[1]陈科尹,吴崇友,关卓怀,等.基于统计直方图k-means聚类的水稻冠层图像分割[J].江苏农业学报,2021,(06):1425-1435.[doi:doi:10.3969/j.issn.1000-4440.2021.05.009]
　CHEN Ke-yin,WU Chong-you,GUAN Zhuo-huai,et al.Rice canopy image segmentation based on statistical histogram k-means clustering[J].,2021,(06):1425-1435.[doi:doi:10.3969/j.issn.1000-4440.2021.05.009]
点击复制

基于统计直方图k-means聚类的水稻冠层图像分割()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年06期
页码:
1425-1435
栏目:
耕作栽培·资源环境
出版日期:
2021-12-30

文章信息/Info

Title:
Rice canopy image segmentation based on statistical histogram k-means clustering
作者:
陈科尹1; 2; 吴崇友2; 关卓怀2; 李海同2; 王刚2
(1.嘉应学院物理与电子工程学院，广东梅州514015；2.农业农村部南京农业机械化研究所，江苏南京210014)
Author(s):
CHEN Ke-yin1; 2; WU Chong-you2; GUAN Zhuo-huai2; LI Hai-tong2; WANG Gang2
(1.School of Physics and Electronic Engineering, Jiaying University, Meizhou 514015, China；2.Nanjing Institute of Agricultural Mechanization，Ministry of Agriculture and Rural Affairs， Nanjing 210014, China)
关键词:
水稻冠层图像; 图像分割; 统计直方图; k-means聚类
Keywords:
rice canopy image; image segmentation; statistical histogram; k-means clustering
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2021.05.009
文献标志码:
A
摘要:
针对现有k-means聚类图像分割方法存在对初始聚类中心敏感、易错分割以及运行时效低等问题，提出了一种基于统计直方图k-means聚类的水稻冠层图像分割方法。该方法首先根据图像直方图蕴含的像素数量先验信息，选择像素数量差异较大的像素值作为水稻冠层图像的初始聚类中心；然后再利用图像直方图中像素值与图像像素数量的先验对应关系，对水稻冠层图像聚类目标函数权值化；最后依据k-means聚类框架对水稻冠层图像进行聚类分割。为了验证本方法的有效性，分别同基于k-means、k-means++、k-mc2、afk-mc2等4种主流均值聚类的水稻冠层图像特征像素提取方法进行对比试验。结果表明：对于临稻20号、武运粳32号以及中粳798号成熟中期水稻冠层图像聚类分割，常光下本方法的平均类内平方差分别为36.6、29.5、29.5，平均类间平方差分别为67.5、51.8、51.8，平均运行时间分别为0.2 s、0.3 s、0.3 s；强光下本方法的平均类内平方差分别为15.2、4.9、12.1，平均类间平方差分别为30.9、9.5、21.2，平均运行时间分别为0.3 s、0.2 s、0.3 s，均优于以上4种聚类方法。
Abstract:
A rice canopy image segmentation method based on statistical histogram k-means clustering was proposed to solve the problems of existing k-means methods, such as sensitivity to the initial cluster center, error prone segmentation and low operation efficiency. Firstly, according to the image histogram, the pixel value with large difference in the number of pixels was selected as the initial cluster center of the rice canopy image. Secondly, the prior correspondence between the pixel value in the image histogram and the number of pixels in the image was used to weight the clustering objective function. Finally, the k-means clustering framework was used to cluster and segment the rice canopy image. In order to verify the effectiveness of the proposed method, comparative experiments were carried out with the feature pixel extraction methods of rice canopy images based on k-means, k-means++, k-mc2 and afk-mc2. The results showed that the canopy images of Lindao 20, Wuyunjing 32 and Zhongjing 798 were clustered and seymented at mid-maturing stage, and the average intra-class sequare errors were 36.6， 29.5 and 29.5 under normal light conditions, the average inter-class square errors were 67.5, 51.8 and 51.8, and the average running time was 0.2 s, 0.3 s and 0.3 s. Under strong light conditions, the average intra-class square errors were 15.2, 4.9 and 12.1, the average inter-class square errors were 30.9, 9.5 and 21.2, and the average running time was 0.3 s, 0.2 s and 0.3 s. The results of the method used in this study are better than the above four traditional clustering methods.

参考文献/References:

[1]杨一平，胡德民. 联合收割机喂入量信号采集电路的设计与研究[J]. 安徽农业科学，2008，36(35)：15746-15748，15750.
[2]陈进，李耀明，季彬彬. 联合收获机喂入量测量方法[J]. 农业机械学报，2006，37(12)：76-78.
[3]梁学修，陈志，张小超，等. 联合收获机喂入量在线监测系统设计与试验[J].农业机械学报，2013，44(增刊)：1-6.
[4]潘静，邵陆寿，王轲. 水稻联合收割机喂入密度检测方法[J]. 农业工程学报，2010，26(8)：113-116.
[5]潘静. 基于遗传算法的水稻联合收割机喂入密度检测方法研究[D]. 合肥：安徽农业大学，2011.
[6]王轲. 基于视频挖掘的成熟期水稻图像处理算法研究[D]. 合肥：安徽农业大学，2011.
[7]KUMHALA F, KROULIK M, MASEK J, et al. Development and testing of two methods for the measurement of the mowing machine feed rate[J]. Plant Soil & Environment，2003，49(11)：519-524.
[8]MONTES J M, PAUL C, MELCHINGER A E. Quality assessment of rapeseed accessions by means of near-infrared spectroscopy on combine harvesters[J]. Plant Breeding，2010，126(3)：329-330.
[9]EI-FAKI M S, ZHANG N, PETERSON D E. Factors affecting color based weed detection[J]. Transaction of the ASAE，2000，43 (4)：1001-1009.
[10]刘汉青. 基于机器视觉的油菜收获疏密度与损失检测[D]. 南京：南京大学，2019.
[11]王远，王德建，张刚，等. 基于数码相机的水稻冠层图像分割及氮素营养诊断[J]. 农业工程学报，2012，28(17)：131-136.
[12]黄巧义，张木，李苹，等. 支持向量机和最大类间方差法结合的水稻冠层图像分割方法[J]. 中国农业科技导报，2019，21(4)：52-60.
[13]黄巧义，张木，黄旭，等. 基于可见光谱色彩指标Otsu法的水稻冠层图像分割[J]. 广东农业科学，2018，45(1)：120-125，3.
[14]黄巧义，樊小林，张木，等. 水稻冠层图像分割方法对比研究[J]. 中国生态农业学报，2018，26(5)：710-718.
[15]徐梅宣，张智刚，潘慕，等. 田间水稻冠层图像分割算法的研究[J]. 广东农业科学，2015，42(13)：161-164.
[16]SELIM S Z, ISMAIL M A. k-means-type algorith-ms: a generalized convergence theorem and character-ization of local optimality[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1984，6(1)：81-87.
[17]ESTEVES R M, HACKER T, RONG C. Competitive K-means, a new accurate and distributed k-means algorithm for large datasets[C]//IEEE. IEEE 5th internati-onal conference on cloud computing technology and science. Bristol:IEEE, 2013：17-24.
[18]CHEN X, MIAO P， BU Q. Image segmentation algorithm based on particle swarm optimization with k-means optimization[C]//IEEE. IEEE International Conference on Power, Intelligent Computing and Systems. Shenyang，China:IEEE,2019：156-159.
[19]SINAGA K P， YANG M. Unsupervised k-means clustering algorithm[J]. IEEE Access, 2020，8： 80716-80727.
[20]KUMAR K M，REDDY A R M. A fast k-means clustering using prototypes for initial cluster center selection[C]//IEEE. IEEE 9th international conference on intelligent systems and control. Coimbatore:IEEE，2015：1-4.
[21]LEI G. A novel locality sensitive k-means clustering algorithm based on subtractive clustering[C]//IEEE. 7th IEEE international conference on software engineering and service science. Beijing:IEEE，2016： 836-839.
[22]GU L. A novel sample weighting k-means clustering algorithm based on angles information[C]//IEEE. International joint conference on neural networks. Vancouver, BC:IEEE, 2016：3697-3702.
[23]HUNG W，YANG M，HWANG C. Exponential-Distance weighted k-means algorithm with spatial constraints for color image segmentation[C]//IEEE. 2011 international conference on multimedia and signal processing. Guilin, Guangxi:IEEE, 2011：131-135.
[24]郭永坤，章新友，刘莉萍，等. 优化初始聚类中心的k-means聚类算法[J]. 计算机工程与应用，2020，56(15)：172-178.
[25]田诗宵，丁立新，郑金秋. 基于密度峰值优化的k-means文本聚类算法[J]. 计算机工程与设计， 2017，38(4)：1019-1023.
[26]贾洪杰，丁世飞，史忠植. 求解大规模谱聚类的近似加权核k-means算法[J]. 软件学报，2015，26(11)：2836-2846.
[27]ESTEVES R M，HACKER T，RONG C. Cluster analysis for the cloud: Parallel competitive fitness and parallel k-means++ for large dataset analysis[C]//IEEE. 4th IEEE international conference on cloud computing technology and science proceedings. Taipei:IEEE,2012：177-184.
[28]NIU K，GAO Z，JIAO H，et al. k-means+：A developed clustering algorithm for big data[C]//CCIS. 4th international conference on cloud computing and intelligence systems(CCIS). Beijing:CCIS，2016：141-144.
[29]GADDAM S R, PHOHA V V，BALAGANI K S. k-means+ID3：A novel method for supervised anomaly detection by cascading K-means clustering and ID3 decision tree learning methods[J]. IEEE Transactions on Knowledge and Data Engineering，2007，19(3)：345-354.
[30]NA S，XUMIN L，YONG G. Research on k-means clustering algorithm: An improved k-means clustering algorithm[C]//IEEE. 2010 third international symposium on intelligent information technology and security informatics. Jinggangshan: IEEE, 2010：63-67.
[31]YANG Q，LIU Y，ZHANG D，et al. Improved k-means algorithm to quickly locate optimum initial clustering number K[C]//IEEE. Proceedings of the 30th chinese control conference. Yantai:IEEE, 2011： 3319-3322.
[32]GUANG-PING C，WEN-PENG W. An improved k-means algorithm with meliorated initial center[C]//ICCSE. 7th international conference on computer science & education. Melbourne，VIC:ICCSE, 2012：150-153.
[33]LIU G L，WANG T T，YU L M，et al. The improved research on k-means clustering algorithm in initial values[C]//IEEE. Proceedings 2013 international conference on mechatronic sciences, electric engineering and computer. Shengyang:IEEE，2013：2124-2127.
[34]朱淑鑫，杨宸，顾兴健，等. K均值算法结合连续投影算法应用于土壤速效钾含量的高光谱分析[J]. 江苏农业学报，2020,36(2):358-365.
[35]BACHEM O, LUCIC M, HASSANI S H, et al. Approximate k-means++ in sublinear time[C]//AAAI. Proceedings of the thirtieth AAAI conference on artificial intelligence. Phoenix，Arizona，USA:AAAI，2016: 1459-1467.
[36]BACHEM O，LUCIC M，HASSANI H，et al. Fast and provably good seedings for k-means[C]//NIPS. 30th conference on neural information processing systems. Barcelona，Spain:NIPS，2016：55-63.
[37]CELEBI M E, KINGRAVI H A, VELA P A. A comparative study of efficient initialization methods for the k-means clustering algorithm[J]. Expert Systems with Applications，2013，40(1)：200-210.

相似文献/References:

[1]胡维炜,张武,刘连忠,等.利用图像处理技术计算大豆叶片相对病斑面积[J].江苏农业学报,2016,(04):774.[doi:10.3969/j.issn.100-4440.2016.04.010]
　HU Wei-wei,ZHANG Wu,LIU Lian-zhong,et al.Measurement of relative lesion area on soybean leaf using image processing technology[J].,2016,(06):774.[doi:10.3969/j.issn.100-4440.2016.04.010]
[2]车金庆,王帆,王艺洁,等.基于视觉注意机制的黄绿色苹果图像分割[J].江苏农业学报,2018,(06):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
　CHE Jin-qing,WANG Fan,WANG Yi-jie,et al.A segmentation method of yellow and green apple images based on visual attention mechanism[J].,2018,(06):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
[3]王振,张善文,王献锋.基于改进全卷积神经网络的黄瓜叶部病斑分割方法[J].江苏农业学报,2019,(05):1054.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
　WANG Zhen,ZHANG Shan-wen,WANG Xian-feng.Method for segmentation of cucumber leaf lesions based on improved full convolution neural network[J].,2019,(06):1054.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
[4]雷旺雄,卢军.葡萄采摘机器人采摘点的视觉定位[J].江苏农业学报,2020,(04):1015.[doi:doi:10.3969/j.issn.1000-4440.2020.04.029]
　LEI Wang-xiong,LU Jun.Visual positioning method for picking point of grape picking robot[J].,2020,(06):1015.[doi:doi:10.3969/j.issn.1000-4440.2020.04.029]
[5]刘连忠,李孟杰,宁井铭.基于改进SLIC的光照干扰下茶树冠层图像分割[J].江苏农业学报,2020,(04):1022.[doi:doi:10.3969/j.issn.1000-4440.2020.04.030]
　LIU Lian-zhong,LI Meng-jie,NING Jing-ming.Segmentation of tea plant canopy image under light interference based on improved SLIC[J].,2020,(06):1022.[doi:doi:10.3969/j.issn.1000-4440.2020.04.030]
[6]魏超宇,韩文,庞程,等.基于多尺度特征融合和密集连接网络的疏果期黄花梨植株图像分割[J].江苏农业学报,2021,(04):990.[doi:doi:10.3969/j.issn.1000-4440.2021.04.023]
　WEI Chao-yu,HAN Wen,PANG Cheng,et al.Image segmentation of Huanghua pear plants at fruit-thinning stage based on multi-scale feature fusion and dense connection network[J].,2021,(06):990.[doi:doi:10.3969/j.issn.1000-4440.2021.04.023]
[7]王万亮,江高飞,严江伟,等.基于卷积评价及对抗网络的花粉、孢子图像增广算法[J].江苏农业学报,2021,(05):1190.[doi:doi:10.3969/j.issn.1000-4440.2021.05.014]
　WANG Wan-liang,JIANG Gao-fei,YAN Jiang-wei,et al.Augmented algorithm for pollen and spore images based on convolution evaluation and pix2pix network[J].,2021,(06):1190.[doi:doi:10.3969/j.issn.1000-4440.2021.05.014]
[8]马立新,夏利利,刘璎瑛,等.基于图像处理的秧苗均匀度合格率检测[J].江苏农业学报,2022,38(02):387.[doi:doi:10.3969/j.issn.1000-4440.2022.02.012]
　MA Li-xin,XIA Li-li,LIU Ying-ying,et al.Seedling uniformity detection based on image processing[J].,2022,38(06):387.[doi:doi:10.3969/j.issn.1000-4440.2022.02.012]
[9]许鑫,耿庆,郑凯,等.基于纹理特征与深度学习的小麦图像中的穗粒分割与计数[J].江苏农业学报,2024,(04):661.[doi:doi:10.3969/j.issn.1000-4440.2024.04.010]
　XU Xin,GENG Qing,ZHENG Kai,et al.Segmentation and counting of wheat spikes and grains based on texture features and deep learning[J].,2024,(06):661.[doi:doi:10.3969/j.issn.1000-4440.2024.04.010]

备注/Memo

备注/Memo:
收稿日期：2021-05-07基金项目：国家重点研发计划项目 ( 2016YFD0702100 )；国家自然科学地区基金项目( 61863011)；广东省普通高校特色创新项目(2020KTSCX142)；中国农业科学院基本科研业务费专项(SR201919)作者简介：陈科尹( 1982-) ，男，广东雷州人，博士，讲师，从事农业图像处理、机器视觉方面研究。(E-mail) chenkeyin10@126.com通讯作者：吴崇友，(E-mail)542681935@ qq com
更新日期/Last Update: 2022-01-07