閬ユ劅鎶�鏈笌搴旂敤 鈥衡�� 2022, Vol. 37 鈥衡�� Issue (1): 161-172.DOI: 10.11873/j.issn.1004-0323.2022.1.0161

鈥� 闈掍績浼氬崄鍛ㄥ勾涓撴爮 鈥� 涓婁竴绡�    涓嬩竴绡�

鍩轰簬缃戠粶鍥剧殑鍦板熀婵�鍏夐浄杈惧鏉傛爲鏈ㄧ偣浜戞灊鍙跺垎绂绘柟娉�

鏋楃娑�1,2(),鏉庣埍鍐�1(),杈归噾铏�1,寮犳寤�1,2,鍗楀笇1   

  1. 1.涓浗绉戝闄㈡按鍒╅儴鎴愰兘灞卞湴鐏惧涓庣幆澧冪爺绌舵墍鏁板瓧灞卞湴涓庨仴鎰熷簲鐢ㄤ腑蹇冿紝鍥涘窛 鎴愰兘 610041
    2.涓浗绉戝闄㈠ぇ瀛﹁祫婧愪笌鐜瀛﹂櫌锛屽寳浜� 100049
  • 鏀剁鏃ユ湡:2021-10-08 淇洖鏃ユ湡:2022-01-05 鍑虹増鏃ユ湡:2022-02-20 鍙戝竷鏃ユ湡:2022-04-08
  • 閫氳浣滆��: 鏉庣埍鍐�
  • 浣滆�呯畝浠�:鏋楃娑碉紙1996鈥旓級锛屽北涓滃▉娴蜂汉锛岀敺锛岀澹爺绌剁敓锛屼富瑕佷粠浜嬫縺鍏夐浄杈鹃仴鎰熺爺绌躲�侲?mail锛�linxiaohan@imde.ac.cn
  • 鍩洪噾璧勫姪:
    鍥藉閲嶇偣鐮斿彂璁″垝椤圭洰鈥滃北鍦扮敓鎬佺郴缁熷叏鐞冨彉鍖栧叧閿弬鏁扮珛浣撹娴嬩笌楂樺垎杈ㄧ巼浜у搧鐮斿埗鈥�(2020YFA0608700);鍥藉鑷劧绉戝鍩洪噾椤圭洰鈥滃北鍦板吀鍨嬬敓鎬佸弬閲忛仴鎰熷弽婕斿缓妯″強鍏舵椂绌鸿〃寰佽兘鍔涚爺绌垛��(41631180)

A Method for Separating Leaf and Wood Components of Complex Tree Point Cloud Data based on Network Graph with Terrestrial Laser Scanning

Xiaohan Lin1,2(),Ainong Li1(),Jinhu Bian1,Zhengjian Zhang1,2,Xi Nan1   

  1. 1.Center for Digital Mountain and Remote Sensing Application锛孖nstitute of Mountain Hazards and Environment锛孋hinese Academy of Sciences锛孋hengdu 610041锛孋hina
    2.University of Chinese Academy of Sciences锛孊eijing 100049锛孋hina
  • Received:2021-10-08 Revised:2022-01-05 Online:2022-02-20 Published:2022-04-08
  • Contact: Ainong Li

鎽樿锛�

鍦板熀婵�鍏夐浄杈炬爲鏈ㄧ偣浜戞暟鎹殑鏋濆彾鍒嗙鏄簿纭绠楀湴涓婄敓鐗╅噺鍜屽彾闈㈢Н鎸囨暟鐨勯噸瑕佸墠鎻愶紝涔熸槸鏍戞湪涓夌淮寤烘ā鐨勯噸瑕佹楠ゃ�傜劧鑰岋紝灞卞湴澶嶆潅鏍戞湪鍐犲箙澶т笖缁撴瀯澶嶆潅锛屼粠鑰岄�犳垚鏍戝彾涓庢灊骞蹭箣闂寸殑鐩镐簰閬尅锛屽洜姝ゅ緢闅捐幏鍙栭珮璐ㄩ噺鐨勭偣浜戞暟鎹紝鐩墠瀵瑰叾瀹炵幇鏋濆彾鍒嗙渚濈劧瀛樺湪杈冨ぇ鐨勫洶闅俱�傚埄鐢ㄥ湴鍩烘縺鍏夐浄杈綟ARO Focus3D X330鑾峰彇涓夌淮婵�鍏夌偣浜戞暟鎹紝鎻愬嚭浜嗕竴绉嶅熀浜庣綉缁滃浘鐨勬爲鏈ㄧ偣浜戞灊鍙跺垎绂绘柟娉曘�傞鍏堬紝閲囩敤LeWos妯″瀷瀵圭偣浜戣繘琛屽垵姝ョ殑鏋濆彾鍒嗙锛屽垎绂诲嚭鏋濆共鍜屽彾鐗囩偣浜戙�傚湪姝ゅ熀纭�涓婏紝閽堝鏋濆共鍜屽彾鐗囨贩鍚堢偣浜戦�氳繃璺緞杩借釜妫�娴嬬畻娉曟潵绮剧粏鍒嗙鏋濆共鍜屽彾鐗囥�傞殢鐫�璺緞闀垮害浠�10澧炲姞鍒�100锛屾灊骞茬偣涓嶆柇澧炲姞锛屽彾鐗囩偣涓嶆柇鍑忓皯锛屾灊鍙跺垎绂荤簿纭害銆佹灊骞睩鍒嗘暟銆佸彾鐗嘑鍒嗘暟銆並appa绯绘暟鍧囧厛澧炲姞鍚庡噺灏戙�傜患鍚堣繖4椤圭簿搴﹁瘎浠锋寚鏍囷紝閫夊彇鍚勪釜鏍戞湪鏈�浼樿矾寰勯暱搴︽墽琛岃矾寰勮拷韪娴嬬畻娉曘�傞�氳繃涓嶭eWos妯″瀷銆乀lseparation妯″瀷鍜岄珮鏂贩鍚堟ā鍨嬬瓑涓绘祦鏋濆彾鍒嗙鏂规硶姣旇緝鍙戠幇锛岃鏂规硶绮惧害鏇翠紭锛岀簿纭害涓�91.97%銆傝�屼笖锛岃鏂规硶鐨勬灊骞睩鍒嗘暟鍜屽彾鐗嘑鍒嗘暟鍧囧ぇ浜�85%锛岃繖琛ㄦ槑璇ユ柟娉曞叿鏈夊緢濂界殑骞宠 鎬с�傝鏂规硶浠呬娇鐢ㄨ矾寰勯暱搴︼紝涓嶈�冭檻鍑犱綍鐗瑰緛锛屽洜姝ゆ瀬澶у湴鎻愰珮浜嗛拡鍙舵爲鏈ㄧ殑鏋濆彾鍒嗙绮惧害銆傚悓鏃讹紝璇ユ柟娉曞涓嶅悓鏍戠銆佷笉鍚屽瘑搴︾偣浜戞灊鍙跺垎绂绘晥鏋滃潎杈冨ソ锛岄瞾妫掓�у己銆傜簿纭殑鏍戞湪鐐逛簯鏋濆彾鍒嗙瀵规.鏋楄祫婧愮鐞嗗拰鐢熺墿澶氭牱鎬х爺绌剁瓑鍏锋湁閲嶈鎰忎箟銆�

鍏抽敭璇�: 鍦板熀婵�鍏夐浄杈�, 鏋濆彾鍒嗙, 缃戠粶鍥�, LeWos妯″瀷, 璺緞杩借釜妫�娴嬬畻娉�

Abstract:

The leaf and wood separation of the terrestrial laser scanning tree point cloud data is an important prerequisite for the accurate estimation of above-ground biomass and leaf area index锛� and it is also an important step for three-dimensional modeling of a tree. However锛� complex trees in mountain areas have large crowns and complex structures锛� resulting in mutual occlusion between leaves and branches. Therefore锛� it is difficult to obtain high-quality point cloud data. At present锛� it is still difficult for complex trees to separate leaf and wood components. High-resolution point clouds were acquired with Faro Focus3D X330. This paper proposes a method for leaf and wood separation of tree point cloud based on network graph. First锛� the LeWos model is used to perform preliminary leaf and wood separation on the point cloud锛� and separate the wood and leaf point cloud. On this basis锛� the path retrace detection algorithm is used to finely separate the leaf and wood for the mixed point clouds. As the retrace steps increases from 10 to 100锛� the wood points continue to increase锛� the leaf points continue to decrease锛� the accuracy锛� wood F-score decreases锛� leaf F-score and the Kappa coefficient first increases and then decreases. By comparing with LeWos model锛� Tlseparation model and Gaussian mixture model锛� it is found that the research method in this paper has the better precision锛� with an accuracy of 91.97%. Moreover锛� the wood F-score and leaf F-score of the proposal method are both greater than 85%锛� which means that the proposal method has a good balance when classifying wood and leaf. The proposal method only uses the retrace steps and does not consider the geometric characteristics锛� so the accuracy of branch and leaf separation of coniferous trees is greatly improved. At the same time锛� the method in this paper has a good effect on the separation of wood and leaf components of point clouds with different densities and different species. Therefore锛� the method in this paper is more robust. Accurate wood and leaf separation of tree point clouds is of great significance to forest resource management and biodiversity research.

Key words: Terrestrial laser scanning, Leaf and wood separation, Network graph, LeWos model, Path trace detection algorithm

涓浘鍒嗙被鍙�: