林业科学研究
林業科學研究
임업과학연구
FOREST RESEARCH
2010年
1期
53-58
,共6页
李春干%代华兵%谭必增%何柏华
李春榦%代華兵%譚必增%何柏華
리춘간%대화병%담필증%하백화
图像分割%SPOT5图像%小班边界%自动提取
圖像分割%SPOT5圖像%小班邊界%自動提取
도상분할%SPOT5도상%소반변계%자동제취
imagery segmentation%SPOT5 imagery%sub-compartment boundary%auto-delineation
以SPPT5图像为研究对象,试验了4种图像分割方案,采用基于最终测量精度准则的多指标评价和基于欧氏距离的相似度综合评价两种方法,对分割效果进行评价,其中多指标包括圆度(RO)、紧致度(CO)、形状指数(SI)、最小包络椭圆短半径(RE)、椭圆度(EF)、形状因子(P2A)、面积相对误差(RA)、周长相对误差(RP)、中心位置绝对位移(DC)9个指标,相似度采用而积(A)、周长(P)、RO、CO、SI、RE、EF、P2A等8个因子计算.结果表明,原始图像直接用于分割的效果远好于经直方图均衡化后的图像.在图像分割过程中,输入图层的权重很大程度上影响分割效果,根据各输入图层标准差设置权重的分割效果,略好于根据图层信息量设置权重的分割效果.采用图像分割的方法自动提取小班边界,经适当后处理后编制工作手图用于森林资源规划设计调查,不但大量节省野外小班勾绘工作时间、降低劳动强度、提高工作效率,而且大幅度地提高了小班勾绘的准确性,确保面积调查精度.
以SPPT5圖像為研究對象,試驗瞭4種圖像分割方案,採用基于最終測量精度準則的多指標評價和基于歐氏距離的相似度綜閤評價兩種方法,對分割效果進行評價,其中多指標包括圓度(RO)、緊緻度(CO)、形狀指數(SI)、最小包絡橢圓短半徑(RE)、橢圓度(EF)、形狀因子(P2A)、麵積相對誤差(RA)、週長相對誤差(RP)、中心位置絕對位移(DC)9箇指標,相似度採用而積(A)、週長(P)、RO、CO、SI、RE、EF、P2A等8箇因子計算.結果錶明,原始圖像直接用于分割的效果遠好于經直方圖均衡化後的圖像.在圖像分割過程中,輸入圖層的權重很大程度上影響分割效果,根據各輸入圖層標準差設置權重的分割效果,略好于根據圖層信息量設置權重的分割效果.採用圖像分割的方法自動提取小班邊界,經適噹後處理後編製工作手圖用于森林資源規劃設計調查,不但大量節省野外小班勾繪工作時間、降低勞動彊度、提高工作效率,而且大幅度地提高瞭小班勾繪的準確性,確保麵積調查精度.
이SPPT5도상위연구대상,시험료4충도상분할방안,채용기우최종측량정도준칙적다지표평개화기우구씨거리적상사도종합평개량충방법,대분할효과진행평개,기중다지표포괄원도(RO)、긴치도(CO)、형상지수(SI)、최소포락타원단반경(RE)、타원도(EF)、형상인자(P2A)、면적상대오차(RA)、주장상대오차(RP)、중심위치절대위이(DC)9개지표,상사도채용이적(A)、주장(P)、RO、CO、SI、RE、EF、P2A등8개인자계산.결과표명,원시도상직접용우분할적효과원호우경직방도균형화후적도상.재도상분할과정중,수입도층적권중흔대정도상영향분할효과,근거각수입도층표준차설치권중적분할효과,략호우근거도층신식량설치권중적분할효과.채용도상분할적방법자동제취소반변계,경괄당후처리후편제공작수도용우삼림자원규화설계조사,불단대량절성야외소반구회공작시간、강저노동강도、제고공작효솔,이차대폭도지제고료소반구회적준학성,학보면적조사정도.
The present implement of remote sensing in practical forest inventory don't take advantage of imagery processing and analysis technology of remote sensing,and is inefficient.Aimed to the auto-delineation of the boundary of forest sub-compartment for actual application,an imagery segmentation method was studied.SPOT5 imagery was segmented by four protocols,evaluation with nine features separately based on ultimate measurement accuracy,and synthetical evaluation of similarity based on Euclidean distance(ED)were used to evaluate the segmentation,here the features were roundness(RO),compactness(CO),shape index(SI),radius of smallest enclosing ellipse(RE),elliptic fit(EF)and form factor(P2A),relative error of area(RA),relative error of perimeter(RP)and displacement of the center of polygon(DC),while area(A),perimeter(P),RO,CO,SI,RE,EF,P2A were used to calculating ED.The result indicated that segmentation on raw imagery was better than that on histogram equalization imagery,the weights of input layers would affect the output of segmentation,and it would get better result by segmentation with the weight based on the standard deviation than that based on the information content of input imagery layers.It is feasible that preparing draft map for forest resources inventory through boundary auto-delineation based on imagery segmentation,for it is not only efficient and low labor intensity,but also improve the division precision of boundary and area accuracy of forest sub-compartment.