑳芥彁渚涙洿涓板瘜鐨勫啘浣滅墿绾圭悊淇℃伅锛岄�夊彇鍚堥�傜殑绾圭悊淇℃伅浣滀负鍒嗙被杈呭姪鏁版嵁锛屽彲浠ユ湁鏁堣В鍐冲厜瀛︽暟鎹腑鈥滃紓鐗╁悓璋扁�濈幇璞★紝鎻愰珮鍐滀綔鐗╄瘑鍒簿搴︼紝瀵逛簬鐮旂┒鍖哄啘浣滅墿鎻愬彇璐＄尞鏈�澶х殑3绉峉AR绾圭悊鐗瑰緛渚濇涓猴細鍧囧�笺�佹柟宸拰鐩稿紓鎬с��

鍏抽敭璇�: Sentinel?1B, 鍙屾瀬鍖朣AR鏁版嵁, 闈㈠悜瀵硅薄鍒嗙被, 鍐崇瓥鏍�, 绾圭悊鐗瑰緛