基于超像素分割的田间小麦穗数统计方法

doi:10.3864/j.issn.0578-1752.2019.01.003

中国农业科学 ›› 2019, Vol. 52 ›› Issue (1): 21-33.doi: 10.3864/j.issn.0578-1752.2019.01.003

• 耕作栽培·生理生化·农业信息技术 • 上一篇下一篇

基于超像素分割的田间小麦穗数统计方法

杜颖^1,²(),蔡义承¹(),谭昌伟¹(),李振海²,杨贵军²,冯海宽²,韩东²

1江苏省粮食作物现代产业技术协同创新中心/江苏省作物遗传生理国家重点实验室培育点/教育部农业与农产品安全国际合作联合实验室/扬州大学农业科技发展研究院,江苏扬州 225009
2农业部农业遥感机理与定量遥感重点实验室/北京农业信息技术研究中心,北京 100097

收稿日期:2018-08-25 接受日期:2018-09-28 出版日期:2019-01-01 发布日期:2019-01-12
通讯作者: 谭昌伟
基金资助:
国家重点研发计划(2016YFD0300405);江苏高校优势学科建设工程资助项目(PAPD);江苏高校品牌专业建设工程资助项目(PPZY2015A060);国家自然科学基金(31771711);国家自然科学基金(61661136003);扬州大学教学改革研究课题(YZUJX2017-22B)

Field Wheat Ears Counting Based on Superpixel Segmentation Method

DU Ying^1,²(),CAI YiCheng¹(),TAN ChangWei¹(),LI ZhenHai²,YANG GuiJun²,FENG HaiKuan²,HAN Dong²

1 Jiangsu Provincial Collaborative Innovation Center of Modern Crop Science and Technology/National Key Laboratory of Crop Genetics and Physiology of Jiangsu Province/Joint Laboratory of International Cooperation on Agriculture and Agricultural Safety of Ministry of Education/Institute of Agricultural Science and Technology Development, Yangzhou University, Yangzhou 225009, Jiangsu
2 Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture/Beijing Research Center for Information Technology in Agriculture, Beijing 100097

Received:2018-08-25 Accepted:2018-09-28 Online:2019-01-01 Published:2019-01-12
Contact: ChangWei TAN

摘要/Abstract

摘要：

【目的】小麦穗数是产量构成的重要因素。通过图像处理技术快速准确地统计小麦穗数,为作物长势监测和产量估测提供重要依据。【方法】本研究以经氮肥梯度处理后不同长势的小麦为研究对象,首先,通过简单线性迭代聚类算法（simple linear iterative cluster,SLIC）对田间小麦图像进行超像素分割的预处理;提取并分析图像的部分颜色特征参数,选择适宜的颜色特征参数训练分类器;选择准确率最高的分类器对图像进行分类处理,识别麦穗。其次,对麦穗识别结果进行二值化;经腐蚀、膨胀等一系列形态学计算提取麦穗主体并进行区域统计;提取麦穗骨架,检测骨架角点数,结合角点数与区域统计结果计算小麦穗数;最后,通过线性回归分析方法验证了无氮（0）、低氮（1/2常规施氮量）、正常氮（常规施氮量）、高氮（2倍的常规施氮量）4个氮水平麦穗统计结果。【结果】（1）利用超绿值（E_g）和归一化红绿指数（D_gr）作为分类特征可以有效地识别麦穗、土壤和叶片;（2）相较于直接基于像素进行图像处理,经超像素分割处理后麦穗识别结果更理想,识别出麦穗主体清晰,形态更为完整;（3）经比较,高氮水平下小麦长势较好,穗数统计准确率最高,为94.4%,无氮水平下小麦长势较差,穗数统计准确率最低,仅为81.9%;排除无氮情况后,长势较均匀的氮水平混合样本中麦穗计数准确率达到92.9%,相较于长势差异较大的混合样本准确率提高了8.3%。【结果】在一般环境下,利用超像素和颜色特征的麦穗自动统计方法可以快速准确地对大田小麦进行穗数计算,长势过弱以及差异过大区域不推荐使用,研究结果为小麦大田估产提供了新的参考。

关键词: 小麦, 识别, 穗数, 超像素, 颜色特征

Abstract:

【Objective】Wheat ears number is a major factor of yield composition and plays an important role in yield estimation and genetic improvement. Using image processing technology to accurately identify and count wheat ears in the field, a new method for obtaining agricultural information was proposed in this paper, which provided a reliable reference for the yield estimation and crop growth monitoring. 【Method】In this paper, wheat with different growth conditions after treatment with nitrogen fertilizer gradient was the research object. Firstly, the simple linear iterative cluster (SLIC) was used to segment the wheat image, and the unit of an image was transformed from pixels to superpixel block. After analyzing the color histograms, the classifiers were trained to identify wheat ears. Then, we performed a simple morphological treatment on the classification results to segment the wheat ears and performed binarization. We obtained the main body of wheat and conducted regional statistics through a series of morphological calculations, such as corrosion and expansion. The wheat ear skeleton was extracted to detect the skeleton corner points to calculate the number of wheat ears. Lastly, the results of counting wheat ears under different nitrogen levels (no nitrogen, low nitrogen, normal nitrogen, high nitrogen) were verified by linear regression analysis. 【Result】 (1) Super green value (Eg) and normalized red green index (Dgr) could be used as classification features to effectively identify wheat ears after color histogram analysis. (2) Compared to directly identifying the field image, the main body of wheat identified after superpixel segmentation was more explicit and complete in shape. (3) By comparison, wheat with better growth situation had better ear counting results, which approached 94.4% in high nitrogen level. However, the wheat ear count accuracy was low at a poor nitrogen level, which was only 81.9%. After eliminating the nitrogen-free condition, the overall growth of the mixed sample was uniform, and the wheat ear count accuracy reached 92.9%. The accuracy was improved by 8.3% compared to mixed samples with large differences in growth.【Conclusion】In the general environment, the automatic counting method of wheat ears using superpixels and color features could quickly and accurately calculate the number of wheat ears in field. While the growth vigor was too weak and the difference was too large, this method was not recommended. The research results provided a new reference for wheat field estimation.

Key words: wheat, identification, ear number, superpixel, color characteristics

杜颖,蔡义承,谭昌伟,李振海,杨贵军,冯海宽,韩东. 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.

DU Ying,CAI YiCheng,TAN ChangWei,LI ZhenHai,YANG GuiJun,FENG HaiKuan,HAN Dong. Field Wheat Ears Counting Based on Superpixel Segmentation Method[J]. Scientia Agricultura Sinica, 2019, 52(1): 21-33.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2019.01.003

https://www.chinaagrisci.com/CN/Y2019/V52/I1/21

图/表 11

图1

图2

图3

表1

不同类型分类器特征"

分类器类型 Classifier type	预测速度 Prediction speed	内存占用 Memory usage	解释性 Interpretability	模型灵活性 Model flexibility
线性支持向量机 linSVM	二分类：快 Binary: Fast 多分类：中 Multiclass: Medium	中等 Medium	简单 Easy	低 Low 在类之间进行简单的线性分隔 Makes a simple linear separation between classes
二次多项式支持向量机 quaSVM	二分类：快 Binary: Fast 多分类：慢 Multiclass: Slow	二分类：中等 Binary: Medium 多分类：大 Multiclass: Large	困难 Hard	中等 Medium
三次多项式支持向量机 cubSVM	二分类：快 Binary: Fast 多分类：慢 Multiclass: Slow	二分类：中等 Binary: Medium 多分类：大 Multiclass: Large	困难 Hard	中等 Medium
细高斯支持向量机 finGSVM	二分类：快 Binary: Fast 多分类：慢 Multiclass: Slow	二分类：中等 Binary: Medium 多分类：大 Multiclass: Large	困难 Hard	高,随内核刻度设置而减小 High, creases with kernel scale setting 类之间精细区分,内核刻度为sqrt(P)/4 Makes finely detailed distinctions between classes, with kernel scale set to sqrt(P)/4
中度高斯支持向量机 medGSVM	二分类：快 Binary: Fast 多分类：慢 Multiclass: Slow	二分类：中等 Binary: Medium 多分类：大 Multiclass: Large	困难 Hard	中等 Medium 中度区分,内核刻度为sqrt(P) Medium distinctions, with kernel scale set to sqrt(P)
粗高斯支持向量机 coaGSVM	二分类：快 Binary: Fast 多分类：慢 Multiclass: Slow	二分类：中等 Binary: Medium 多分类：大 Multiclass: Large	困难 Hard	低 Low 在类之间粗区分,内核刻度为sqrt(P)4,其中P为预测因子数 Makes coarse distinctions between classes, with kernel scale set to sqrt(P)4, where P is the number of predictors
细 K最近邻 finKNN	中 Medium	中等 Medium	困难 Hard	类之间细微差异区分,邻域数设为1 Finely detailed distinctions between classes. The number of neighbors is set to 1
中度 K最近邻 medKNN	中 Medium	中等 Medium	困难 Hard	类之间中等差异区分,邻域数设为10 Medium distinctions between classes. The number of neighbors is set to 10
粗 K最近邻 coaKNN	中 Medium	中等 Medium	困难 Hard	类之间粗略差异区分,邻域数设为100 Coarse distinctions between classes. The number of neighbors is set to 100
余弦 K最近邻 cosKNN	中 Medium	中等 Medium	困难 Hard	使用余弦距离度量,在类之间中等区分,邻域数设为10 Medium distinctions between classes, using a cosine distance metric. The number of neighbors is set to 10
三次多项式 K最近邻 cubKNN	慢 Slow	中等 Medium	困难 Hard	使用立方距离度量,在类之间中等区分,邻域数设为10 Medium distinctions between classes, using a cubic distance metric. The number of neighbors is set to 10
加权 K最近邻 weiKNN	中 Medium	中等 Medium	困难 Hard	使用权重距离度量,在类之间中等区分,邻域数设为10 Medium distinctions between classes, using a distance weight. The number of neighbors is set to 10

表1

图4

图5

图6

表2

图7

表3

图8

参考文献 37

[1]	田纪春, 邓志英, 胡瑞波, 王延训 . 不同类型超级小麦产量构成因素及籽粒产量的通径分析. 作物学报, 2006,32(11):1699-1705. doi: 10.3321/j.issn:0496-3490.2006.11.017
	TIAN J C, DENG Z Y, HU R B, WANG Y X . Yield components of super wheat cultivars with different types and the path coefficient analysis on grain yield. Acta Agronomica Sincia, 2006,32(11):1699-1705. (in Chinese) doi: 10.3321/j.issn:0496-3490.2006.11.017
[2]	方正, 邵锡珍, 李云海 . 从小麦的超高产实践谈良种选育的问题. 作物杂志, 1999(1):20-21.
	FANG Z, SHAO X Z, LI Y H . Discussion on the breeding of fine varieties from the super high yield practice in wheat. Crops, 1999(1):20-21. (in Chinese)
[3]	KONG W W, ZHANG C, HUANG W H, LIU F, HE Y . Application of hyperspectral imaging to detect sclerotinia sclerotiorum on oilseed rape stems. Sensors, 2018,18(1):123. doi: 10.3390/s18010123 pmid: 29300315
[4]	李小龙, 王库, 马占鸿, 王海光 . 基于热红外成像技术的小麦病害早期检测. 农业工程学报, 2014,30(18):183-189. doi: 10.3969/j.issn.1002-6819.2014.18.023
	LI X L, WANG K, MA Z H, WANG H G . Early detection of wheat disease based on thermal infrared imaging. Transactions of the Chinese Society of Agricultural Engineering, 2014,30(18):183-89. (in Chinese) doi: 10.3969/j.issn.1002-6819.2014.18.023
[5]	鲁军景, 黄文江, 张竞成, 蒋金豹 . 基于小波特征的小麦白粉病与条锈病的定量识别. 光谱学与光谱分析, 2016,36(6):1854-1858.
	LU J J, HUANG W J, ZHANG J C, JIANG J B . Quantitative identification of yellow rust and powdery mildew in winter wheat based on wavelet feature. Spectroscopy and Spectral Analysis, 2016,36(6):1854-1858. (in Chinese)
[6]	谭昌伟, 杜颖, 童璐, 周健, 罗明, 严伟伟, 陈菲 . 基于开花期卫星遥感数据的大田小麦估产方法比较. 中国农业科学, 2017,50(16):3101-3109. doi: 10.3864/j.issn.0578-1752.2017.16.005
	TAN C W, DU Y, TONG L, ZHOU J, LUO M, YAN W W, CHEN F . Comparison of the methods for predicting wheat yield based on satellite remote sensing data at anthesis. Scientia Agricultura Sinica, 2017,50(16):3101-3109. (in Chinese) doi: 10.3864/j.issn.0578-1752.2017.16.005
[7]	GUO J X, TIAN G L, ZHOU Y, WANG M, LING N, SHEN Q R, GUO S W . Evaluation of the grain yield and nitrogen nutrient status of wheat (Triticum aestivum L.) using thermal imaging. Field Crops Research, 2016,196:463-472. doi: 10.1016/j.fcr.2016.08.008
[8]	OMAR V D, MAINASSARA Z A, BENHILDAH M, ALBERTO H, PABLO Z T, BODDUPALLI M P, JILL E C, JOSE L A . A novel remote sensing approach for prediction of maize yield under different conditions of nitrogen fertilization. Frontiers in Plant Science, 2016,7:666. doi: 10.3389/fpls.2016.00666 pmid: 4870241
[9]	于仁师, 孙华丽, 韩仲志 . 玉米品种识别多算法模型比较研究. 湖北农业科学, 2016,55(9):2366-2369. doi: 10.14088/j.cnki.issn0439-8114.2016.09.055
	YU R S, SUN H L, HAN Z Z . A comparative study of multi-algorithm for maize varieties identification. Hubei Agricultural Sciences, 2016,55(9):2366-2369. (in Chinese) doi: 10.14088/j.cnki.issn0439-8114.2016.09.055
[10]	马惠玲, 王若琳, 蔡骋, 王栋 . 基于高光谱成像的苹果品种快速鉴别. 农业机械学报, 2017,48(4):305-312. doi: 10.6041/j.issn.1000-1298.2017.04.040
	MA H L, WANG R L, CAI C, WANG D . Rapid identification of apple varieties based on hyperspectral imaging. Transactions of the Chinese Society for Agricultural Machinery, 2017,48(4):305-312. (in Chinese) doi: 10.6041/j.issn.1000-1298.2017.04.040
[11]	毕立恒 . 基于叶片图像算法的植物种类识别方法研究. 浙江农业学报, 2017,29(12):2142-2148.
	BI L H . Plant species recognition based on leaf image algorithm. Acta Agriculturae Zhejiangensis, 2017,29(12):2142-2148. (in Chinese)
[12]	JIN X L, LIU S Y, FREDERIC B, COMAR A . Estimates of plant density of wheat crops at emergence from very low altitude UAV imagery. Remote Sensing of Environment, 2017,198:105-114. doi: 10.1016/j.rse.2017.06.007
[13]	WALTER J, EDWARDS J, MCDONALD G, KUCHEL H . Photogrammetry for the estimation of wheat biomass and harvest index. Field Crops Research, 2018,216:165-174. doi: 10.1016/j.fcr.2017.11.024
[14]	陈含, 吕行军, 田凤珍, 王克俭, 韩宪忠 . 基于Sobel算子边缘检测的麦穗图像分割. 农机化研究, 2013(3):33-36. doi: 10.3969/j.issn.1003-188X.2013.03.007
	CHEN H, LÜ X J, TIAN F Z, WANG K J, HAN X Z . Wheat panicle image segmentation based on sobel operator–edge detection.Journal of Agricultural Mechanization Research, 2013(3):33-36. (in Chinese) doi: 10.3969/j.issn.1003-188X.2013.03.007
[15]	LI Q, CAI J, BERGER B, OKAMOTO M, MIKLAVCIC S J . Detecting spikes of wheat plants using neural networks with laws texture energy. Plant Methods, 2017,13(1):83. doi: 10.1186/s13007-017-0231-1
[16]	路文超, 罗斌, 潘大宇, 于春花, 王成 . 基于图像处理的小麦穗长和小穗数同步测量. 中国农机化学报, 2016,37(6):210-215. doi: 10.13733/j.jcam.issn.2095-5553.2016.06.46
	LU W C, LUO B, PAN D Y, YU C H, WANG C . Synchronous measurement of wheat ear length and spikelets number based on image processing. Journal of Chinese Agricultural Mechanization, 2016,37(6):210-215. (in Chinese) doi: 10.13733/j.jcam.issn.2095-5553.2016.06.46
[17]	王宁, 孔斌, 王灿, 何立新, 李伟, 徐海明 . 基于图像分形分割的麦穗粒数计算方法. 计算机系统应用, 2017,26(10):219-224. doi: 10.15888/j.cnki.csa.006030
	WANG N, KONG B, WANG C, HE L X, LI W, XU H M . Counting grains per wheat spike based on fractal segmentation of image. Computer Systems & Applications, 2017,26(10):219-224. (in Chinese) doi: 10.15888/j.cnki.csa.006030
[18]	刘涛, 孙成明, 王力坚, 仲晓春, 朱新开, 郭文善 . 基于图像处理技术的大田麦穗计数. 农业机械学报, 2014,45(2):282-290. doi: 10.6041/j.issn.1000-1298.2014.02.047
	LIU T, SUN C M, WANG L J, ZHONG X C, ZHU X K, GUO W S . In-field wheatear counting based on image processing technology. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(2):282-290. (in Chinese) doi: 10.6041/j.issn.1000-1298.2014.02.047
[19]	FERNANDEZGALLEGO J A, KEFAUVER S C , GUTIÉRREZ N A, NIETOTALADRIZ M T, ARAUS J L. Wheat ear counting in-field conditions: High throughput and low-cost approach using RGB images. Plant Methods, 2018,14(1):22. doi: 10.1186/s13007-018-0289-4
[20]	ACHANTA R, SHAJI A, SMITH K, LUCCHI A, FUA P , SÜSSTRUNK S. SLIC Superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2274-2282. doi: 10.1109/TPAMI.2012.120 pmid: 22641706
[21]	赵博, 宋正河, 毛文华, 毛恩荣, 张小超 . 基于PSO与K-均值算法的农业超绿图像分割方法. 农业机械学报, 2009,40(8):166-169.
	ZHAO B, SONG Z H, MAO W H, MAO E R, ZHANG X C . Agriculture extra-green image segmentation based on particle swarm optimization and K-means clustering. Transactions of the Chinese Society for Agricultural Machinery, 2009,40(8):166-169. (in Chinese)
[22]	STAJNKO D, LAKOTA M, HOCEVAR M . Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging. Computers & Electronics in Agriculture, 2004,42(1):31-42. doi: 10.1016/S0168-1699(03)00086-3
[23]	XUE C, MA J, QIAO H, YUAN F . The take-all of wheat diseases feature extraction method study using ground spectral measurement data and tm multispectral data//International Geoscience and Remote Sensing Symposium. IEEE, Boston, 2008: 320-322. doi: 10.1109/IGARSS.2008.4778858
[24]	颜七笙, 王士同 . 一种基于调节形态学的骨架提取算法. 计算机应用与软件, 2006,23(3):116-117. doi: 10.3969/j.issn.1000-386X.2006.03.044
	YAN Q S, WANG S T . A new skeletonization algorithm based on regulated morphology. Computer Applications and Software, 2006,23(3):116-117. (in Chinese) doi: 10.3969/j.issn.1000-386X.2006.03.044
[25]	杨志平, 齐清文, 黄仁涛 . 数学形态学在空间格局图像骨架提取中的应用. 地球信息科学, 2003,5(2):79-83. doi: 10.3969/j.issn.1560-8999.2003.02.021
	YANG Z P, QI Q W, HUANG R T . Application of mathematical morphology in the skeleton extraction of spatial pattern image. Geo-Information Science, 2003,5(2):79-83. (in Chinese) doi: 10.3969/j.issn.1560-8999.2003.02.021
[26]	尚振宏, 刘明业 . 二值图像中拐点的实时检测算法. 中国图像图形学报, 2005,10(3):295-300. doi: 10.11834/jig.20050357
	SHANG Z H, LIU M Y . Real-time corner detection in binary image. Journal of Image and Graphics, 2005,10(3):295-300. (in Chinese) doi: 10.11834/jig.20050357
[27]	MUKHERJEE D , WU Q M J, WANG G H. A comparative experimental study of image feature detectors and descriptors. Machine Vision & Applications, 2015,26(4):443-466. doi: 10.1007/s00138-015-0679-9
[28]	CHANG M Z, GU G C, LIU H B, SHEN J, YU H L . Segmentation of ultrasound image based on texture feature and graph cut. Computer Science and Software Engineering, IEEE, Hubei, 2008: 795-798. doi: 10.1109/CSSE.2008.294
[29]	TAN W M, YAN B, LI K, TIAN Q . Image retargeting for preserving robust local feature: application to mobile visual search. IEEE Transactions on Multimedia, 2015,18(1):128-137. doi: 10.1109/TMM.2015.2500727
[30]	ZHOU C Q, LIANG D, YANG X D, XU B, YANG G J . Recognition of wheat spike from field based phenotype platform using multi-sensor fusion and improved maximum entropy segmentation algorithms. Remote Sensing, 2018,10(2):246-269. doi: 10.3390/rs10020246
[31]	ZHANG Y X, LI X M, GAO X F, ZHANG C M . A simple algorithm of superpixel segmentation with boundary constraint. IEEE Transactions on Circuits & Systems for Video Technology, 2017,27(7):1502-1514. doi: 10.1109/TCSVT.2016.2539839
[32]	宋熙煜, 周利莉, 李中国, 陈健, 曾磊, 闫镔 . 图像分割中的超像素方法研究综述. 中国图象图形学报, 2015,20(5):599-608. doi: 10.11834/jig.20150502
	SONG X Y, ZHOU L L, LI Z G, CHEN J, ZENG L, YAN B . Review on superpixel methods in image segmentation. Journal of Image and Graphics, 2015,20(5):599-608. (in Chinese) doi: 10.11834/jig.20150502
[33]	SHU G, DEHGHAN A, SHAH M . Improving an object detector and extracting regions using superpixels. Computer Vision and Pattern Recognition, IEEE, Portland, 2013: 3721-3727. doi: 10.1109/CVPR.2013.477
[34]	WANG J, WANG X Q . VCells: simple and efficient superpixels using edge-weighted centroidal voronoi tessellations. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2012,34(6):1241-1247. doi: 10.1109/TPAMI.2012.47 pmid: 22331852
[35]	XIONG X, DUAN L F, LIU L B, TU H F, YANG P, WU D, CHEN G X, XIONG L Z, YANG W N, LIU Q . Panicle-SEG: A robust image segmentation method for rice panicles in the field based on deep learning and superpixel optimization. Plant Methods, 2017,13(1):104-118. doi: 10.1186/s13007-017-0254-7 pmid: 5704426
[36]	张小艳, 李强 . 基于SVM的分类方法综述. 科技信息, 2008(28):350-351. doi: 10.3969/j.issn.1001-9960.2008.28.285
	ZHANG X Y, LI Q . The summary of text classification based on support vector machines.Science & Technology Information, 2008(28):350-351. (in Chinese) doi: 10.3969/j.issn.1001-9960.2008.28.285
[37]	PEREIRA T, PAIVA J S, CORREI C, CARDOSO J . An automatic method for arterial pulse waveform recognition using KNN and SVM classifiers. Medical & Biological Engineering & Computing, 2016,54(7):1049-1059. doi: 10.1007/s11517-015-1393-5 pmid: 26403299

分类器类型 Classifier type	氮水平 Nitrogen level
分类器类型 Classifier type	N1	N2	N3	N4	混合 Mix
linSVM	81.2	86.2	90.1	90.9	85.1
quaSVM	86.1	89.7	91.9	92.8	87.6
cubSVM	86.6	89.5	92.2	93.8	56.8
finGSVM	84.9	92.6	90.7	93.1	88.2
medGSVM	87.2	90.5	93.5	92.7	88.2
coaGSVM	82.4	87.0	90.6	90.8	86.3
finKNN	85.0	89.5	87.0	92.3	85.2
medKNN	85.8	89.9	92.3	93.0	85.2
coaKNN	83.4	88.4	90.8	90.9	87.2
cosKNN	84.8	89.4	91.1	93.0	87.1
cubKNN	85.5	89.8	92.0	91.4	87.1
weiKNN	86.4	91.1	92.1	92.2	88.2

分类器类型 Classifier type	总体准确率 Overall accuracy (%)	穗部准确率 Ear accuracy (%)	背景准确率 Background accuracy (%)
linSVM	87.1	88.0	86.0
quaSVM	89.2	91.0	87.0
cubSVM	84.0	77.0	91.0
finGSVM	89.2	89.0	90.0
medGSVM	89.5	91.0	88.0
coaGSVM	88.0	90.0	86.0
finKNN	87.4	87.0	87.0
medKNN	89.4	90.0	89.0
coaKNN	89.1	93.0	86.0
cosKNN	88.8	88.0	90.0
cubKNN	88.9	89.0	88.0
weiKNN	90.2	93.0	88.0

基于超像素分割的田间小麦穗数统计方法

Field Wheat Ears Counting Based on Superpixel Segmentation Method

RichHTML

PDF

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 37

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	陈吉浩, 周界光, 曲翔汝, 王素容, 唐华苹, 蒋云, 唐力为, $\boxed{\hbox{兰秀锦}}$, 魏育明, 周景忠, 马建. 四倍体小麦胚大小性状QTL定位与分析[J]. 中国农业科学, 2023, 56(2): 203-216.
[2]	严艳鸽, 张水勤, 李燕婷, 赵秉强, 袁亮. 葡聚糖改性尿素对冬小麦产量和肥料氮去向的影响[J]. 中国农业科学, 2023, 56(2): 287-299.
[3]	徐久凯, 袁亮, 温延臣, 张水勤, 李燕婷, 李海燕, 赵秉强. 畜禽有机肥氮在冬小麦季对化肥氮的相对替代当量[J]. 中国农业科学, 2023, 56(2): 300-313.
[4]	古丽旦,刘洋,李方向,成卫宁. 小麦吸浆虫小热激蛋白基因Hsp21.9的克隆及在滞育过程与温度胁迫下的表达特性[J]. 中国农业科学, 2023, 56(1): 79-89.
[5]	王浩琳,马悦,李永华,李超,赵明琴,苑爱静,邱炜红,何刚,石美,王朝辉. 基于小麦产量与籽粒锰含量的磷肥优化管理[J]. 中国农业科学, 2022, 55(9): 1800-1810.
[6]	唐华苹,陈黄鑫,李聪,苟璐璐,谭翠,牟杨,唐力为,兰秀锦,魏育明,马建. 基于55K SNP芯片的普通小麦穗长非条件和条件QTL分析[J]. 中国农业科学, 2022, 55(8): 1492-1502.
[7]	马小艳,杨瑜,黄冬琳,王朝辉,高亚军,李永刚,吕辉. 小麦化肥减施与不同轮作方式的周年养分平衡及经济效益分析[J]. 中国农业科学, 2022, 55(8): 1589-1603.
[8]	刘硕,张慧,高志源,许吉利,田汇. 437个小麦品种钾收获指数的变异特征[J]. 中国农业科学, 2022, 55(7): 1284-1300.
[9]	王洋洋,刘万代,贺利,任德超,段剑钊,胡新,郭天财,王永华,冯伟. 基于多元统计分析的小麦低温冻害评价及水分效应差异研究[J]. 中国农业科学, 2022, 55(7): 1301-1318.
[10]	职蕾,者理,孙楠楠,杨阳,Dauren Serikbay,贾汉忠,胡银岗,陈亮. 小麦苗期铅耐受性的全基因组关联分析[J]. 中国农业科学, 2022, 55(6): 1064-1081.
[11]	秦羽青,程宏波,柴雨葳,马建涛,李瑞,李亚伟,常磊,柴守玺. 中国北方地区小麦覆盖栽培增产效应的荟萃（Meta）分析[J]. 中国农业科学, 2022, 55(6): 1095-1109.
[12]	蔡苇荻,张羽,刘海燕,郑恒彪,程涛,田永超,朱艳,曹卫星,姚霞. 基于成像高光谱的小麦冠层白粉病早期监测方法[J]. 中国农业科学, 2022, 55(6): 1110-1126.
[13]	宗成, 吴金鑫, 朱九刚, 董志浩, 李君风, 邵涛, 刘秦华. 添加剂对农副产物和小麦秸秆混合青贮发酵品质的影响[J]. 中国农业科学, 2022, 55(5): 1037-1046.
[14]	马鸿翔, 王永刚, 高玉姣, 何漪, 姜朋, 吴磊, 张旭. 小麦抗赤霉病育种回顾与展望[J]. 中国农业科学, 2022, 55(5): 837-855.
[15]	冯子恒,宋莉,张少华,井宇航,段剑钊,贺利,尹飞,冯伟. 基于无人机多光谱和热红外影像信息融合的小麦白粉病监测[J]. 中国农业科学, 2022, 55(5): 890-906.