[1]茅正冲,刘永娟.基于机器视觉的玉米雄穗识别算法[J].南京理工大学学报(自然科学版),2016,40(06):661.[doi:10.14177/j.cnki.32-1397n.2016.40.06.004]
 Mao Zhengchong,Liu Yongjuan.Corn tassel recognition algorithm based on machine vision[J].Journal of Nanjing University of Science and Technology,2016,40(06):661.[doi:10.14177/j.cnki.32-1397n.2016.40.06.004]
点击复制

基于机器视觉的玉米雄穗识别算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
40卷
期数:
2016年06期
页码:
661
栏目:
出版日期:
2016-12-30

文章信息/Info

Title:
Corn tassel recognition algorithm based on machine vision
文章编号:
1005-9830(2016)06-0661-05
作者:
茅正冲刘永娟
江南大学 轻工过程先进控制教育部重点实验室,江苏 无锡 214122
Author(s):
Mao ZhengchongLiu Yongjuan
Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education), Jiangnan University,Wuxi 214122,China
关键词:
机器视觉 玉米 雄穗 识别 抽雄期 错分率 查全率
Keywords:
machine vision corn tassels recognition corn tasseling stage fault rate recall rate
分类号:
TP391
DOI:
10.14177/j.cnki.32-1397n.2016.40.06.004
摘要:
为了根据田间图像自动判断玉米抽雄期,提出了1种玉米雄穗分割方法。首先将红绿蓝(RGB)图像转换到YCbCr空间,对Cb、Cr分量图进行增强处理; 再利用训练好的Fisher分类器对每个像素的Cb、Cr值进行分类,初步分割出玉米雄穗; 然后利用颜色指数超蓝因子(ExB)对RGB图像进行灰度化处理,利用改进的Kmeans聚类对灰度图像进行聚类; 最后结合Fisher分类结果和聚类结果确定玉米雄穗像素。实验结果表明采用该文方法识别玉米雄穗,正常环境下的错分率和查全率分别为0.177%和0.831%,干旱环境下的错分率和查全率分别为0.141%和0.811%,该文方法对玉米生长环境具有很好的鲁棒性。
Abstract:
A corn tassel segmentation algorithm is proposed for corn field large area images to determine corn tasseling stage automatically.Firstly,a red green blue(RGB)image is converted to the YCbCr space,Cb and Cr component images are enhanced respectively; then a Fisher classifier is trained to classify the Cb and Cr value of each pixel and corn tassels are segmented preliminary; next,a new color index excess blue index(ExB)is used to gray the RGB image,and the gray image is clustered by an improved Kmeans; lastly,the Fisher classification results and clustering results are combined to determine final corn tassel pixels.Experimental results show that this algorithm can identify corn tassels effectively,fault rate and recall rate of a normal environment are 0.177% and 0.831% respectively,fault rate and recall rate of a drought environment are 0.141% and 0.811% respectively,this algorithm is robust for maize growth environments.

参考文献/References:

[1] 唐文冰,张彦娥,张东兴,等.基于双目立体视觉的玉米雄穗识别与定位研究[C]//中国农业工程学会2011年学术年会论文集.重庆:中国农业工程学会,2011:1-6.
[2]Ye Mengni,Cao Zhiguo,Yu Zhenghong.An image-based approach for automatic detecting tasseling stage of maize using spatio-temporal saliency[J].Proceedings of SPIE,2013,8921(6):89210Z-89210Z-8.
[3]Kurtulmus F,Kavdir I.Detecting corn tassels using computer vision and support vector machines[J].Expert Systems with Applications,2014,41(16):7390-7397.
[4]杨帆,王志陶,张华.精通图像处理经典算法(MATLAB版)[M].北京:北京航空航天大学出版社,2014.
[5]杨莉萍,路松峰,胡和平,等.基于Fisher判别法的一种DNA序列分类方法[J].华中农业大学学报,2013,32(1):125-129.
Yang Liping,Lu Songfeng,Hu Heping,et al.A classification method of DNA sequence based on Fisher discriminant analysis[J].Journal of Huazhong Agricultural University,2013,32(1):125-129.
[6]李正兵,罗斌,翟素兰,等.基于关联图划分的Kmeans算法[J].计算机工程与应用,2013,49(21):141-144,151.
Li Zhengbing,Luo Bin,Zhai Sulan,et al.Kmeans algorithm based on partition of correlational graph[J].Computer Engineering and Applications,2013,49(21):141-144,151.
[7]Zahra S,Ghazanfar M A,Khalid A,et al.Novel centroid selection approaches for KMeans-clustering based recommender systems[J].Information Sciences,2015,320(C):156-189.

备注/Memo

备注/Memo:
收稿日期:2016-03-18 修回日期:2016-05-09
基金项目:国家自然科学基金(60973095); 江苏省自然科学基金(BK20131107)
作者简介:茅正冲(1964-),男,硕士,副教授,主要研究方向:机器人视听觉识别、工业控制,E-mail:1063519780@qq.com。
引文格式:茅正冲,刘永娟.基于机器视觉的玉米雄穗识别算法[J].南京理工大学学报,2016,40(6):661-665.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2016-12-30