基于无人机可见光遥感的棉花面积信息提取

doi:10.6048/j.issn.1001-4330.2018.03.018

摘要/Abstract

摘要： 【目的】针对传统大区域棉花种植信息提取方法相对落后的问题,运用面向对象的影像分析方法,对无人机遥感试验获取的可见光影像进行棉花种植信息的提取。【方法】选用双子星MyFlyDream MTD固定翼无人机搭载佳能EF-M 18-55相机,获取新疆建设兵团第八师135团的可见光影像,借助eCognition软件平台,运用面向对象的方法对研究区内棉花种植信息进行提取试验。【结果】目视解译提取的棉花种植面积为0.35 km²,面向对象提取的棉花种植面积为0.33 km²,分类结果精度为94.29%,误差系数为5.71%,可以有效地提取研究区域棉花种植信息。【结论】面向对象的分类方法相比于传统的基于像素的分类方法提取精度更高,更加接近于目视解译的提取结果。

关键词: eCognition; 面向对象; 无人机可见光遥感; 棉花; 种植信息

Abstract: 【Objective】 This project aims to use object-oriented image classification method to extract the planting information of the visible light remote sensing image of the UAV in the hope of providing a new method for extracting large-scale farmland information and improving the speed and precision of classification results.【Method】The study selected fixed-wing UAV equipped with a camera and obtained the visible light images of 135th regiment farm of the eighth division of Xinjiang Production and Construction Corps. With the help of eCognition software platform, using the object-oriented method, the cotton planting information in the study area was extracted for experiments.【Result】The planting area of cotton extracted by visual interpretation was 0.35 km²,and that by object-oriented approach was 0.33 km². The results showed that this method could effectively extract the cotton planting area in the study area, and the classification accuracy reached 94.29%, error of 5.71%.【Conclusion】Compared with traditional pixel-based classification methods, using the object-oriented classification method to extract the range information of visible light images captured by UAV has higher extraction accuracy and is greatly closer to visual interpretation.

Key words: eCognition; object oriented; visible light remote sensing of UAV; cotton; planting information

中图分类号:

李路曼,郭鹏,张国顺,周倩,吴锁智. 基于无人机可见光遥感的棉花面积信息提取[J]. 新疆农业科学, 2018, 55(3): 548-555.

LI Lu-man, GUO Peng, ZHANG Guo-shun, ZHOU Qian, WU Suo-zhi. Research on Area Information Extraction of Cotton Field Based on UAV Visible Light Remote Sensing[J]. Xinjiang Agricultural Sciences, 2018, 55(3): 548-555.

参考文献

[1] 李敏, 赵庚星, 蔡明庆. 县域棉花信息遥感提取与棉田精确化管理分区研究[J]. 自然资源学报, 2012, 27(11): 1 972-1 980.
LI Min, ZHAO Geng-xing, CAI Ming-qing. (2012). Extraction of Cotton Information Using Remote Sensing and Precision Management Zoning at County Scale [J]. Journal of Natural Resources, 27(11): 1,972-1,980. (in Chinese)
[2] 黄青, 王利民, 滕飞. 利用MODIS -NDVI 数据提取新疆棉花播种面积信息及长势监测方法研究[J]. 干旱地区农业研究, 2011, 29(2): 214-217.
HUANG Qing, WANG Li-min, TENG Fei. (2011). MODIS-NDVI-based monitoring of cotton planting areas and growth condition in Xinjiang [J]. Agricultural Research in the Arid Regions, 29(2): 214-217. (in Chinese)
[3] 田野, 张清, 李希灿, 等. 基于多时相影像的棉花种植信息提取方法研究[J]. 干旱区研究, 2017, 34(2): 423-430.
TIAN Ye, ZHANG Qing, LI Xi-can, et al. (2017). Extraction Method of Cotton Plantation Information Based on Multi-Temporal Images [J]. Research in the Arid Areas, 34(2): 423-430. (in Chinese)
[4] 杨进生, 郭颖平, 盖利亚, 等. 无人直升机遥感在华北平原地裂缝监测中的应用[J]. 遥感信息, 2015, 30(1): 66-70.
QANG Jin-sheng, GUO Ying-ping, GAI Li-ya, et al. (2015). Application of Unmanned Helicopter Remote Sensing in Monitoring Ground Fissure in North China Plain[J]. Remote Sensing Information, 30(1): 66-70. (in Chinese)
[5] 赵丹曹. 基于多光谱影像的县域农田质量信息提取与快速评价[D]. 北京: 中国地质大学硕士论文, 2015.
ZHAO Dan-cao. (2015). Extraction and Assessment of Farmland Information based on Multispectral Images of County Area [D]. Master Dissertation. China University of Geosciences, Beijing. (in Chinese)
[6] 李敏. 基于RS和GIS的县域棉花信息提取几分区管理研究-以山东省夏津县为例[D]. 泰安: 山东农业大学硕士论文, 2012.
LIN Min. (2012). Cotton Information Extraction and Management Zoning Based on RS and GIS at County Scale --A Case Study in Xiajin County, Shandong Province [D]. Master Dissertation. Shandong Agricultural University, Taian. (in Chinese)
[7] 尤惠, 高华东, 苏荣瑞, 等. 基于多时相中分辨率时间过程特征的江汉平原棉花种植面积变化监测[J]. 地球信息科学, 2016, 18(8): 1 142-1 149.
YOU Hui, GAO Hua-dong, SU Rong-rui. et al. (2016). Monitoring the Changes of Cotton Plantation Area Based on the Multi-temporal Middle Resolution Features of Temporal Process in Jianghan Plain [J]. Geo-Information Science, 18(8): 1,142-1,149. (in Chinese)
[8] 翟立君. 卫星MPLS网络关键技术研究[M].北京: 清华大学出版社, 2001.
ZHAI Li-jun. (2001). Research on the Key Technologies in Satellite MPLS Networks [M]. Beijing: Tsinghua University Press. (in Chinese)
[9] 杜红, 杜峰, 李红英, 等. 新疆农八师垦区气候变化及对农业的影响[J]. 中国农学通报, 2012, 28(20): 290-294.
DU Hong, DU Feng, LI Hong-ying, et al. (2012). Climate Change and Its Effect on Agriculturalin Xinjiang Nong Ba Shi Reclamation Area [J]. Chinese Agricultural Science Bulletin, 28(20): 290-294. (in Chinese)
[10] 秦修功, 陈曦, 杨辽. 构架航线对无人机影像区域网平差精度影响分析[J]. 测绘科学, 2017, 42(1): 151-163.
QIN Xiu-gong, CHEN Xi, YANG Liao. (2017). Impact analysis of flight on accuracy of block adjustment for UAV aerial images [J]. Science of Surveying and Mapping, 42(1): 151-163. (in Chinese)
[11] 刘家福, 刘吉平, 姜海玲. eCognition数字图像处理方法[M]. 北京: 科学出版社, 2017: 57-58.
LIU Jia-fu, LIU Ji-ping, JIANG Hai-ling. (2017). eCognitionDigital image processing method [M]. Beijing: Science Press, 57-58. (in Chinese)
[12] 江华. 基于eCognition的地理国情普查道路信息提取[D]. 上海: 华东理工大学硕士论文, 2015.
JIANG Hua. (2015). Road Information Extraction for National Geographical Conditions Census Based on eCognition [D]. Master Dissertation. East China Institute of Technology, Shanghai. (in Chinese)
[13] 吴健生, 刘建政, 黄秀兰. 基于面向对象分类的土地整理区农田灌排系统自动化识别[J]. 农业工程学报, 2012, 28(8): 25-31.
WU Jian-sheng, LIU Jian-zheng, HUANG Xiu-lan. (2012). Automatic identification of irrigation and drainage system in land reclamation area based on object-oriented classification [J]. Transactions of the CSAE, 28(8): 25-31. (in Chinese)
[14] 董梅, 苏建东, 刘广玉, 等. 面向对象的无人机遥感影像烟草种植面积提取与监测[J]. 测绘科学, 2014, 39(9): 88-90.
DONG Mei, SU Jian-dong, LIU Guang-yu, et al. (2014). Extraction of tobacco planting area from UAV remote sensing image by object-oriented classification method [J]. Science of Surveying and Mapping, 39(9): 88-90. (in Chinese)
[15] 曹卫彬, 杨邦杰, 宋金鹏. TM影像中基于光谱特征的棉花识别模型[J]. 农业工程学报, 2004, 20(4): 113-116.
CAO Wei-bin, YANG Bang-jie, SONG Jin-peng. (2004) Spectral information based model for cotton identification on Landsat TM Image. Transactions of the CSAE, 20(4): 113-116. (in Chinese)
[16] 丛瑜, 苗红正. 基于面向对象技术的农田分类方法[J]. 地理空间信息, 2016, 14(10): 89-92.
CONG Yu, MIAO Hong-zheng. (2016). Farmland Classification Method Based on Object-oriented Technology [J]. Geospatial Information, 14(10): 89-92. (in Chinese)
[17] 玉苏甫·买买提, 吐尔逊·艾山, 买合皮热提·吾拉木. 新疆渭 - 库绿洲棉花种植面积遥感监测研究[J]. 农业现代化研究, 2014, 35(2): 241-243.
Yusup Mamat, Tursun Hasan, Magpirat Gulam. (2014). Remote Sensing of Cotton Plantation Areas Monitoring in Delta Oasis of Ugan-Kucha River, Xinjiang [J]. Agricultural Modernization Research, 35(2): 241-243.(in Chinese)
[18] 齐义娜. 面向对象的高分辨率遥感影像信息提取与尺度效应分析[M]. 吉林: 东北师范大学, 2009: 12-13.
QI Yi-na. (2009). Feature extraction and scale effect analysis of high-resolution image using object-oriented approach [M]. Jilin: Northeast Normal University, 12-13. (in Chinese)
[19] 汪小钦,王苗苗,王绍强,等. 基于可见光波段无人机遥感的植被信息提取[J]. 农业工程学报,2015,31(5):152-158.
WANG Xiao-qin, WANG Miao-miao, WANG Shao-qiang, et al. (2015). Extraction of vegetation information from visible unmanned aerial vehicle images [J]. Transactions of the CSAE, 31(5): 152-158. (in Chinese)