浏览全部资源
扫码关注微信
1.昆明理工大学 国土资源工程学院
2.云南省高校高原山区空间信息测绘技术应用工程研究中心,云南 昆明 650093
韩颖(1998-),女,昆明理工大学国土资源工程学院硕士研究生,研究方向为资源环境遥感
吕杰(1984-),女,博士,昆明理工大学国土资源工程学院讲师、硕士生导师,研究方向为资源环境遥感
赵昌福(1998-),男,昆明理工大学国土资源工程学院硕士研究生,研究方向为资源环境遥感。
收稿:2025-03-11,
纸质出版:2026-04-15
移动端阅览
韩颖,吕杰,赵昌福.基于Sentinel-2多时序多特征信息的茶园提取研究[J].软件导刊,2026,25(04):12-19.
HAN Ying,LYU Jie,ZHAO Changfu.Tea Garden Extraction Study Based on Sentinel-2 Multi-Temporal Multi-Feature Information[J].Software Guide,2026,25(04):12-19.
韩颖,吕杰,赵昌福.基于Sentinel-2多时序多特征信息的茶园提取研究[J].软件导刊,2026,25(04):12-19. DOI: 10.11907/rjdk.251044.
HAN Ying,LYU Jie,ZHAO Changfu.Tea Garden Extraction Study Based on Sentinel-2 Multi-Temporal Multi-Feature Information[J].Software Guide,2026,25(04):12-19. DOI: 10.11907/rjdk.251044.
茶叶作为具有高附加值的经济作物,成为西南山区乡村振兴的重要支柱之一。因此,准确、快速地获取茶园的空间分布对政府监管和茶叶产业的规划发展至关重要。以云南省普洱市思茅区为研究区域,综合利用2020—2022年的8期Sentinel-2影像数据,分析茶园及其他地类在不同时间段内的物候、光谱、纹理特征变化,运用Relief-F算法对特征进行排序,确定5个植被指数特征和3个纹理特征,建立8种不同的茶园分类方案,并通过支持向量机(SVM)和随机森林(RF)对方案进行精度评价。结果显示,RF分类模型的精度更高,总体精度为94.22%,Kappa系数为0.89,相比SVM分类模型在总体精度上提高了2.06%,Kappa系数提高了0.03。因此,在Sentinel-2多光谱影像数据中,结合多时序多特征信息可以大幅提高茶园的识别精度。
As one of the important pillars of rural revitalization in the mountainous areas of southwest China, tea has attracted much attention because of its characteristics of high value-added cash crops, so accurate and rapid access to the spatial distribution of tea plantations is crucial for government supervision and the planning and development of the tea industry. This paper took Simao District, Pu'er City, Yunnan Province as the research area, comprehensively used 8 Sentinel-2 image data from 2020 to 2022, analyzed the changes of phenology, spectrum and texture characteristics of tea gardens and other land types in different time periods, used the Relief-F algorithm to sort the features, determined 5 vegetation index features and 3 texture features, and established 8 different classification schemes for tea gardens. The accuracy of the scheme was evaluated by SVM and RF. The results showed that the RF classification model had better classification accuracy, with an overall accuracy of 94.22% and a Kappa coefficient of 0.89, which was 2.06% higher than that of the SVM classification model, and the Kappa coefficient was increased by 0.03. Therefore, integrating multi-temporal and multi-feature information in Sentinel-2 multispectral imagery data can significantly enhance the accuracy of tea plantation identification.
XU J Q , QIU X F , ZENG Y , et al . Analysis of climate change characteristics of spring frost damage of tea in Zhejiang [J]. Jiangsu Agricultural Science , 2018 , 46 ( 22 ): 101 - 105 . doi: 10.15889/j.issn.1002-1302.2018.22.022 http://dx.doi.org/10.15889/j.issn.1002-1302.2018.22.022
徐金勤 , 邱新法 , 曾燕 , 等 . 浙江茶叶春霜冻害的气候变化特征分析 [J]. 江苏农业科学 , 2018 , 46 ( 22 ): 101 - 105 . doi: 10.15889/j.issn.1002-1302.2018.22.022 http://dx.doi.org/10.15889/j.issn.1002-1302.2018.22.022
REN F L , WANG W L , YANG G Q . The major problem facing the development of Anji white tea industry and its countermeasures [J]. Journal of Huzhou University , 2015 , 37 ( 9 ): 10 - 13,64 . doi: 10.3969/j.issn.1009-1734.2015.09.002 http://dx.doi.org/10.3969/j.issn.1009-1734.2015.09.002
任富丽 , 王文龙 , 杨国庆 . 安吉白茶产业发展面临的主要问题及其对策 [J]. 湖州师范学院学报 , 2015 , 37 ( 9 ): 10 - 13,64 . doi: 10.3969/j.issn.1009-1734.2015.09.002 http://dx.doi.org/10.3969/j.issn.1009-1734.2015.09.002
DUNCAN J M A , SAIKIA S D , GUPTA N , et al . Observing climate impacts on tea yield in Assam, India [J]. Applied Geography , 2016 , 77 : 64 - 71 . doi: 10.1016/j.apgeog.2016.10.004 http://dx.doi.org/10.1016/j.apgeog.2016.10.004
RAJAPAKSE R , TRIPATHI N K , HONDA K . Spectral characterization and LAI modelling for the tea canopy [J]. International Journal of Remote Sensing , 2002 , 23 ( 18 ): 3569 - 3577 . doi: 10.1080/01431160110114583 http://dx.doi.org/10.1080/01431160110114583
ZHANG D J , PAN Y Z , ZHANG J S , et al . A generalized approach based on convolutional neural networks for large area cropland mapping at very high resolution [J]. Remote Sensing of Environment , 2020 , 247 : 111912 . doi: 10.1016/j.rse.2020.111912 http://dx.doi.org/10.1016/j.rse.2020.111912
TONG X Y , XIA G S , LU Q K , et al . Land-cover classification with high-resolution remote sensing images using transferable deep models [J]. Remote Sensing of Environment , 2020 , 237 : 111322 . doi: 10.1016/j.rse.2019.111322 http://dx.doi.org/10.1016/j.rse.2019.111322
BRUZZONE L , CARLIN L . A multilevel context-based system for classification of very high spatial resolution images [J]. IEEE Transactions on Geoscience and Remote Sensing , 2006 , 44 ( 9 ): 2587 - 2600 .
YANG Y K , CHEN Y Z , WU B , et al . Tea garden extraction based on high resolution image 2 and texture information [J]. Jiangsu Agricultural Science , 2019 , 47 ( 2 ): 210 - 214 . doi: 10.15889/j.issn.1002-1302.2019.02.053 http://dx.doi.org/10.15889/j.issn.1002-1302.2019.02.053
杨艳魁 , 陈芸芝 , 吴波 , 等 . 基于高分二号影像结合纹理信息的茶园提取 [J]. 江苏农业科学 , 2019 , 47 ( 2 ): 210 - 214 . doi: 10.15889/j.issn.1002-1302.2019.02.053 http://dx.doi.org/10.15889/j.issn.1002-1302.2019.02.053
PAN J H , SU N N , LIAO X L , et al . A comparative study on the extraction of tea plantation in mountainous areas of northern Fujian based on the GF2 satellite remote sensing [J]. Modern Computer , 2021 , 27 ( 33 ): 77 - 81,86 . doi: 10.3969/j.issn.1007-1423.2021.33.014 http://dx.doi.org/10.3969/j.issn.1007-1423.2021.33.014
潘俊虹 , 苏宁宁 , 廖晓莉 , 等 . 基于GF2号卫星遥感的闽北山区茶园提取对比研究 [J]. 现代计算机 , 2021 , 27 ( 33 ): 77 - 81,86 . doi: 10.3969/j.issn.1007-1423.2021.33.014 http://dx.doi.org/10.3969/j.issn.1007-1423.2021.33.014
XU W Y , SUN R , JIN Z F . Extracting tea plantations based on ZY-3 satellite data [J]. Transactions of the Chinese Society of Agricultural Engineering , 2016 , 32 ( S1 ): 161 - 168 . doi: 10.11975/j.issn.1002-6819.2016.z1.023 http://dx.doi.org/10.11975/j.issn.1002-6819.2016.z1.023
徐伟燕 , 孙睿 , 金志凤 . 基于资源三号卫星影像的茶树种植区提取 [J]. 农业工程学报 , 2016 , 32 ( S1 ): 161 - 168 . doi: 10.11975/j.issn.1002-6819.2016.z1.023 http://dx.doi.org/10.11975/j.issn.1002-6819.2016.z1.023
MA C , YANG F , WANG X C . Extracting tea plantations in southern hilly and mountainous region based on mesoscale spectrum and temporal phenological festures [J]. Remote Sensing for Land and Resources , 2019 , 31 ( 1 ): 141 - 148 . doi: 10.6046/gtzyyg.2019.01.19 http://dx.doi.org/10.6046/gtzyyg.2019.01.19
马超 , 杨飞 , 王学成 . 基于中尺度光谱和时序物候特征提取南方丘陵山区茶园 [J]. 国土资源遥感 , 2019 , 31 ( 1 ): 141 - 148 . doi: 10.6046/gtzyyg.2019.01.19 http://dx.doi.org/10.6046/gtzyyg.2019.01.19
CHEN P P , REN Y M , ZHAO C J , et al . Research on the classification of Yingde tea plantations based on time series Sentinel-2 images [J]. Spectroscopy and Spectral Analysis , 2024 , 44 ( 4 ): 1136 - 1143 . doi: 10.3964/j.issn.1000-0593(2024)04-1136-08 http://dx.doi.org/10.3964/j.issn.1000-0593(2024)04-1136-08
陈盼盼 , 任艳敏 , 赵春江 , 等 . 基于Sentinel-2时序数据的广东省英德市茶园分类研究 [J]. 光谱学与光谱分析 , 2024 , 44 ( 4 ): 1136 - 1143 . doi: 10.3964/j.issn.1000-0593(2024)04-1136-08 http://dx.doi.org/10.3964/j.issn.1000-0593(2024)04-1136-08
WANG B , HE B H , LIN N , et al . Tea plantation remote sensing extraction based on random forest feature selection [J]. Journal of Jilin University(Engineering and Technology Edition) , 2022 , 52 ( 7 ): 1719 - 1732 .
王斌 , 何丙辉 , 林娜 , 等 . 基于随机森林特征选择的茶园遥感提取 [J]. 吉林大学学报(工学版) , 2022 , 52 ( 7 ): 1719 - 1732 .
ZHAO X Q , WANG P , JING L H , et al . The application of spectral characteristics of time series Sentinel-2A images in tea land extraction [J]. Science of Surveying and Mapping , 2020 , 45 ( 6 ): 80 - 88 . doi: 10.16251/j.cnki.1009-2307.2020.06.012 http://dx.doi.org/10.16251/j.cnki.1009-2307.2020.06.012
赵晓晴 , 王萍 , 荆林海 , 等 . 时序Sentinel-2A影像光谱特征的茶园提取应用 [J]. 测绘科学 , 2020 , 45 ( 6 ): 80 - 88 . doi: 10.16251/j.cnki.1009-2307.2020.06.012 http://dx.doi.org/10.16251/j.cnki.1009-2307.2020.06.012
BO H , MA F L , JIAO L C . Analysis of the calculation problem of grayscale symbiotic matrix of image texture [J]. Acta Electronica Sinica , 2006 ( 1 ): 155 - 158,134 . doi: 10.3321/j.issn:0372-2112.2006.01.032 http://dx.doi.org/10.3321/j.issn:0372-2112.2006.01.032
薄华 , 马缚龙 , 焦李成 . 图像纹理的灰度共生矩阵计算问题的分析 [J]. 电子学报 , 2006 ( 1 ): 155 - 158,134 . doi: 10.3321/j.issn:0372-2112.2006.01.032 http://dx.doi.org/10.3321/j.issn:0372-2112.2006.01.032
ZHANG X , WEI H K . Improved algorithms of rotation invariance based on GLCM [J]. Industrial Control Computer , 2016 , 29 ( 6 ): 115 - 117 .
张鑫 , 魏海坤 . 基于灰度共生矩阵的旋转不变性改进算法 [J]. 工业控制计算机 , 2016 , 29 ( 6 ): 115 - 117 .
LUO J C , ZHOU C H , LIANG Y , et al . Support vector machines for spatial feature extraction and classification of remotely sensed imagery [J]. Journal of Remote Sensing , 2002 ( 1 ): 50 - 55 . doi: 10.1007/s11769-002-0073-1 http://dx.doi.org/10.1007/s11769-002-0073-1
骆剑承 , 周成虎 , 梁怡 , 等 . 支撑向量机及其遥感影像空间特征提取和分类的应用研究 [J]. 遥感学报 , 2002 ( 1 ): 50 - 55 . doi: 10.1007/s11769-002-0073-1 http://dx.doi.org/10.1007/s11769-002-0073-1
ZHANG R , MA J W . State of the art on remotely sensed data classification based on support vector machines [J]. Advances in Earth Science , 2009 , 24 ( 5 ): 555 - 562 . doi: 10.11867/J.ISSN.1001-8166.2009.05.0555 http://dx.doi.org/10.11867/J.ISSN.1001-8166.2009.05.0555
张睿 , 马建文 . 支持向量机在遥感数据分类中的应用新进展 [J]. 地球科学进展 , 2009 , 24 ( 5 ): 555 - 562 . doi: 10.11867/J.ISSN.1001-8166.2009.05.0555 http://dx.doi.org/10.11867/J.ISSN.1001-8166.2009.05.0555
JIANG Y Q . Research on the identification of tea plantations based on multi-source remote sensing data and its recognition accuracy scale effect [D]. Kunming : Yunnan Normal University , 2021 .
蒋永泉 . 基于多源遥感数据茶园识别及其识别精度尺度效应研究 [D]. 昆明 : 云南师范大学 , 2021 .
QIAN R , XU W H . RF and SVM classification algorithms of tea plantations extraction based on GEE platform [J]. Forest Inventory and Planning , 2023 , 48 ( 1 ): 1 - 6 .
钱瑞 , 徐伟恒 . 基于GEE平台结合RF和SVM算法的茶园提取研究 [J]. 林业调查规划 , 2023 , 48 ( 1 ): 1 - 6 .
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
鄂公网安备42010602004949号