Satisfactory image segmentation results can improve the accuracy of tree species classification, and the segmentation effect depends on the selection of the optimal scale parameter (OSP). Previous studies have relied on manually set scale sequences, resulting in subjectivity. To avoid this issue, this study used GF-2 images as the data source and proposed an unsupervised selection method of OSP based on effective scale intervals to determine at which scale the optimal segmentation results for different forest types occur. Multi-resolution segmentation (MRS) algorithm was used to segment images, and constructing effective scale interval estimation functions (ESF) and combining with the overall goodness F-measure (OGF), the OSPs of different forest types at different scale intervals were obtained. Finally, the optimal segmentation results were determined by supervised segmentation accuracy analysis combined with Google map visual interpretation. The results showed that the OSPs obtained from the effective scale interval Ⅲ achieved the best segmentation results for each forest type, with the lowest and highest F-measure of 0.7311 and 0.8733, respectively. Meanwhile, in the segmentation task of tree species classification based on GF-2 image, OSP was related to tree species and forest types. This paper provided technical support for object extraction of object-based tree species classification based on high-resolution remote sensing images and also provided a methodological reference for the selection of scale parameters for images composed of different geographical objects.
MAH W, LIUH, YAOS B,et al.Analysis and prospect on the application of tree species classification based on forestry remote sensing[J].Forest Resources Management,2020(3):118-121.
SONGY Q, WEIX Y, ZHENGP B,et al.Spatial pattern analysis of forest ecosystem service value based on forest stand scale:A case from Weixi Lisu Autonomous County[J].Journal of West China Forestry Science,2023,52(6):80-86,93.
WANGB Y, ZHOUS Y, XUY Y,et al.Ten years of Gaofen-series satellite imagery in forestry:applications and trends[J].Journal of Hunan Ecological Science,2023,10(4):110-119.
[7]
BLASCHKET, HAYG J, KELLYM,et al.Geographic object-based image analysis-towards a new paradigm[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,87(100):180-191.
ZHANGY F, WANGZ H, WANGB,et al.Spatiotemporal variations of carbon storage in the natural forest protection project regions of the Greater Khingan Mountains based on InVEST model[J].Journal of West China Forestry Science,2024,53(1):108-118.
HONGL, FENGY F, PENGS Y,et al.Classification of high spatial resolution remote sensing imagery based on object-oriented multi-scale weighted sparse representation[J].Acta Geodaetica et Cartographica Sinica,2022,51(2):224-237.
SHIQ L, HUANGS M, ZHANGM X,et al.Automatic extraction method of pine woods nematode infected wood based on unmanned aerial vehicle remote sensing and deep learning[J].Journal of West China Forestry Science,2022,51(5):28-33.
[14]
BAATZM, SCHÄPEA.Multiresolution segmentation-an optimization approach for high quality multi-scale image segmentation[J].Angewandte Geographische Information Sverarbeitung,2000(12):12-23.
[15]
JOHNSONB A, BRAGAISM, ENDOI,et al.Image segmentation parameter optimization considering within- and between-segment heterogeneity at multiple scale levels:test case for mapping residential areas using Landsat imagery[J].ISPRS International Journal of Geo-Information,2015,4(4):2292-2305.
HANJ L, HANL S, MUH X,et al.Research on land desertification information extraction by object-oriented classification method[J].Science of Surveying and Mapping,2023,48(4):149-160.
YINR J, SHIR H, LIJ Y.Automatic selection of optimal segmentation scale of high-resolution remote sensing images[J].Journal of Geo-Information Science,2013,15(6):902-910.
[20]
NAJ, DINGH, ZHAOW,et al.Object-based large-scale terrain classification combined with segmentation optimization and terrain features:A case study in China[J].Transactions in GIS,2021,25(6):2939-2962.
LIUJ L, CHENZ.Research on the method of determining the optimal segmentation scale for tree species classification of high-resolution image[J].Scientia Silvae Sinicae,2019,55(11):95-104.
WANGN, MINJ, GUOJ L,et al.On the remote sensing classification of tree species based on multi-scale feature transfer learning[J].Journal of Ezhou University,2021,28(2):93-97.
[25]
廖娟.多尺度多维特征的高分辨率遥感影像变化检测方法研究[D].西安:长安大学,2022.
[26]
LIAOJ.Research on the change detection method of high-resolution remote sensing image with multi-scale and multi-dimensional features[D].Xi’an:Chang’an University,2022.
CHENC L, WUG.Evaluation of optimal segmentation scale with object-oriented method in remote sensing[J].Remote Sensing Technology and Application,2011,26(1):96-102.
[29]
WANGY J, QIQ W, LIUY,et al.Unsupervised segmentation parameter selection using the local spatial statistics for remote sensing image segmentation[J].International Journal of Applied Earth Observation and Geoinformation,2019,81:98-109.
[30]
HUZ W, ZHANGQ, ZOUQ,et al.Stepwise evolution analysis of the region-merging segmentation for scale parameterization[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(7):2461-2472.
[31]
HUZ W, SHIT Z, WANGC S,et al.Scale-sets image classification with hierarchical sample enriching and automatic scale selection[J].International Journal of Applied Earth Observation and Geoinformation,2021,105:102605.
[32]
王锋军.基于自适应邻域尺度的高分辨率遥感影像变化检测方法研究[D].西安:西安理工大学,2024.
[33]
WANGF J.Research on change detection methods based on adaptation neighborhood scale using high resolution remote sensing images[D].Xi′an:Xi′an University of Technology,2024.
[34]
莫寒翔.PolSAR面向对象分类中同质区分割研究[D].大连:大连海事大学,2016.
[35]
MOH X.The PolSAR object-oriented classification of homogenous area segmentation research[D].Dalian:Dalian Maritime University,2016.
[36]
ANSELINL.Local indicators of spatial association-LISA[J].Geographical Analysis,1995,27(2):93-115.
[37]
ZHANGX, FENGX, XIAOP,et al.Segmentation quality evaluation using region-based precision and recall measures for remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2015,102:73-84.
[38]
刘金丽.基于高分二号遥感数据的树种精细分类技术研究[D].北京:北京林业大学,2019.
[39]
LIUJ L.Research on fine classification technology of tree species based on GF-2 remote sensing data[D].Beijing:Beijing Forestry University,2019.
MAOX G, CHENW Q, WEIJ Y,et al.Effect and evaluation of segmentation scale on object-based forest species classification[J].Scientia Silvae Sinicae,2017,53(12):73-83.