复杂地形区土地利用/土地覆被分类机器学习方法比较研究

doi:10.11873/j.issn.1004-0323.2019.1.0057

鎽樿/Abstract

鎽樿锛�

閽堝楂樻捣鎷斿鏉傚湴褰㈠尯鍦拌矊绫诲瀷澶嶆潅銆佸鏍凤紝娌熷绾垫í銆佸湴褰㈢牬纰庣瓑鐗圭偣锛岀爺绌跺揩閫熴�佹湁鏁堢殑鍦熷湴鍒╃敤/鍦熷湴瑕嗚鍒嗙被鏂规硶瀵瑰湡鍦板埄鐢ㄤ俊鎭幏鍙栧強鏇存柊鏄潪甯搁噸瑕佺殑銆備互浣嶄簬榛勫湡楂樺師鍚戦潚钘忛珮鍘熻繃娓″甫鐨勬篃姘存祦鍩熶负鐮旂┒鍖哄煙锛屽熀浜嶭andsat 8 OLI褰卞儚鏁版嵁銆丏EM鏁版嵁锛屽苟缁撳悎鍚勭涓撻鐗瑰緛锛屽湪瀵圭爺绌跺尯杩涜鍦扮悊鍒嗗尯鐨勫熀纭�涓婏紝閲囩敤浜哄伐绁炵粡缃戠粶銆佸喅绛栨爲銆佹敮鎸佸悜閲忔満鍜岄殢鏈烘．鏋�4绉嶆満鍣ㄥ涔犳柟娉曡繘琛屽湡鍦板埄鐢ㄤ俊鎭彁鍙栧苟杩涜绮惧害璇勪环锛屾帰绱㈤�傚悎浜庡鏉傚湴褰㈠尯鏈�浼樼殑鍒嗙被鏂规硶銆傜爺绌剁粨鏋滆〃鏄庯細闅忔満妫灄鍜屽喅绛栨爲鐨勫垎绫荤簿搴︽槑鏄鹃珮浜庢敮鎸佸悜閲忔満鍜屼汉宸ョ缁忕綉缁溿�傚叾涓殢鏈烘．鏋楁柟娉曠殑鍒嗙被绮惧害鏈�楂橈紝鎬讳綋鍒嗙被绮惧害杈�85.65%锛孠appa绯绘暟杈�0.84銆傚湪涓婅堪鍒嗙被鍩虹涓婏紝閫夋嫨闅忔満妫灄鍒嗙被鏂规硶瀵筁andsat 8鍏ㄨ壊涓庡鍏夎氨褰卞儚铻嶅悎鏁版嵁杩涜杩涗竴姝ョ殑鍒嗙被鐮旂┒锛屾�讳綋鍒嗙被绮惧害杈惧埌[JP]86.49%锛孠appa绯绘暟杈�0.85銆傝繖琛ㄦ槑闅忔満妫灄鍒嗙被鏂规硶鍦ㄤ繚璇佸垎绫荤簿搴︾殑鍚屾椂鍙堣兘鑾峰緱杈冮珮鐨勫垎绫绘晥鐜囷紝瀵逛簬澶嶆潅鍦板舰鍖哄湡鍦板埄鐢ㄤ俊鎭彁鍙栨槸闈炲父鏈夋晥鐨勶紝鏁版嵁铻嶅悎鍦ㄤ竴瀹氱▼搴︿笂鎻愰珮浜嗗垎绫荤簿搴︺��

鍏抽敭璇�: , 鍦熷湴鍒╃敤/鍦熷湴瑕嗚鍒嗙被锛汱andsat OLI褰卞儚锛涙満鍣ㄥ涔狅紱浜哄伐绁炵粡缃戠粶锛涘喅绛栨爲锛涙敮鎸佸悜閲忔満锛涢殢鏈烘．鏋楋紱婀熸按娴佸煙

Abstract: Aiming at the characteristics of varied and complex geomorphic types锛宑risscross network of ravines and broken terrain in high altitude complicated terrain regions锛宨t is very important to study and find the rapid and effective land use/land cover classification method for obtaining and timely updating of land use information.Taking the Huangshui river basin located in the transitional zone between the Loess Plateau and the Qinghai-Tibet Plateau as acasestudy area锛宼he objective of this study is to explore a kind of effective information extraction method from comparison of four kinds machine learning methods for complicated terrain regions.based on Landsat 8 OLI satellite data锛孌EM and combined with various thematic features锛宱n the basis of geographical division of the study area锛宎rtificial neural network锛宒ecision tree锛宻upport vector machine and random forest four machine learning methods for land use information extraction were used to obtain land use data锛宎nd confusion matrix was constructed to evaluate classification accuracy.The results showed that the classification accuracies of random forest and decision tree are obviously higher than those of support vector machine and artificial neural network.The random forest method has the highest classification accuracy锛宼he overall classification accuracy is 85.65%锛宼he Kappa coefficient is 0.84.based on the above classification锛孯andom forest classification method was chose to further classify Landsat 8 fusion datafrom panchromatic 15 meter and multispectral 30 meter image锛宼he overall classification accuracy is 86.49% and the Kappa coefficient is 0.85.This indicated that the random forest classification method can obtain higher classification efficiency while ensuring the classification accuracy.It is very effective for the extraction of land use information in complicated terrain regions.Data fusion can improve the classification accuracy to a certain extent.

Key words: Land use/land cover classification, Landsat OLI images, Machine learning, Artificial neural network, Decision tree, Support vector machine, Random forest, the Huangshui river basin

涓浘鍒嗙被鍙�:

TP79

璋锋檽澶�, 楂樺皬绾�, 椹収濞�, 鍙查椋�, 鍒橀洩姊�, 鏇规檽鏁�. 澶嶆潅鍦板舰鍖哄湡鍦板埄鐢�/鍦熷湴瑕嗚鍒嗙被鏈哄櫒瀛︿範鏂规硶姣旇緝鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(1): 57-67.

Gu Xiaotian, Gao Xiaohong, Ma Huijuan, Shi Feifei, Liu Xuemei, Cao Xiaomin顎�. Comparison of Machine Learning Methods for Land Use/Land Cover Classification in the Complicated Terrain Regions[J]. Remote Sensing Technology and Application, 2019, 34(1): 57-67.

鍙傝�冩枃鐚�

锛�1锛絁ia Kun锛孡i Qiangzi锛孴ian Yichen锛宔t al.A Review of Classification Methods of Remote Sensing Imagery[J].Spectroscopy and Spectral Analysis锛�2011锛�31(10)锛�2618-2623.[璐惧潳锛屾潕寮哄瓙锛岀敯浜﹂檲锛岀瓑.閬ユ劅褰卞儚鍒嗙被鏂规硶鐮旂┒杩涘睍[J].鍏夎氨瀛︿笌鍏夎氨鍒嗘瀽锛�2011锛�31(10)锛�2618-2623.] [2]Zhao Jing锛學ang Chongchang锛學ang Jiahai锛宔t al.Remote Sensing Image Classification Method based on Cloud Theory[J].Engineering of Surveying and Mapping锛�2014锛�23(12)锛�21-24.[璧甸潤锛岀帇宕囧�★紝鐜嬪娴凤紝绛�.鍩轰簬浜戠悊璁虹殑閬ユ劅褰卞儚鍒嗙被鏂规硶鍒嗘瀽[J].娴嬬粯宸ョ▼锛�2014锛�23(12)锛�21-24.] [3]Oza N C锛孴umer K.Classifier Ensembles锛歋elect Real-World Applications[J].Information Fusion锛�2008锛�9(1)锛�4-20. [4]Mitchell T M.Machine Learning[M].Portland锛歁c Graw Hill锛�1997. [5]Zhao Danping锛孏u Haiyan锛孞ia Ying.Comparison of Machine Learning Method in Object-based Image Classification[J].Science of Surveying and Mapping锛�2016锛�41(10)锛�181-186.[璧典腹骞筹紝椤炬捣鐕曪紝璐捐幑.鏈哄櫒瀛︿範娉曞湪闈㈠悜瀵硅薄褰卞儚鍒嗙被涓殑瀵规瘮鍒嗘瀽[J].娴嬬粯绉戝锛�2016锛�41(10)锛�181-186.] [6]Zhang Run锛學ang Yongbin.Research on Machine Learning With Algorithm and Development[J].Journal of Communication University of China锛歋cience and Technology Edition锛�2016锛�23(2)锛�10-18.[寮犳鼎锛岀帇姘告花.鏈哄櫒瀛︿範鍙婂叾绠楁硶鍜屽彂灞曠爺绌禰J].涓浗浼犲獟澶у瀛︽姤锛氳嚜鐒剁瀛︾増锛�2016锛�23(2)锛�10-18.][JP] [7]Xiu Lina锛孡iu Xiangnan.Current Status and Future Direction of the Study on Artificial Neural Network Classification Processing in Remote Sensing[J].Remote Sensing Technology and Application锛�2003锛�18(5)锛�339-345.[淇附濞滐紝鍒樻箻鍗�.浜哄伐绁炵粡缃戠粶閬ユ劅鍒嗙被鏂规硶鐮旂┒鐜扮姸鍙婂彂灞曡秼鍔挎帰鏋怺J].閬ユ劅鎶�鏈笌搴旂敤锛�2003锛�18(5)锛�339-345.] [8]Han Tingting锛孹i Xiaohuan锛學ang Cheng锛宔t al.Study on Forest Classification in Yunnan based on Decision Tree Algorithm[J].Remote Sensing Technology and Application锛�2014锛�29(5)锛�744-751.[闊╁┓濠凤紝涔犳檽鐜紝鐜嬫垚锛岀瓑.鍩轰簬鍐崇瓥鏍戞柟娉曠殑浜戝崡鐪佹．鏋楀垎绫荤爺绌禰J].閬ユ劅鎶�鏈笌搴旂敤锛�2014锛�29(5)锛�744-751.] [9]Yang Changkun锛學ang Chongchang锛孼hang Dingkai锛宔t al.Classification of GF-1 Satellite Image based on SVM[J].Geomatics 锛� Spatial Information Technology锛�2015(9)锛�142-144.[鏉ㄩ暱鍧わ紝鐜嬪磭鍊★紝寮犻紟鍑紝绛�.鍩轰簬SVM鐨勯珮鍒嗕竴鍙峰崼鏄熷奖鍍忓垎绫籟J].娴嬬粯涓庣┖闂村湴鐞嗕俊鎭紝2015(9)锛�142-144.] [10]Yao Minghuang.Random Forests and Its Application to the Classification of Remote Sensing Image[D].Quanzhou锛欻uaqiao University锛�2014.[濮氭槑鐓�.闅忔満妫灄鍙婂叾鍦ㄩ仴鎰熷浘鍍忓垎绫讳腑鐨勫簲鐢╗D].娉夊窞锛氬崕渚ㄥぇ瀛︼紝2014.] [11]Wang Tingting锛孡i Shanshan锛孡i An锛宔t al.Land Cover Classification in Beijing Using Landsat 8 Image[J].Journal of Image and Graphics锛�2015锛�20(9)锛�1275-1284.[鐜嬪┓濠凤紝鏉庡北灞憋紝鏉庡畨锛岀瓑.鍩轰簬Landsat 8鍗槦褰卞儚鐨勫寳浜湴鍖哄湡鍦拌鐩栧垎绫籟J].涓浗鍥捐薄鍥惧舰瀛︽姤锛�2015锛�20(9)锛�1275-1284.] [12]Xu H Q锛孴ang F.Analysis of New Characteristics of the First Landsat 8 Image and Their Eco-Environmental Significance[J].Acta Ecologica Sinica锛�2013锛�33(11)锛�3249-3257. [13]Song Fuqiang锛孠ang Muyi锛孼heng Zhuangli锛宔t al.Land Use and Land Cover Classification and Verification in Northern Shaanxi Loess Plateau[J].Transactions of the CSAE锛�2011锛�27(3)锛�316-324.[瀹嬪瘜寮猴紝搴锋厱璋婏紝閮戝．涓斤紝绛�.闄曞寳榛勫湡楂樺師鍦板尯鍦熷湴鍒╃敤/瑕嗚鍒嗙被鍙婇獙璇乕J].鍐滀笟宸ョ▼瀛︽姤锛�2011锛�27(3)锛�316-324.] [14]Liu Yi锛孌u Peijun锛孼heng Hui锛宔t al.Classification of China Small Satellite Remote Sensing Image based on Random Forests[J].Science of Surveying and Mapping锛�2012锛�37(4)锛�198-200.[鍒樻瘏锛屾潨鍩瑰啗锛岄儜杈夛紝绛�.鍩轰簬闅忔満妫灄鐨勫浗浜у皬鍗槦閬ユ劅褰卞儚鍒嗙被鐮旂┒[J].娴嬬粯绉戝锛�2012锛�37(4)锛�198-200.] [15]Wang Yannan锛學ang Jianjian锛孏ong Jianxin锛宔t al.Detection of Coastal Tidal Flat Using the Random Forests Method and HJ Satellite Images[J].Remote Sensing Technology and Application锛�2016锛�31(6)锛�1107-1113.[鐜嬭壋妤狅紝鐜嬪仴鍋ワ紝榫氬仴鏂帮紝绛�.鍩轰簬鐜鍗槦鏁版嵁鐨勬部娴锋哗娑傚湴鐗╃被鍨嬪垎绫荤殑闅忔満妫灄鏂规硶[J].閬ユ劅鎶�鏈笌搴旂敤锛�2016锛�31(6)锛�1107-1113.] [16][KG*5/6]Zeng Yongnian锛孞in Wenping锛孒e Lili锛宔t al.Land Use Mapping Using Remote Sensing for Eastern Part of Qinghai Plateau[J].Transactions of the Chinese Society of Agricultural Engineering锛�2012锛�28(16)锛�225-231.[鏇炬案骞达紝闈虫枃鍑紝浣曚附涓斤紝绛�.闈掓捣楂樺師涓滈儴鍐滀笟鍖哄湡鍦板埄鐢ㄩ仴鎰熷垎绫诲埗鍥綶J].鍐滀笟宸ョ▼瀛︽姤锛�2012锛�28(16)锛�225-231.] [17]Li Jinshan.Research on Automatical Classification of Land Use/Land Cover Change in Complicated Terrain Regions-A Case Study of Huangshui River Basin[D].Xining锛歈inghai Normal University锛�2013.[鏉庨噾灞�.澶嶆潅鍦板舰鍖哄湡鍦板埄鐢�/鍦熷湴瑕嗚鍒嗙被鐮旂┒[D].瑗垮畞锛氶潚娴峰笀鑼冨ぇ瀛︼紝2013.] [18]Jia Wei.Land Use Information Extraction for Complicated Terrain Regions from Object-oriented Classification Technique锛欰 Case Study of the Huangshui River Basin锛孮inghai[D].Xining锛歈inghai Normal University锛�2015.[璐句紵.闈㈠悜瀵硅薄鐨勫鏉傚湴褰㈠尯鍦熷湴鍒╃敤淇℃伅鎻愬彇鐮旂┒[D].瑗垮畞锛氶潚娴峰笀鑼冨ぇ瀛︼紝2015.] [19]Xu Hanqiu.A Study on Information Extraction of Water Body With the Modified Normalized Difference Water Index (MNDWI)[J].Journal of Remote Sensing锛�2005锛�9(5)锛�589-595.[寰愭兜绉�.鍒╃敤鏀硅繘鐨勫綊涓�鍖栧樊寮傛按浣撴寚鏁�(MNDWI)鎻愬彇姘翠綋淇℃伅鐨勭爺绌禰J].閬ユ劅瀛︽姤锛�2005锛�9(5)锛�589-595.] [20]Yang Shan.On Extraction and Fractal of Urban and Rural Residential Spatial Pattern in Developed Area[J].Acta Geographica Sinica锛�2000锛�55(6)锛�671-678.[鏉ㄥ北.鍙戣揪鍦板尯鍩庝埂鑱氳惤褰㈡�佺殑淇℃伅鎻愬彇涓庡垎褰㈢爺绌�--浠ユ棤閿″競涓轰緥[J].鍦扮悊瀛︽姤锛�2000锛�55(6)锛�671-678.] [21]Jia Yonghong.Application of Artificial Neural Network to Classification of Multi-Source Remote Sensing Imagery[J].Bulletin of Surveying and Mapping锛�2000(7)锛�7-8.[璐炬案绾�.浜哄伐绁炵粡缃戠粶鍦ㄥ婧愰仴鎰熷奖鍍忓垎绫讳腑鐨勫簲鐢╗J].娴嬬粯閫氭姤锛�2000(7)锛�7-8.] [22]Hou Haiyan锛孒ou Jinliang锛孒uang Chunlin锛宔t al.Retrieve Snow Depth of North of Xinjiang Region from ARMS2 Data based on Artificial Neural Network Technology[J].Remote Sensing Technology and Application锛�2018锛�33(2)锛�241-251.[渚捣鑹筹紝渚噾浜紝榛勬槬鏋楋紝绛�.鍩轰簬浜哄伐绁炵粡缃戠粶鍜孉MSR2澶氶寰尝浜俯鐨勫寳鐤嗗湴鍖洪洩娣卞弽婕擺J].閬ユ劅鎶�鏈笌搴旂敤锛�2018锛�33(2)锛�241-251.] [23]Vapnik V.The Natureof Statistical Learning Theory[C]鈭pringer-Verlag New York锛孖nc.1995锛�988-999. [24]Chen Yangbo锛孼hang Tao锛孌ou Peng锛宔t al.Error Sources and Post Processing Method for Land Use/Cover Change Estimation of Dongguan City based on Landsat Remote Sensing Imagery With SVM[J].Remote Sensing Technology and Application锛�2017锛�32(5).[闄堟磱娉紝寮犳稕锛岀楣忥紝绛�.鍩轰簬SVM鐨勪笢鑾炲競鍦熷湴鍒╃敤/瑕嗚鑷姩鍒嗙被璇樊鏉ユ簮涓庡悗澶勭悊[J].閬ユ劅鎶�鏈笌搴旂敤锛�2017锛�32(5).] [25]Xiong Wei锛孹u Yongli锛孻ao Libo锛宔t al.A New Ship Target Detection Algorithm based on SVM in High Resolution SAR Images[J].Remote Sensing Technology and Application锛�2018锛�33(1)锛�119-127.[鐔婁紵锛屽緪姘稿姏锛屽鍔涙尝锛岀瓑.鍩轰簬SVM鐨勯珮鍒嗚鲸鐜嘢AR鍥惧儚鑸拌埞鐩爣妫�娴嬬畻娉昜J].閬ユ劅鎶�鏈笌搴旂敤锛�2018锛�33(1)锛�119-127.] [26]Li Miaomiao锛學u Bingfang锛孻an Changzhen锛宔t al.Estimation of Vegetation Fraction in the Upper Basin of Miyun Reservoir by Remote Sensing[J].Resources Science锛�2004锛�26(4)锛�153-159.[鏉庤嫍鑻楋紝鍚寸偝鏂癸紝棰滈暱鐝嶏紝绛�.瀵嗕簯姘村簱涓婃父妞嶈瑕嗙洊搴︾殑閬ユ劅浼扮畻[J].璧勬簮绉戝锛�2004锛�26(4)锛�153-159.] [27]Shi Shilian锛孼hang Wenbo锛學ang Guoyan.The Measurement of Vegetation Coverage and the Analysis of Seasonal Change in Beijing[J].Remote Sensing Technology and Application锛�2014锛�29(5)锛�866-872.[鍙蹭笘鑾诧紝绔犳枃娉紝鐜嬪浗鐕�.鍖椾含鍦板尯妞嶈鐩栧害鎻愬彇鍙婂叾鍒嗗竷鍙樺寲鐮旂┒[J].閬ユ劅鎶�鏈笌搴旂敤锛�2014锛岊��29(5)锛氼��866-872.] [28]Breiman L.Random Forests[J].Machine Learning锛�2001锛�45(1)锛�5-32. [29]Guo Yubao锛孋hi Tianhe锛孭eng Ling锛宔t al.Classification of GF-1 Remote Sensing Image based on Random Forests for Urban Land Use[J] Bulletin of Surveying and Mapping锛�2016(5)锛�73-76.[閮帀瀹濓紝姹犲ぉ娌筹紝褰幉锛岀瓑.鍒╃敤闅忔満妫灄鐨勯珮鍒嗕竴鍙烽仴鎰熸暟鎹繘琛屽煄甯傜敤鍦板垎绫籟J].娴嬬粯閫氭姤锛�2016(5)锛�73-76.] [30]Wang Dong锛孻ue Cairong锛孴ian Chuanzhao锛宔t al.Classification of TM Remote Sensing Image based on Random Forests of Dayao County[J].Forest Inventory and Planning锛�2014(2)锛�1-5.[鐜嬫爧锛屽渤褰╄崳锛岀敯浼犲彫锛岀瓑.鍩轰簬闅忔満妫灄鐨勫ぇ濮氬幙 TM 閬ユ劅褰卞儚鍒嗙被鐮旂┒[J].鏋椾笟璋冩煡瑙勫垝锛�2014(2)锛�1-5.] [31]Breiman L.Statistical Modeling锛歍he Two Cultures[J].Statistical Science锛�2001锛�16(3)锛�199-215. [32]Chen Weimin锛孼hang Ling锛孲ong Dongmei锛宔t al.Research on Hyperspectral Imagery Land Cover Classification Method based on AdaBoost Improved Random Forest[J].Remote Sensing Technology and Application锛�2018锛�33(4)锛�612-620.[闄堜紵姘戯紝寮犲噷锛屽畫鍐锛岀瓑.鍩轰簬AdaBoost鏀硅繘闅忔満妫灄鐨勯珮鍏夎氨鍥惧儚鍦扮墿鍒嗙被鏂规硶鐮旂┒[J].閬ユ劅鎶�鏈笌搴旂敤锛�2018锛�33(4)锛�612-620] [33]Zhao Yu锛學ang Hong锛孼hang Zhenzhen.Forest Healthy Classification of Robinia Pseudoacacia in the Yellow River Delta锛孋hina based on Spectral and Spatial Remote Sensing Variables Using Random Forest[J].Remote Sensing Technology and Application锛�2016锛�31(2)锛�359-367.[璧电帀锛岀帇绾紝寮犵弽鐝�.鍩轰簬閬ユ劅鍏夎氨鍜岀┖闂村彉閲忛殢鏈烘．鏋楃殑榛勬渤涓夎娲插埡妲愭灄鍋ュ悍绛夌骇鍒嗙被[J].閬ユ劅鎶�鏈笌搴旂敤锛�2016锛�31(2)锛�359-367.] [34]Liaw A锛學iener M.Classification and Regression by random Forest[J].Rnews锛�2002锛�23(23)锛�18-22.

[1]	绾ⅵ璞�, 鍞愪集鎯�, 鏉庡彫鑹�. 澶槼璇卞鍙剁豢绱犺崸鍏夌殑鍗槦閬ユ劅鍙嶆紨鏂规硶鐮旂┒杩涘睍[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(3): 455-466.
[2]	鐜嬫�濇亽, 榛勯暱骞�, 寮犵珛绂�, 楂樻樉杩�, 浠樺畨姘�. 闄嗗湴鐢熸�佺郴缁熺⒊鐩戞祴鍗槦杩滅孩娉㈡鍙剁豢绱犺崸鍏夊弽婕旂畻娉曡璁�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(3): 476-487.
[3]	鐢版収鎱�, 鍐� 鑾�, 璧电拪鐠�, 閮� 鏉�, 钁ｇ户浼�. 鏃犱汉鏈虹儹绾㈠鍩庡競鍦拌〃娓╁害绮剧粏鐗瑰緛鐮旂┒ [J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(3): 553-563.
[4]	鏉庨暱鏄�, 寰愯僵, 鍖呭畨鏄�, 鍒橀洩宄�, 鏉ㄦ枃鏀�顎�. 鍩轰簬FY3B-MWRI鏁版嵁鏂扮枂鍖哄煙绉洩娣卞害鍙嶆紨[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2018, 33(6): 1030-1036.
[5]	閫勯敠濞�,瀛欑澘,鐜嬫倍顎�. 楂樺垎杈ㄧ巼褰卞儚閰嶅噯璇樊瀵瑰湡鍦拌鐩栧垎绫诲拰鍙樺寲妫�娴嬬殑褰卞搷[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2014, 29(3): 498-505.
[6]	娼樹僵鑺�,鏉ㄦ骞�,鎴存檽鐖�,閮戣彔顎�. 涓嶅悓妫灄妞嶈鐨勯珮鍏夎氨鐗瑰緛鍒嗘瀽顎�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2013, 28(6): 1000-1005.
[7]	鍞愭檽鐕�,楂樻槅,鍊浗寮�. 楂樺厜璋卞浘鍍忛潪绾挎�цВ娣锋柟娉曠殑鐮旂┒杩涘睍[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2013, 28(4): 731-738.
[8]	璧垫櫠鏅额��, 鏉庢檽鏉�, 榛勬収钀�, 瑁翠寒, 鍚寸偝鏂�. 鍩轰簬TM6鐨勫煄甯傚眳姘戝缓绛戣妭鑳界爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2009, 24(6): 766-771.
[9]	鏉庡, 棰滈暱鐝�. 鍒╃敤MODIS妞嶈鎸囨暟璇勪及鍒嗘按瀵归粦娌充腑娓哥殑褰卞搷[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2009, 24(6): 793-796.
[10]	鐜嬪溅, 鏉庢枃鑺�. 閬ユ劅鍙婇儴鍒嗙浉鍏冲绉慡CI鏀跺綍鏈熷垔浠嬬粛[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2009, 24(6): 855-858.
[11]	楂樺, 鐭抽煣, 棰夎��鏂�. 钀藉彾鏉炬棭钀界梾鍗卞鐨勫厜璋辩壒寰佸強涓庡彾缁跨礌娴撳害鐨勫叧绯荤爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2007, 22(6): 710-714.
[12]	濮滅珛楣�, 瑕冨織璞�, 璋€��闆�. 閽堝MODIS 鏁版嵁鐨勫湴琛ㄦ俯搴﹂潪绾挎�ц凯浠ｅ弽婕旀柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2006, 21(6): 483-487.
[13]	鍠绘灄闈�, 椴佸畨鏂�, 鍐夊痉鐢�, 鐜嬩附绾�, 寮犱笘寮�. 鍥介亾214 绾胯タ钘忓婊戝鐏惧閬ユ劅璋冩煡鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2006, 21(6): 517-520.
[14]	鏉庡畧娉�, 璧典紶鐕�. 鍩轰簬鑳介噺骞宠　鐨勫叧宸濇渤娴佸煙钂告暎鍙戠殑閬ユ劅鍙嶆紨[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2006, 21(6): 521-526.
[15]	寮犮��宄�, 鐜嬨��妗�, 鐜嬫枃鏉�, 鐢虫枃鏄�, 缃楁捣姹�, 鍒樻檽鏇�. 缇庡浗楂樺垎杈ㄧ巼鍦熷湴瑕嗙洊淇℃伅鎻愬彇鎶�鏈爺绌惰繘灞�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2006, 21(6): 593-600.

澶嶆潅鍦板舰鍖哄湡鍦板埄鐢�/鍦熷湴瑕嗚鍒嗙被鏈哄櫒瀛︿範鏂规硶姣旇緝鐮旂┒

Comparison of Machine Learning Methods for Land Use/Land Cover Classification in the Complicated Terrain Regions

PDF (PC)

鍙鍖�

鎽樿/Abstract

寮曠敤鏈枃

浣跨敤鏈枃

鍙傝�冩枃鐚�

鐩稿叧鏂囩珷 15

缂栬緫鎺ㄨ崘

Metrics

鏈枃璇勪环