新疆师范大学地理科学与旅游学院 / 新疆干旱区湖泊环境与资源实验室,新疆 乌鲁木齐 830054
李坤玉(1999年生),女;研究方向:资源环境遥感;E-mail:kunyu_li@163.com
王雪梅(1976年生),女;研究方向:干旱区资源环境遥感技术应用;E-mail:wangxm_1225@sina.com
纸质出版日期:2024-01-25,
网络出版日期:2023-10-31,
收稿日期:2023-05-19,
录用日期:2023-05-30
扫 描 看 全 文
李坤玉,王雪梅,李锐等.融入辅助数据集的面向对象土地利用分类研究[J].中山大学学报(自然科学版)(中英文),2024,63(01):34-44.
LI Kunyu,WANG Xuemei,LI Rui,et al.The object-oriented land use classification incorporating auxiliary data sets[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2024,63(01):34-44.
李坤玉,王雪梅,李锐等.融入辅助数据集的面向对象土地利用分类研究[J].中山大学学报(自然科学版)(中英文),2024,63(01):34-44. DOI: 10.13471/j.cnki.acta.snus.2023D031.
LI Kunyu,WANG Xuemei,LI Rui,et al.The object-oriented land use classification incorporating auxiliary data sets[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2024,63(01):34-44. DOI: 10.13471/j.cnki.acta.snus.2023D031.
土地利用分类结果对国土空间的管理至关重要。为提高土地利用分类结果的准确性,本文以博湖县为研究区,使用Sentinel-2A影像提取光谱特征,并结合雷达、光谱指数、土壤和地形特征构建6个面向对象的土地利用分类模型,使用简单非迭代聚类(SNIC)算法和随机森林(RF)算法对影像进行分割和分类,得出模型的分类精度以及特征重要性排序,最后使用分类回归树(CART)算法验证辅助数据集对提高分类精度的影响。结果表明:使用SNIC算法分割影像时,分别设置种子大小为17、紧凑度为0时,该研究区影像分割效果最好。基于RF分类算法,在只使用光谱信息进行分类时分类精度最低,加入雷达、光谱指数、土壤和地形特征中任何一个辅助数据集均可提高土地利用的分类精度,其中地形特征对提高分类精度的效果更显著,加入所有辅助数据集时分类精度达到最高,OA=92.34%,Kappa系数=0.91。使用CART算法进行分类有效性验证得出,基于RF算法的分类效果优于CART算法。基于遥感云平台的SNIC分割算法,融入辅助数据集进行面向对象分类,为提高土地利用分类精度提供参考。
Land use classification is critical to the management of land space. To improve the accuracy of land use classification
this study takes Bohu County as the research area
uses Sentinel-2A images to extract spectral features
and combines radar
spectral index
soil
and terrain features to construct six object-oriented land use classification models. We then use a simple non-iterative clustering algorithm and random forest algorithm to segment and classify the images and obtain the classification accuracy and feature importance ranking of the model. In the final step
we use the classification regression tree algorithm to verify the influence of the auxiliary dataset on the improvement of the classification accuracy. The results show that when using the SNIC algorithm to segment the images
with seed size 17 and compactness 0
the image segmentation effect in this study area is the best. The classification accuracy is the lowest when only spectral information is used
and adding any auxiliary dataset of radar
spectral index
soil
and terrain features can improve the classification accuracy of land use. Among those auxiliary datasets
the effect of terrain features on improving classification accuracy is more significant
and the classification accuracy reaches the highest when all auxiliary datasets are added
with OA=92.34% and Kappa coefficient=0.91. The classification validity is verified using the categorical regression tree algorithm
it shows that the classification effect based on the random forest algorithm is better than that of the categorical regression tree algorithm. The SNIC segmentation algorithm based on the remote sensing cloud platform is integrated into an auxiliary data set for object-oriented classification
which provide a reference for improving the accuracy of land use classification.
土地利用分类辅助数据集SNIC分割面向对象随机森林Sentinel-2A影像
land use classificationauxiliary datasetsSNIC segmentationobject-orientedrandom forestsentinel-2A image
陈媛媛,雷鸣,王泽远,等,2022.基于Sentinel卫星影像的土地利用类型提取——以丽水市莲都区为例[J].森林工程,38(2):54-61.
胡云锋,商令杰,王召海,等,2018.GEE平台和CART方法的北京市土地解译[J].测绘科学,43(4):87-93.
何炳伟,赵伟,李爱农,等,2017.基于Landsat 8遥感影像的新旧城区热环境特征对比研究—以成都市为例[J].遥感技术与应用,32(6):1141-1150.
匡开新,杨英宝,高永年,等,2023.协同Sentinel合成孔径雷达和光学影像多特征的不透水面随机森林提取方法[J].遥感技术与应用,38(2):422-431.
李恒凯,王利娟,肖松松,等,2021.基于多源数据的南方丘陵山地土地利用随机森林分类[J].农业工程学报,37(7):244-251.
刘通,任鸿瑞,2022.GEE平台下利用物候特征进行面向对象的水稻种植分布提取[J].农业工程学报,38(12):189-196.
刘睿,王志勇,高瑞,2021.时序SAR影像的干旱地区土地利用分类应用[J].测绘科学,46(10):90-97.
毛丽君,李明诗,2023.GEE环境下联合Sentinel主被动遥感数据的国家公园土地覆盖分类[J].武汉大学学报(信息科学版),48(5):756-764.
潘磊,孙玉军,王轶夫,等,2020.基于Sentinel-1和Sentinel-2数据的杉木林地上生物量估算[J].南京林业大学学报(自然科学版),44(3):149-156.
舒弥,杜世宏,2022.国土调查遥感40年进展与挑战[J].地球信息科学学报,24(4):597-616.
吴静波,2018. 盐碱地信息提取和变化检测方法应用与比较[D].银川:宁夏大学.
吴静波,汪西原,2018.宁夏石嘴山地区盐碱地变化的目标级检测[J].陕西师范大学学报(自然科学版),46(2):104-109.
岳巍,李世明,李增元,等,2022.基于多时相Sentinel-2影像和SNIC分割算法的优势树种识别[J].林业科学,58(9):60-69.
张来红,秦婷婷,泽仁卓格,等,2023.基于GEE和多维特征集的锡林浩特露天矿区近30a土地利用分类[J].金属矿山,(3):234-241.
朱永森,曾永年,张猛,2017.基于HJ卫星数据与面向对象分类的土地利用/覆盖信息提取[J].农业工程学报,33(14):258-265.
ACHANTA R, SUSSTRUNK S,2017.Superpixels and polygons using simple non-iterative clustering[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Honolulu:4651-4660.
BREIMAN L,2001. Random forests[J]. Mach Learn,45(1):5-32.
DJERRIRI K, SAFIA A, ADJOUDJ R,2020. Object-based classification of sentinel-2 imagery using compact texture unit descriptors through google earth engine[C]//2020 Mediterranean and Middle-East geoscience and remote sensing symposium (M2GARSS). Tunisia:105-108.
FRANKLIN S E,2018. Pixel- and object-based multispectral classification of forest tree species from small unmanned aerial vehicles[J]. J Unmanned Veh Sys,6(8):195-211.
HURSKAINEN P, ADHIKARI H, SILJANDER M, et al,2019. Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes[J].Remote Sens Environ,233: 111354.
OUMA Y, NKWAE B, MOALAFHI D, et al, 2022. Comparison of machine learning classifiers for multitemporal and multisensor mapping of urban lulc features[J]. Int Arch Photogramm Remote Sens Spatial Inf Sci, 43(B3):681-689.
PAREETH S, KARIMI P, SHAFIEI M, et al,2019. Mapping agricultural landuse patterns from time series of Landsat 8 using random forest based hierarchial approach.[J]. Remote Sens,11(5): 601.
PHIRI D, MORGENROTH J,2017. Developments in Landsat land cover classification methods:A review[J]. Remote Sens,9(9):967.
QU L, CHEN Z, LI M, et al, 2021. Accuracy improvements to pixel-based and object-based LULC classification with auxiliary datasets from Google Earth engine[J]. Remote Sens, 13(3): 453.
TASSI A,VIZZARI M,2020. Object-oriented LULC classification in google earth engine combining SNIC, GLCM, and machine learning algorithms[J]. Remote Sens,12(22): 3776.
TOMÁŠ K, DAVID M, JAN K, et al, 2018. Selecting appropriate variables for detecting grassland to cropland changes using high resolution satellite data[J]. Peer J,6: e5487.
0
浏览量
8
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构