决策树分类法及其在土地覆盖分类中的应用

doi:10.11873/j.issn.1004-0323.2002.1.6

閬ユ劅鎶�鏈笌搴旂敤鈥衡�� 2002, Vol. 17 鈥衡�� Issue (1): 6-11.DOI: 10.11873/j.issn.1004-0323.2002.1.6

鈥� 鐮旂┒涓庡簲鐢� 鈥� 涓婁竴绡� 涓嬩竴绡�

鍐崇瓥鏍戝垎绫绘硶鍙婂叾鍦ㄥ湡鍦拌鐩栧垎绫讳腑鐨勫簲鐢�

鏉� 鐖�^1,2,涓佸湥褰�¹,閽变箰绁�¹

(1.娌冲崡澶у鐜涓庤鍒掑闄� 娌冲崡寮�灏� 475001; 2.鑱婂煄甯堣寖瀛﹂櫌鍦扮悊绯� 娌冲崡鑱婂煄 252059)

鏀剁鏃ユ湡:2001-09-26 淇洖鏃ユ湡:2001-12-05 鍑虹増鏃ユ湡:2002-02-20 鍙戝竷鏃ユ湡:2011-11-21
浣滆�呯畝浠�:鏉庣埥(1974-),鐢�,璁插笀,涓昏浠庝簨GIS銆丷S搴旂敤鐮旂┒銆�
鍩洪噾璧勫姪:
鏈」鐩爺绌跺緱鍒版渤鍗楃渷鏉板嚭闈掑勾绉戝鍩洪噾璧勫姪(椤圭洰缂栧彿:0003,9920)銆�

The Decision Tree Classification and Its
Application Research in Land Cover

LI Shuang^1,2, DING Sheng-yan¹, QIAN Le-xiang¹

(1.College of Environment and Planning,Henan University,Kaifeng475001,China;
2.Department of Geography,Liaocheng Normal University,Liaocheng252059,China)

Received:2001-09-26 Revised:2001-12-05 Online:2002-02-20 Published:2011-11-21

鎽樿/Abstract

鎽樿锛�

鍩轰簬鍐崇瓥鏍戝垎绫荤畻娉曞湪閬ユ劅褰卞儚鍒嗙被鏂归潰鐨勬繁鍘氭綔鍔�,鎺㈣浜�3绉嶄笉鍚岀殑鍐崇瓥鏍戠畻娉�(UDT銆丮DT鍜孒DT)銆傞鍏堝鍐崇瓥鏍戠畻娉曠粨鏋勩�佺畻娉曠悊璁鸿繘琛屼簡闃愯堪,鐒跺悗鍒╃敤鍐崇瓥鏍戠畻娉曡繘琛岄仴鎰熷湡鍦拌鐩栧垎绫诲疄楠�,骞舵妸鑾峰緱鐨勭粨鏋滀笌浼犵粺缁熻鍒嗙被娉曡繘琛屾瘮杈冦�傜爺绌惰〃鏄�,鍐崇瓥鏍戝垎绫绘硶鏈夎澶氫紭鍔�,濡�:鐩稿绠�鍗曘�佹槑纭�佸垎绫荤粨鏋勭洿瑙�,鍙﹀,涓庝互鍋囧畾鏁版嵁婧愬憟涓�鍥哄畾姒傜巼鍒嗗竷,鐒跺悗鍦ㄦ鍩虹涓婅繘琛屽弬鏁颁及璁＄殑甯歌鍒嗙被鏂规硶鐩告瘮,鍐崇瓥鏍戝睘浜庝弗鏍�“闈炲弬”,瀵逛簬杈撳叆鏁版嵁绌洪棿鐗瑰緛鍜屽垎绫绘爣璇嗗叿鏈夋洿濂界殑寮规�у拰椴佹鎬�(Robust)銆�

鍏抽敭璇�: 鍐崇瓥鏍戝垎绫�, 閬ユ劅褰卞儚, 鏈�澶т技鐒跺垎绫绘硶

Abstract:

Decision tree classification algorithms have significant potential for remote sensing data classification.In this paper, three different types decision tree classification (UDT, MDT and HDT)are presented. First, the paper discussed the algorithms structure and the algorithms theory of decision tree. Second, decision tree algorithms were used to make land cover classification from remotely sensed data, and the results were compared with conventional statistics classification. The results of this research showed that decision trees have several advantages for remote sensing applications by virtue of their relatively simple, explicit, and intuitive classification
structure. In addition, decision tree algorithms are strictly nonparametric and, therefore, without assumptions
regarding the distribution of input data the methods are flexible and robust with respect to general classifications
among input features and class labels.

Key words: Decision tree classification, Remote sensing image, Maximum likelihood classification

涓浘鍒嗙被鍙�:

TP 75

鏉� 鐖�,涓佸湥褰�,閽变箰绁�. 鍐崇瓥鏍戝垎绫绘硶鍙婂叾鍦ㄥ湡鍦拌鐩栧垎绫讳腑鐨勫簲鐢╗J]. 閬ユ劅鎶�鏈笌搴旂敤, 2002, 17(1): 6-11.

LI Shuang, DING Sheng-yan, QIAN Le-xiang. The Decision Tree Classification and Its
Application Research in Land Cover[J]. Remote Sensing Technology and Application, 2002, 17(1): 6-11.

鍙傝�冩枃鐚�

銆�1銆� DeFries R, Hansen M, Townshend J. Global Discrimination of Land Cover Types from Metrics Derived from AVHRR Pathfinder Data銆擩銆�. Remote Sens Environ,1995,54:209~222.
銆�2銆� Safavian S R, Landgrebe D. A Survey of Decision Tree Classifer Methodology銆擩銆�. IEEE Trans Syst Man Cybern,1991,21:660~674.
銆�3銆� Friedl M A, Brodeley C E. Decision Tree Classification of Land Cover from Remotely Sensed Data銆擩銆�. Remote Sens Environ,1997,61:399~409.
銆�4銆� Defries R S, Townsend J R G. NDVI-derived Land Cover Classifications at a Global Scale銆擩銆�. Int J Remote Sens,1994,15:3567~3586.
銆�5銆� Loveland T R, Merchand J W, Ohlen D O,et al. Development of a Land-cover Characteristics Database for the Conterminous U.S銆擩銆�. Photogramm Eng Remote Sens,1991,57:1453~1463.
銆�6銆� Running S, Loveland T R, Pierce L L,et al. A Remote Sensing Based Vegetation Classification Logic for Global Land Cover Analysis銆擩銆�. Remote Sens Environ, 1995,51:39~48.
銆�7銆� 楠嗗墤鎵�,鍛ㄦ垚铏�,鏉ㄨ壋.浜哄伐绁炵粡缃戠粶閬ユ劅褰卞儚鍒嗙被妯″瀷鍙婂叾涓庣煡璇嗛泦鎴愭柟娉曠爺绌躲�擩銆�.閬ユ劅瀛︽姤,2001,2:122~129.
銆�8銆� 鏉ㄥ瓨寤�,鍛ㄦ垚铏�.鍩轰簬鐭ヨ瘑鐨勯仴鎰熷浘鍍忓垎绫绘柟娉曠殑鎺㈣銆擩銆�.鍦扮悊瀛︿笌鍥藉湡鐮旂┒, 2001,1:72~77.
銆�9銆� 闄堣堪褰�.閬ユ劅鍦板鍒嗘瀽鐨勬椂绌虹淮銆擩銆�.閬ユ劅瀛︽姤, 1997, 1(3):161~169.
銆�10銆曞瓩瀹朵笝,鑸掑畞,鍏虫辰缇�.閬ユ劅鍘熺悊銆佹柟娉曞拰搴旂敤銆擬銆�.鍖椾含:娴嬬粯鍑虹増绀�, 1997.
銆�11銆旴rodley C E. Recursive Automatic Bias Selection for Classifier Constrution銆擩銆�. Mach Learn,1995,20:63~94.
銆�12銆昋uinlan J R. Induction of Decision Trees銆擩銆�. Mach Learn,1986,1:81~106.
銆�13銆旴reiman L, Friedman J H, Olshen R A,et al. Classification and Regression Trees銆擩銆�. Wadsworth Belmont CA, 1984.
銆�14銆昐wain P H, Hauska H. The Decision Tree Classifier: Design and Potential銆擩銆�. IEEE Trans Geosci Remote Sens,1969,GE-15:142~147.
銆�15銆昁ittler J. Feature Selection and Extraction銆擜銆�. In Handbook of Pattern Recognition and Image Processing銆擟銆�. Academic Press New York,1986.

[1]	鍗㈠織鍒�,闄堣姵娣�,琚佽秴,鐢颁害闄�,闄堝己,鏂囩編骞�,灏归敶,鏉ㄥ厜. 閲囩敤I-PSPNet璇箟鍒嗗壊妯″瀷鐨勯珮鍒嗚鲸鐜囬仴鎰熷奖鍍忔煇鐗圭妞嶇墿绉嶆鍦板潡鎻愬彇鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(1): 222-233.
[2]	寮犳烦,钁涙瘏,浠昏秺,楂橀,闊╁媷,钁ｆ�濇簮,绉︽澃鑻�,璁歌讲,鍚曞┃,楂樿壋鑺�. 鍩轰簬浼樺寲鐨凞eeplabV3+缃戠粶鍜岄珮鍒嗗奖鍍忓垎鍓叉诞钀嶅瀷鍐滄潙榛戣嚟姘翠綋[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(6): 1433-1444.
[3]	鍒橀懌,榛勮繘,鏉ㄧ憶鐜�,鏉庡墤娉�. 鍩轰簬CenterNet鐨勬敼杩涢仴鎰熸棆杞洰鏍囨娴�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(5): 1081-1091.
[4]	寮犳垚鎵�,鍒樺▉,鏉ㄥ嘲,褰嚡,鍛ㄩ洩涓�. 鍩轰簬缂栫爜瀵归綈鐢熸垚瀵规姉缃戠粶鐨勫紓婧愰仴鎰熷奖鍍忓湴琛ㄨ琚彉鍖栨娴嬫柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(5): 1107-1117.
[5]	鑳¤吘浜�,瑙ｉ箯椋�,娓╀簹妤�,鎱曞彿浼�. 鍩轰簬涓嶅悓娣卞害瀛︿範妯″瀷鎻愬彇寤虹瓚杞粨鐨勬柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(4): 892-902.
[6]	寰愪腹,鏋楁枃楣�,椹竻. 鍩轰簬鏈哄櫒瀛︿範鐨勬鎴峰尯璇嗗埆搴旂敤鈥斺�斾互涓婃捣妫氭埛鍖轰负渚�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(4): 990-1002.
[7]	榛勪徊鑹�,浣曟暚,鍒樺垰,鏉庢斂. 闈㈠悜GEE骞冲彴鐨勯仴鎰熷奖鍍忓垎鏋愪笌搴旂敤鐮旂┒杩涘睍[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(3): 527-534.
[8]	璧典細鑺�,浜庡崥,闄堟柟,鐜嬮浄. 鍩轰簬楂樺垎杈ㄧ巼鍗槦閬ユ劅褰卞儚婊戝潯鎻愬彇鏂规硶鐮旂┒鐜扮姸[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(1): 108-115.
[9]	閭磋姵椋�,閲戞案娑�,寮犳枃璞�,寰愬,浣欐稕,寮犱附涓�,瑁磋幑鑾�. 鍩轰簬鏈哄櫒瀛︿範鐨勯仴鎰熷奖鍍忎簯妫�娴嬬爺绌惰繘灞�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(1): 129-142.
[10]	鍚曞紑浜�,渚槶闃�,榫氬惊寮�,鏉ㄧ. 涓�绉嶅熀浜嶢SR鍜孭APCNN鐨凬SCT鍩熼仴鎰熷奖鍍忚瀺鍚堟柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(4): 829-838.
[11]	鍙蹭匠鐫�,鐢宠寽,褰孩鏄�,鏉庡埄浼�,濮氭湀,姹槑绉�,鐜嬭尮. 鍩轰簬涓夌楂樺垎杈ㄧ巼褰卞儚鏍锋湰杩佺Щ瀛︿範鐨勫煄甯傛按浣撴彁鍙栫爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(3): 731-738.
[12]	鐜嬩慨鎴�,寮犻粠鏄�. 涓�绉嶅熀浜庡悓鎬佸叕閽ュ姞瀵嗙殑閬ユ劅褰卞儚鏁板瓧鎸囩汗鏂规[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(2): 532-538.
[13]	鍚存娆�,鍥藉阀鐪�,鑷ч噾榫�,涔旀偊,鏈变附,浣曚簯娴�. 鍩轰簬Landsat 8涓庡疄娴嬫暟鎹殑姘磋川鍙傛暟鍙嶆紨鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(4): 898-907.
[14]	楂樺瓙涓�,瀛欎紵浼�,绋嬫湅鏍�,鏉ㄥ垰,瀛熺ゥ瓒�. 铻嶅悎楂樺垎杈ㄧ巼閬ユ劅褰卞儚鍜孭OI鏁版嵁鐨勫鐗瑰緛娼滃湪璇箟淇℃伅鐢ㄤ簬璇嗗埆鍩庡競鍔熻兘鍖�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(3): 618-626.
[15]	闄堟晱,娼樹匠濞�,鏉庢睙鏉�,寰愮拹,鍒樺姞鏁�,闊╁仴,闄堝浜�. 缁撳悎VGGNet涓嶮ask R-CNN鐨勯珮鍒嗚鲸鐜囬仴鎰熷奖鍍忓缓璁剧敤鍦版娴�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(2): 256-264.

鍐崇瓥鏍戝垎绫绘硶鍙婂叾鍦ㄥ湡鍦拌鐩栧垎绫讳腑鐨勫簲鐢�

The Decision Tree Classification and Its
Application Research in Land Cover

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

鍐崇瓥鏍戝垎绫绘硶鍙婂叾鍦ㄥ湡鍦拌鐩栧垎绫讳腑鐨勫簲鐢�

The Decision Tree Classification and Its Application Research in Land Cover

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

The Decision Tree Classification and Its
Application Research in Land Cover