基于多尺度标记优化分水岭方法的油茶冠幅提取

doi:10.13287/j.1001-9332.202107.010

应用生态学报 ›› 2021, Vol. 32 ›› Issue (7): 2449-2457.doi: 10.13287/j.1001-9332.202107.010

基于多尺度标记优化分水岭方法的油茶冠幅提取

吴炅^1,2,3, 彭邵锋⁴, 蒋馥根^1,2,3, 唐杰^1,2,3, 孙华^1,2,3*

¹中南林业科技大学林业遥感信息工程研究中心, 长沙 410004;
²林业遥感大数据与生态安全湖南省重点实验室, 长沙 410004;
³南方森林资源经营与监测国家林业与草原局重点实验室, 长沙 410004;
⁴湖南省林业科学院, 长沙 410004

收稿日期:2020-12-24 修回日期:2021-04-02 出版日期:2021-07-15 发布日期:2022-01-15
通讯作者: *sunhua@csuft.edu.cn
作者简介:吴炅,女,1998年生,硕士研究生。主要从事林业遥感和地理信息系统研究。E-mail:972082061@qq.com
基金资助:
湖南省林业科技创新专项(XLK201986)、国家重点研发计划项目(2016YFD0702105)和湖南省普通高校青年骨干教师培养对象项目(7070220190001)

Extraction of Camellia oleifera crown width based on the method of optimized watershed with multi-scale markers

WU Jiong^1,2,3, PENG Shao-feng⁴, JIANG Fu-gen^1,2,3, TANG Jie^1,2,3, SUN Hua^1,2,3*

¹Research Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, China;
²Key Laboratory of Forestry Remote Sensing Based Big Data & Ecological Security for Hunan Province, Changsha 410004, China;
³Key Laboratory of State Forestry & Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, China;
⁴Hunan Academy of Forestry, Changsha 410004, China

Received:2020-12-24 Revised:2021-04-02 Online:2021-07-15 Published:2022-01-15
Contact: *sunhua@csuft.edu.cn
Supported by:
Scientific Research Fund of Forestry Administration of Hunan Province (XLK201986),the National Key R&D Program (2016YFD0702105),and the Training Fund of Young Professors from Hunan Provincial Education Department(7070220190001).

摘要/Abstract

摘要： 针对尺度对地物空间结构的限制以及传统分水岭分割易产生树冠过分割等问题,选择长沙县明月村油茶基地为研究区,提出一种基于多尺度标记优化分水岭分割油茶树冠的方法。首先使用高分辨率无人机影像采集图像,分析影像特征,构建油茶分类体系,提取油茶林分布区域。其次,运用多尺度区域迭代增长方法提取树冠标记,将标记应用于多阈值尺度的分水岭变换,并结合Johnson指数选取树冠标记增长和分水岭阈值的最优尺度,实现油茶单木的准确识别。结果表明:多尺度标记优化分水岭方法在分离油茶单木时,树冠面积提取值与目视解译参考值的相对误差为9.4%;单木总体识别精度为89.4%,相对于传统的分水岭分割方法精度提高了34.8%;通过Johnson指数确定的最优迭代增长尺度为20,分水岭分割阈值尺度为85,对比不同尺度组合下的油茶冠幅提取结果,最优尺度下的油茶冠幅提取精度最高(R²=0.75)。多尺度标记优化分水岭方法能较准确地分离油茶树冠,将该方法应用于无人机影像树冠分割,可有效提高经济林调查的效率。

关键词: 面向对象, 最优尺度, 无人机, 油茶, 标记分水岭

Abstract: In view of the limitation of scale on the spatial structure of ground objects and the problem that traditional watershed segmentation tends to produce crown over-segmentation, we proposed a segmentation method of Camellia oleifera crown based on the optimized watershed with multi-scale markers, with the C. oleifera base in Mingyue Village of Changsha County as the research object. Firstly, the high-resolution unmanned aerial vehicle (UAV) was used to collect images. The image features were analyzed to construct the classification system of C. oleifera, and the distribution area of C. oleifera was extracted. After being extracted by multi-scale region iterative growth, the crown markers were applied to the multi-threshold scale watershed transformation. Combined with Johnson index, the optimal scale of crown marker growth and watershed threshold was used to realize the accurate identification of individual trees. The results showed that the relative error between the method of optimized watershed with multi-scale markers and the visual interpretation of the reference value of tree-crown was 9.4% for the separation of individual trees. The overall identification accuracy of each tree was 89.4%, which was 34.8% higher than that of the traditional watershed segmentation method. The optimal iterative growth scale obtained by Johnson index was 20, while the thre-shold scale of watershed segmentation was 85. Compared with the results of different scale combinations, the crown extraction accuracy under the optimal scale was the highest (R²=0.75). The method of optimized watershed with multi-scale markers could accurately separate C. oleifera crown. Applying this method to UAV image crown segmentation could effectively improve the efficiency of economic forest investigation.

Key words: object-oriented, optimal scale, unmanned aerial vehicle, Camellia oleifera, marked watershed

吴炅, 彭邵锋, 蒋馥根, 唐杰, 孙华. 基于多尺度标记优化分水岭方法的油茶冠幅提取[J]. 应用生态学报, 2021, 32(7): 2449-2457.

WU Jiong, PENG Shao-feng, JIANG Fu-gen, TANG Jie, SUN Hua. Extraction of Camellia oleifera crown width based on the method of optimized watershed with multi-scale markers[J]. Chinese Journal of Applied Ecology, 2021, 32(7): 2449-2457.

参考文献

[1] 张东生, 金青哲, 薛雅琳, 等. 油茶籽油的营养价值及掺伪鉴定研究进展. 中国油脂, 2013, 38(8): 47-50 [Zhang D-S, Jin Q-Z, Xue Y-L, et al. Nutritional value and adulteration identification of oil-tea Camellia seed oil. China Oils and Fats, 2013, 38(8): 47-50]
[2] 孙少波, 杜华强, 李平衡, 等. 基于小波变换的毛竹叶片净光合速率高光谱遥感反演. 应用生态学报, 2016, 27(1): 49-58 [Sun S-B, Du H-Q, Li P-H, et al. Retrieval of leaf net photosynthetic rate of moso bamboo forests using hyperspectral remote sensing based on wavelet transform. Chinese Journal of Applied Ecology, 2016, 27(1): 49-58]
[3] 曾霞辉, 王颖, 曾掌权, 等. 无人机影像树冠信息提取研究. 中南林业科技大学学报, 2020, 40(8): 75-82 [Zeng X-H, Wang Y, Zeng Z-Q, et al. Research on extraction of tree crown information from UAV images. Journal of Central South University of Forestry & Technology, 2020, 40(8): 75-82]
[4] Chen W, Xiang H, Moriya K. Individual tree position extraction and structural parameter retrieval based on airborne LiDAR data: Performance evaluation and comparison of four algorithms. Remote Sensing, 2020, 12: 571
[5] 汤文超. 无人机多光谱影像油菜估产方法研究. 博士论文. 武汉: 武汉大学, 2016 [Tang W-C. Remote Estimation of Yield in Oilseed Rape with Unmanned Aerial Vehicle Data. PhD Thesis. Wuhan: Wuhan University, 2016]
[6] Li C, Li M, Li Y. Improving estimation of forest aboveground biomass using Landsat 8 imagery by incorporating forest crown density as a dummy variable. Canadian Journal of Forest Research, 2020, 50: 390-398
[7] 毛学刚, 魏晶昱. 基于多源遥感数据的面向对象林分类型识别. 应用生态学报, 2017, 28(11): 3711-3719 [Mao X-G, Wei J-Y. Object-oriented stand type classification based on the combination of multi-source remote sensing data. Chinese Journal of Applied Ecology, 2017, 28(11): 3711-3719]
[8] 党涛. 基于多层次分割分类模型及其特征空间优化的高分辨率遥感影像城市建筑物提取研究. 硕士论文. 兰州: 兰州大学, 2018 [Dang T. Extraction of Buildings in Remote Sensing Imagery Based on Multi-level Segmentation and Classification Hierarchical Model and Feature Space Optimization. Master Thesis. Lan-zhou: Lanzhou University, 2018]
[9] Xiao P, Zhang X, Zhang H, et al. Multiscale optimized segmentation of urban green cover in high resolution remote sensing image. Remote Sensing, 2018, 10: 1813
[10] Li J, Feng L, Zhang X, et al. Adaptive scale selection for multiscale segmentation of satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10: 3641-3651
[11] 井然, 邓磊, 赵文吉, 等. 基于可见光植被指数的面向对象湿地水生植被提取方法. 应用生态学报, 2016, 27(5): 1427-1436 [Jing R, Deng L, Zhao W-J, et al. Object-oriented aquatic vegetation extracting approach based on visible vegetation indices. Chinese Journal of Applied Ecology, 2016, 27(5): 1427-1436]
[12] Shen Y, Chen J, Xiao L, et al. Optimizing multiscale segmentation with local spectral heterogeneity measure for high resolution remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 157: 13-25
[13] Lowe SH, Guo X. Detecting an optimal scale parameter in object-oriented classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sen-sing, 2011, 4: 890-895
[14] Wang YJ, Qi QW, Liu Y. Unsupervised segmentation evaluation using area-weighted variance and Jeffries-Matusita distance for remote sensing images. Remote Sensing, 2018, 10: 1193
[15] 张俊, 朱国龙, 李妍. 面向对象高分辨率影像信息提取中的尺度效应及最优尺度研究. 测绘科学, 2011, 36(2): 107-109 [Zhang J, Zhu G-L, Li Y. Scale effect and optimal scale in object-oriented information extraction of high spatial resolution remote sensing image. Science of Surveying and Mapping, 2011, 36(2): 107-109]
[16] 何安良, 程兴保, 廖龙长, 等. 耦合H-minima与数学形态学的分水岭遥感图像分割方法. 东华理工大学学报: 自然科学版, 2020, 43(4): 396-400 [He A-L, Cheng X-B, Liao L-C, et al. An improved watershed method for remote sensing image segmentation coupling H-minima with mathematical morphology. Journal of East China University of Technology: Natural Science, 2020, 43(4): 396-400]
[17] 高丽, 杨树元, 李海强. 一种基于标记的分水岭图像分割新算法. 中国图象图形学报, 2007, 12(6): 1025-1032 [Gao L, Yang S-Y, Li H-Q. New unsupervised image segmentation via marker-based watershed. Journal of Image and Graphics, 2007, 12(6): 1025-1032]
[18] 赵栋. 改进的分水岭变换高分辨率遥感影像分割方法研究. 硕士论文. 北京: 中国地质大学, 2016 [Zhao D. Research of High Resolution Remote Sensing Image Segmentation based on Modified Watershed. Master Thesis. Beijing: China University of Geosciences, 2016]
[19] 任守纲, 马超, 谢忠红, 等. 基于分水岭和梯度的蝴蝶兰图像分割方法. 农业工程学报, 2012, 28(9): 125-129 [Ren S-G, Ma C, Xie Z-H, et al. Image segmentation algorithm for Phalaenopsis amabilis based on watershed algorithm and gradient. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(9): 125-129]
[20] 张建华, 韩书庆, 翟治芬, 等. 改进自适应分水岭方法分割棉花叶部粘连病斑. 农业工程学报, 2018, 34(24): 165-174 [Zhang J-H, Han S-Q, Zhai Z-F, et al. Improved adaptive watershed method for segmentation of cotton leaf adhesion lesions. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(24): 165-174]
[21] 李雅男. 多尺度形态学及自适应阈值标记的分水岭分割算法研究. 硕士论文. 阜新: 辽宁工程技术大学, 2017 [Li Y-N. Research on Watershed Segmentation Algorithm with Multi-scale Morphology & Adaptive Threshold Marker. Master Thesis. Fuxin: Liaoning Technical University, 2017]
[22] 蔡利平, 史文中, 张华, 等. 边缘走向自适应的多尺度分水岭分割算法. 中国矿业大学学报, 2015, 44(4): 739-746 [Cai L-P, Shi W-Z, Zhang H, et al. An edge direction adaptive multi-scale watershed segmentation algorithm. Journal of China University of Mining & Technology, 2015, 44(4): 739-746]
[23] Johnson B, Xie ZX. Unsupervised image segmentation evaluation and refinement using a multi-scale approach. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66: 473-483
[24] Woebbecke DM, Meyer GE, Bargen KV, et al. Color indices for weed identification under various soil, residue, and lighting conditions. Transactions of the American Society of Agricultural and Biological Engineers, 1995, 38: 259-269
[25] 伍艳莲, 赵力, 姜海燕, 等. 基于改进均值漂移算法的绿色作物图像分割方法. 农业工程学报, 2014, 30(24): 161-167 [Wu Y-L, Zhao L, Jiang H-Y, et al. Image segmentation method for green crops using improved mean shift. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(24): 161-167]
[26] 王露. 面向对象的高分辨率遥感影像多尺度分割参数及分类研究. 硕士论文. 长沙: 中南大学, 2014 [Wang L. Analysing Classification and Segmentation Parameters Selection in High Resolution Remote Sensing Image based on Object. Master Thesis. Changsha: Central South University, 2014]
[27] Lian L, Chen J. Research on segmentation scale of multi-resources remote sensing data based on object-oriented. Procedia Earth and Planetary Science, 2011, 2: 352-357
[28] 黄慧萍. 面向对象影像分析中的尺度问题研究. 博士论文. 北京: 中国科学院遥感应用研究所, 2003 [Huang H-P. Scale Issues in Object-oriented Image Analysis. PhD Thesis. Beijing: Institute of Remote Sensing Applications, Chinese Academy of Sciences, 2003]
[29] Moran PAP. Notes on continuous stochastic phenomena. Biometrika, 1950, 37: 17-23
[30] 张猛, 曾永年, 朱永森. 面向对象方法的时间序列MODIS数据湿地信息提取——以洞庭湖流域为例.遥感学报, 2017, 21(3): 479-492 [Zhang M, Zeng Y-N, Zhu Y-S. Wetland mapping of Dongting Lake Basin based on time-series MODIS data and object-oriented method. Journal of Remote Sensing, 2017, 21(3): 479-492]
[31] 董新宇, 李家国, 陈瀚阅, 等. 无人机遥感影像林地单株立木信息提取. 遥感学报, 2019, 23(6): 1269-1280 [Dong X-Y, Li J-G, Chen H-Y, et al. Extraction of individual tree information based on remote sensing images from an Unmanned Aerial Vehicle. Journal of Remote Sensing, 2019, 23(6): 1269-1280]

基于多尺度标记优化分水岭方法的油茶冠幅提取

Extraction of Camellia oleifera crown width based on the method of optimized watershed with multi-scale markers

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨涛, 于颖, 杨曦光, 杜红萱. 无人机高光谱联合LiDAR估测林分与单木尺度叶绿素含量 [J]. 应用生态学报, 2023, 34(8): 2101-2112.
[2]	李睿, 孙钊, 谢运鸿, 李豪伟, 张运根, 孙玉军. 联合U-Net和分水岭算法的高郁闭度杉木纯林树冠信息提取 [J]. 应用生态学报, 2023, 34(4): 1024-1034.
[3]	王怡婧, 丁启东, 张俊华, 陈睿华, 贾科利, 李小林. 基于无人机高光谱遥感和机器学习的土壤水盐信息反演 [J]. 应用生态学报, 2023, 34(11): 3045-3052.
[4]	宜树华, 陈世苹, 李英年, 胡中民. 中国生态脆弱区联网协同观测及其在承载力研究中的应用 [J]. 应用生态学报, 2022, 33(8): 2271-2278.
[5]	王曦, 李玉环, 王瑞燕, 史丰智, 徐绍棠. 基于无人机的冬小麦拔节期表层土壤有机质含量遥感反演 [J]. 应用生态学报, 2020, 31(7): 2399-2406.
[6]	王小军, 刘光旭, 相爱存, 肖彤. 江西省油茶综合生产潜力与资源利用效率评估 [J]. 应用生态学报, 2020, 31(4): 1175-1184.
[7]	唐亮, 何明珠, 许华, 贾谱超. 基于无人机低空遥感的荒漠植被覆盖度与归一化植被指数验证及其对水热梯度的响应 [J]. 应用生态学报, 2020, 31(1): 35-44.
[8]	李长春, 陈鹏, 陆国政, 马春艳, 马潇潇, 王双亭. 基于无人机高清数码影像和高光谱遥感数据反演大豆典型生育期氮平衡指数 [J]. 应用生态学报, 2018, 29(4): 1225-1232.
[9]	刘俊萍,刘刚,游璐,喻苏琴,连鲁楠,王翰琨,闫梦,胡冬南. 不同品种油茶细根时空分布动态 [J]. 应用生态学报, 2018, 29(12): 3927-3933.
[10]	毛学刚, 杜子涵, 刘家倩, 陈树新, 侯吉宇. 基于面向对象的QuickBird遥感影像林隙分割与分类 [J]. 应用生态学报, 2018, 29(1): 44-52.
[11]	孙中宇, 陈燕乔, 杨龙, 唐光良, 袁少雄, 林志文. 轻小型无人机低空遥感及其在生态学中的应用进展 [J]. 应用生态学报, 2017, 28(2): 528-536.
[12]	满卫东, 刘明月, 王宗明, 毛德华, 田艳林, 贾明明, 李想, 任春颖, 欧阳玲. 1990—2015年三江平原生态功能区水禽栖息地适宜性动态 [J]. 应用生态学报, 2017, 28(12): 4083-4091.
[13]	毛学刚, 魏晶昱. 基于多源遥感数据的面向对象林分类型识别 [J]. 应用生态学报, 2017, 28(11): 3711-3719.
[14]	杜华强,孙晓艳,,韩凝,毛方杰,. 综合面向对象与决策树的毛竹林调查因子及碳储量遥感估算 [J]. 应用生态学报, 2017, 28(10): 3163-3173.
[15]	井然, 邓磊, 赵文吉, 宫兆宁. 基于可见光植被指数的面向对象湿地水生植被提取方法 [J]. 应用生态学报, 2016, 27(5): 1427-1436.