[1]徐金勤,邱新法,丁肖,等.基于数码照片的草地植被盖度快速提取方法对比[J].江苏农业学报,2018,(02):313-319.[doi:doi:10.3969/j.issn.1000-4440.2018.02.013]
 XU Jin-qin,QIU Xin-fa,DING Xiao,et al.Research on the rapid extraction approach of grassland vegetation coverage based on digital photos[J].,2018,(02):313-319.[doi:doi:10.3969/j.issn.1000-4440.2018.02.013]
点击复制

基于数码照片的草地植被盖度快速提取方法对比()
分享到:

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2018年02期
页码:
313-319
栏目:
耕作栽培·资源环境
出版日期:
2018-04-25

文章信息/Info

Title:
Research on the rapid extraction approach of grassland vegetation coverage based on digital photos
作者:
徐金勤1邱新法1丁肖2何永健2王丹丹1
(1.南京信息工程大学应用气象学院,江苏南京210044;2.南京信息工程大学地理与遥感学院,江苏南京210044)
Author(s):
XU Jin-qin1QIU Xin-fa1DING Xiao2HE Yong-jian2WANG Dan-dan1
(1.School of Applied Meteorology, Nanjing University of Information Science and Technology, Nanjing 210044, China;2.School of Geography and Remote Sensing, Nanjing University of Information Science and Technology, Nanjing 210044, China)
关键词:
草地植被盖度数码照片颜色特征自动分割
Keywords:
grasslandvegetation coveragedigital photoscolor featuresauto-segmentation
分类号:
TP751
DOI:
doi:10.3969/j.issn.1000-4440.2018.02.013
文献标志码:
A
摘要:
草地植被盖度是表征草地群落结构及其生长状况的重要生态学参数之一。本研究基于乌拉特中旗草地照片,设计一种利用自动阈值分割算法快速计算植被盖度的方法,依次选取RGB颜色空间的EXG指数、HIS颜色空间的H分量、L*a*b*颜色空间的a*分量作为草地植被盖度提取的颜色特征,对比分析上述3种颜色特征方法快速提取草地盖度的效果。结果表明:EXG指数法的提取效果最好,其估算误差相对最低、精度最高、适用性最好;a*分量法次之;H分量法的估算误差相对较大。在去除阴影后,H分量法的估算误差降低、精度也随之升高,EXG指数法的估算精度略有降低,a*分量法无明显变化。3种方法对绿色草地的估算效果均优于黄绿色草地,尤其是a*分量法,其对黄绿色草地的估算精度为80.7%,而对绿色草地的估算精度却高达91.7%,仅次于EXG指数法(93.4%)。
Abstract:
Grassland vegetation coverage is an important ecological parameter of grassland community structure and growth status. Based on the photo of Wulatezhongqi grassland, the EXG index based on RGB space, H component of HIS and a* component of L*a*b* were selected as the color features for grassland vegetation cover extraction. Using the automatic threshold segmentation algorithm,the effects of EXG method, H component method and a* component method were compared and analyzed. The results showed that the EXG method had the best effect, it had the lowest estimation error, highest precision and best applicability. The a* component method had suboptimal effect, and H component method had the worst effect. After removing the shadow, the estimate error of H component method had a significant reduction, the precision of EXG method decreased, but a* component method had no obvious change. The estimation accuracy of three methods to green grass was better than that to yellow-green grass, especially a* component method, its precision to estimate green grass was about 91.7% which was second only to EXG method (93.4%).

参考文献/References:

[1]温庆可,张增祥,刘斌,等. 草地覆盖度测算方法研究进展[J]. 草业科学,2009,26(12):30-36.
[2]朱敬芳,邢白灵,居为民,等. 内蒙古草原植被覆盖度遥感估算[J]. 植物生态学报,2011,35(6):615-622.
[3]李岩,尚士友,王晓娟,等.西乌珠穆沁典型草原植被盖度空间异质性研究[J]. 江苏农业科学,2017,45(22):283-288.
[4]张云霞,李晓兵,陈云浩.草地植被覆盖度的多尺度遥感与实地测量方法综述[J].地球科学进展,2003,18(1):85-93.
[5]张云霞,张云飞,李晓兵.地面测量与ASTER 影像综合计算植被盖度[J].生态学报,2007,27(3):964-976.
[6]陈祖刚,巴图娜存,徐芝英,等.基于数码相机的草地植被盖度测量方法对比研究[J].草业学报,2014,23(6):20-27.
[7]GUIJARRO M,PAJARES G,RIOMOROS I,et al. Automatic segmentation of relevant textures in agricultural images[J]. Computers & Electronics in Agriculture,2011,75(1):75-83.
[8]池宏康,周广胜,许振柱,等. 草地植被盖度的近距离遥感测定[J]. 草业学报,2007,16(2):105-110.
[9]张清平,章山山,陈露,等. 应用WinCAM软件判识分析草坪盖度[J]. 草业科学,2010,27(7):13-17.
[10]VOL N. Color indices for weed identification under various soil,residue,and lighting conditions[J]. Transactions of the Asae,1995,38(1):259-269.
[11]毛文华. 基于机器视觉的田间杂草识别技术研究[D]. 北京:中国农业大学,2004.
[12]任世龙,宜树华,陈建军,等.基于不同数码相机和图像处理方法的高寒草地植被覆盖度估算的比较[J].草业科学,2014,31(6):1007-1013.
[13]谈蓉蓉. 利用颜色和形状特征的杂草识别方法研究[D]. 镇江:江苏大学,2009.
[14]付忠良. 图像阈值选取方法——Otsu方法的推广[J]. 计算机应用,2000,20(5):37-39.
[15]陈纯. 计算机图像处理技术与算法[M]. 北京:清华大学出版社,2003.
[16]LALIBERTE A S,RANGO A,HERRICK J E,et al. An object-based image analysis approach for determining fractional cover of senescent and green vegetation with digital plot photography [J]. Journal of Arid Environments,2007,69(1):1-14.
[17]BAUER T,STRAUSS P. A rule-based image analysis approach for calculating residues and vegetation cover under field conditions[J]. Catena,2014,113(113):363-369.
[18]章超斌,李建龙,张颖,等.基于RGB模式的一种草地盖度定量快速测定方法研究[J].草业学报,2013,22(4):220-226.
[19]胡健波,张璐,黄伟,等. 基于数码照片的草地植被覆盖度快速提取方法[J]. 草业科学,2011,28(9):1661-1665.

备注/Memo

备注/Memo:
收稿日期:2017-09-05 基金项目:国家自然科学基金项目(41330529);江苏省第四期“333高层次人才培养工程” 科研项目(BRA2014373) 作者简介:徐金勤(1995-),女,山东临沂人,硕士研究生,主要从事应用气象与草地生态系统研究。(E-mail)xujinqin0307@163.com 通讯作者:邱新法,(E-mail)xfqiu135@nuist.edu.cn
更新日期/Last Update: 2018-05-04