Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (5): 1158-1166    DOI: 10.11873/j.issn.1004-0323.2020.5.1158
遥感应用     
基于无人机影像的烟草精细提取
夏炎1(),黄亮1,2(),王枭轩1,陈朋弟1
1.昆明理工大学 国土资源工程学院测绘系,云南 昆明 650093
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
Fine Extraction of Tobacco based on UAV Images
Yan Xia1(),Liang Huang1,2(),Xiaoxuan Wang1,Pengdi Chen1
1.Kunming University of Science and Technology,Faculty of Land Resource Engineering,Kunming 650093,China
2.Surveying and Mapping Geo-Informatics Technology Research Center on Plateau;Mountains of Yunnan Higher Education,Kunming 650093,China
 全文: PDF(6392 KB)   HTML
摘要:

烟草是一种特殊农作物,烟草的提取对其信息统计起着重要作用。针对烟草单株提取难的问题,提出了一种结合多特征和超像素的无人机影像烟草精细提取方法。首先利用简单线性迭代聚类 (Simple Linear Iterative Clustering, SLIC)算法对影像进行超像素分割;然后统计超像素的平均值、亮度、长宽比、形状指数、红绿蓝波段值和自定义植被指数;接着通过对超像素特征组合和特征阈值选取来实现烟草的精细提取;最后对提取信息进行统计和分析。实验结果表明:该方法能有效地提取烟草株树,准确度分别为99%和98.6%。利用该方法,在计算烟草产量方面供了有效参考,节省了大部分的人力财力。

关键词: 烟草无人机影像简单线性迭代聚类超像素分割信息提取    
Abstract:

Tobacco is a special crop and the extraction of tobacco plays an important role in its statistics. Aiming at the difficulty of extracting tobacco plants, a tobacco fine extraction method in Unmanned Aerial Vehicle image combined with multi-features and superpixels is proposed. Firstly, the image is segmented by simple linear iterative clustering algorithm; secondly, the Mean value, Brightness, Length/Width, Shape index, Red, Green and Blue band value and custom vegetation index of super pixel are counted; thirdly, fine extraction of tobacco by superpixel features combination and features threshold selection; finally, the extracted information are satisficed and analyzed. The experimental results shown that the method can effectively extract tobacco trees, and the accuracy is 99% and 98.6%, respectively. Using this method, it provides an effective reference in calculating tobacco production, saving most of the human and financial resources.

Key words: Tobacco    UAV image    SLIC    Superpixel segmentation algorithm    Information extraction
收稿日期: 2019-07-17 出版日期: 2020-11-26
ZTFLH:  TP79  
基金资助: 国家自然科学基金项目“南方山地城镇建设用地与变化的坡度样度效应研究”(41961039);云南省应用基础研究计划面上项目“基于全卷积神经网络的多源遥感影像变化检测”(2018FB078);云南省高校工程中心建设计划共同资助
通讯作者: 黄亮     E-mail: 799537530@qq.com;kmhuangliang@163.com
作者简介: 夏炎(1995-),女,云南昆明人,硕士,主要从事遥感影像处理研究。E?mail:799537530@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
夏炎
黄亮
王枭轩
陈朋弟

引用本文:

夏炎,黄亮,王枭轩,陈朋弟. 基于无人机影像的烟草精细提取[J]. 遥感技术与应用, 2020, 35(5): 1158-1166.

Yan Xia,Liang Huang,Xiaoxuan Wang,Pengdi Chen. Fine Extraction of Tobacco based on UAV Images. Remote Sensing Technology and Application, 2020, 35(5): 1158-1166.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.5.1158        http://www.rsta.ac.cn/CN/Y2020/V35/I5/1158

图1  无人机影像图
图2  方法流程图
图3  逐级分类结构图
图4  SLIC算法分割图
图5  数据一的地物特征分布曲线图
图6  数据二的地物特征分布曲线图
光谱均值自定义 特征长宽比亮度指数形状指数
最佳阈值(上)85.480.121.05126.471.20
最佳阈值(下)102.040.161.50143.951.42
表1  烟草各特征值最佳阈值表
图7  烟草精细提取结果
面积级别等级一等级二等级三
数据一烟叶株数3422549
数据一烟叶株数2681 134275
表2  烟叶面积分级统计结果
方法实际 株数提取 株数精确度 /%总体精度 /%

错检率

/%

漏检率 /%
SLIC算法3113089993.415.80.79
对比方法64.5827.38.1
表3  数据一烟草提取精度评价
方法实际 株数提取 株数精确度 /%总体精度 /%错检率 /%漏检率 /%
SLIC算法1701167798.682.5719.060.86
对比方法60.394.135.5
表4  数据二烟草提取精度评价
1 Yan Xinwei, Ma Jianwei, Yingyuan Wand ,et al. Analysis of Grade Qualty of Tobacco Enterprises Transferred into Tobacco Leaves [J].Tobacco Science & Technology,2006,(8):55-59.闫新甫,马建伟,王英元,等.卷烟企业调入烟叶的等级质量分析[J].烟草科技,2006,(8):55-59.
2 Li Runsheng, Cao Fanzhi, Cao Wen, et al. High-resolution Image Road Network Extraction with Multi-features and Multi-method fusion[J].Remote Sensing for Land and Resources,2018,30(3):33-39.
2 李润生,曹帆之,曹闻,等.多特征、多方法融合的高分辨率影像道路网提取[J].国土资源遥感,2018,30(3):33-39
3 Hu Hualong, Wu Bing, Huang Shaomei, et al. High-resolution Remote Sensing Image Combined with Gabor Texture and Geometric Features Urban Road Extraction Method[J]. Journal of Surveying and Mapping Science and Technology, 2015, 32(4): 395-400.
3 胡华龙,吴冰,黄邵美,等.结合Gabor纹理与几何特征的高分辨率遥感影像城区道路提取方法[J].测绘科学技术学报,2015,32(4):395-400.
4 Lin Yuzhun, Zhang Baoming, Wang Danyu, et al. High-resolution Remote Sensing Image Building Classification Extraction with Multi-feature Fusion[J].Journal of Image and Graphics,2017,22(12):1798-1808.
4 林雨准,张保明,王丹菂,等.多特征融合的高分辨率遥感影像建筑物分级提取[J].中国图象图形学报,2017,22(12):1798-1808.
5 Yan Li, Jiang Weiwei. A Method for Automatic Extraction of High Resolution Remote Sensing Image Plantation Using Structural Features[J]. Acta Geochimica et Cartograpgaica Sinica,2016,45(9):1065-1072.
5 闫利,江维薇.一种利用结构特征的高分辨率遥感影像种植园自动提取方法[J].测绘学报,2016,45(9):1065-1072.
6 Han Wenting, Li Guang, Yuan Mengchan, et al. Study on Corn Planting Information Extraction Method based on UAV Remote Sensing Technology[J].Transactions of the Chinese Society of Agricultural Machinery, 2017, 48(1): 139-147.
6 韩文霆, 李广, 苑梦婵, 等. 基于无人机遥感技术的玉米种植信息提取方法研究[J].农业机械学报,2017,48(1):139-147.
7 Dong Mei, Su Jiandong, Liu Guangyu, et al. Object-oriented Remote Sensing Image Extraction and Monitoring of Tobacco Planting Surface[J].Science of Surveying and Mapping,2014,39(9):87-90.
7 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提取和监测[J].测绘学科,2014,39(9):87-90.
8 Li Tiankun. Research on Extraction of Tobacco Planting Area based on Object-oriented Classification Method[D]. Ya`an: Sichuan Agricultural University, 2013.
8 李天坤. 基于面向对象分类方法的烟草种植面积提取研究[D].雅安:四川农业大学,2013.
9 Chen Jin, Liu Pinchao, Huang Guoqiang, et al. Extraction of Tobacco Planting Area Information based on Remote Sensing Image of UAV[J].Hunan Agricultural Sciences, 2018,(1):96-99,103.陈金,刘品超,黄国强,等.基于无人机遥感影像的烟草种植面积信息提取[J].湖南农业科学,2018,(1):96-99,103.
10 Liu Shuaibing, Yang Guijun, Zhou Chengquan, et al. Extraction of Plant Number Information of Maize Seedlings based on Remote Sensing Image of UAV[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,(22): 69-77.刘帅兵,杨贵军,周成全,等.基于无人机遥感影像的玉米苗期株数信息提取[J].农业工程学报,2018,(22):69-77.
11 Li Xin, Zhang Y E, Zhu J F, et al. Pose Parameter Extraction of Corn Canopy Remote Sensing Images based on Parallel Multi-ocular Imaging[J].2010,(13):168-176.doi:10.1117/ 12.866202
doi: 10.1117/ 12.866202
12 Du Ying, Cai Yicheng, Tan Changwei, et al. Statistical Method of Field Wheat Spike Number based on Superpixel Segmentation[J]. Chinese Agricultural Science, 2019,52(1):21-33.
12 杜颖,蔡义承,谭昌伟,等.基于超像素分割的田间小麦穗数统计方法[J].中国农业科学,2019,52(1):21-33.
13 Zhou C Q, Liang D, Yang X D, et al. Recognition of Wheat Spike from Field based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms [J]. Remote Sensing, 2018,10(2):246-.doi: 10.3390/rs10020246.
doi: 10.3390/rs10020246
14 Chen Wen. Evaluation of Wheat Seedling Uniformity based on UAV Images[D]. Yangzhou: Yangzhou University, 2018.
14 陈雯.基于无人机图像的小麦出苗均匀度评价[D].扬州:扬州大学,2018.
15 Lv Qiang, Cai Jianrong, Zhan Jiewen, et al. Real-time Recognition Technology of Citrus on Tree under Natural Scene [J]. Transactions of the Chinese Society of Agricultural Machinery, 2010, 41(2):185-188.
15 吕强, 蔡健荣, 赵杰文,等. 自然场景下树上柑橘实时识别技术[J].农业机械学报, 2010, 41(2):185-188.
16 Maldonado W, José Carlos Barbosa. Automatic Green Fruit Counting in Orange Trees Using Digital Images[M]. Elsevier Science Publishers, 2016(12):66-70. doi:10.1016/j.compag.2016.07.023.
doi: 10.1016/j.compag.2016.07.023
17 Koc-San D, Selim S, Aslan N, et al. Automatic Citrus Tree Extraction from UAV Images and Digital Surface Models Using Circular Hough transform[J]. Computers and Electronics in Agriculture, 2018, 150:289-301.
18 Roth, Sandra , Leiterer, et al. Automated Detection of Individual Clove Trees for Yield Quantification in Northeastern Madagascar based on Multi-spectral Satellite Data[J]. Remote Sensing of Environment, 2018, 221:144-156.doi: 10.1016/j.rse.2018.11.009
doi: 10.1016/j.rse.2018.11.009
19 Zhao Kun, Zhang Yujun, Zhang Jianlong, et al. Small Target Detection Method for UAV Images based on SLIC Hierarchical Segmentation[J].Journal of Data Acquisition & Processing,2017,32(4):737-745.
19 赵坤,张羽君,张建龙,等.基于SLIC分层分割的无人机图像极小目标检测方法[J].数据采集与处理,2017,32(4):737-745.
20 Run Yi, Wang Mi, Dong Zhipeng, et al. Urban Road Extraction based on SLIC Superpixel High Resolution Remote Sensing Image [J]. Geomatics of Surveying and Mapping, 2019, 44(1): 84-88.
20 润一,王密,董志鹏,等.基于SLIC超像素的高分辨率遥感影像城镇道路提取[J].测绘地理信息,2019,44(1):84-88.
21 Achanta R, Shaji A, Smith K, et al. SLIC Super Pixels[R]. No. EPFL REPORT 149300. 2010.
22 Achanta R , Shaji A , Smith K , et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282. doi: 10.1109/TPAMI.2012.120
doi: 10.1109/TPAMI.2012.120
[1] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[2] 李越帅,郑宏伟,罗格平,杨辽,王伟胜,桂东伟. 集成U-Net方法的无人机影像胡杨树冠提取和计数[J]. 遥感技术与应用, 2019, 34(5): 939-949.
[3] 周在明,杨燕明,陈本清. 基于无人机影像的滩涂入侵种互花米草植被信息提取与覆盖度研究[J]. 遥感技术与应用, 2017, 32(4): 714-720.
[4] 吕利利,颉耀文,黄晓君,张秀霞,李汝嫣. 基于CART决策树分类的沙漠化信息提取方法研究[J]. 遥感技术与应用, 2017, 32(3): 499-506.
[5] 马斅良,王钦军,陈玉. 基于图像模拟的蚀变矿物信息提取技术评价[J]. 遥感技术与应用, 2016, 31(4): 756-763.
[6] 张明哲,张红,王超,刘萌,谢镭. 基于超像素分割和多方法融合的SAR 图像变化检测方法[J]. 遥感技术与应用, 2016, 31(3): 481-487.
[7] 张正健,李爱农,边金虎,赵伟,南希,靳华安,谭剑波. 基于无人机影像可见光植被指数的若尔盖草地地上生物量估算研究[J]. 遥感技术与应用, 2016, 31(1): 51-62.
[8] 韩忻忆,颉耀文. 基于决策树的干旱区湿地信息自动提取—以疏勒河流域为例[J]. 遥感技术与应用, 2015, 30(6): 1146-1152.
[9] 田力,徐雯佳. 卫星遥感海冰监测技术在河北省近海海域的应用[J]. 遥感技术与应用, 2015, 30(4): 793-797.
[10] 白晓燕,陈晓宏,王兆礼. 基于面向对象分类的土地利用信息提取及其时空变化研究[J]. 遥感技术与应用, 2015, 30(4): 798-809.
[11] 张勇,谷正气,刘水长,罗伦,李程. 基于高分辨率遥感影像的城市群交通路网监测技术研究[J]. 遥感技术与应用, 2015, 30(1): 76-81.
[12] 刘辰,刘修国,陈启浩,高伟. 面向对象滑坡信息提取中DEM空间分辨率影响分析[J]. 遥感技术与应用, 2014, 29(4): 631-638.
[13] 钱家航,王金亮,马如彪,邓钰. 基于QuickBird影像城市道路特征语义信息提取[J]. 遥感技术与应用, 2014, 29(4): 653-659.
[14] 李政,李永树,唐敏. 一种求解无人机影像外方位角元素的方法[J]. 遥感技术与应用, 2014, 29(3): 506-510.
[15] 曹林,许子乾,代劲松,王靖琦,羌鑫林,佘光辉. 基于LiDAR和CCD数据的地形与建筑提取方法优化及精度评价[J]. 遥感技术与应用, 2014, 29(1): 130-137.