The Nitrogen Content in Cotton Leaves: Estimation Based on Digital Image

doi:10.11924/j.issn.1000-6850.casb2021-0539

Abstract

Abstract:

In order to study the best image characteristic parameters and leaf position for diagnosing cotton nitrogen nutrition by digital image processing techniques, the cotton variety ‘Xinluzao53’ was used as the material, and the leaf images in different leaf positions were obtained by smartphone. The color and texture characteristic parameters of cotton leaf were extracted by digital image processing techniques, the correlation was analyzed between nitrogen content in leaves and characteristic parameters, and the estimation model of nitrogen contents was established based on different characteristic parameters. The results showed that the color characteristic parameters r, G/(B+R) and G/B, and texture characteristic parameters COR and ASM had good correlation with leaf nitrogen content, and the correlation coefficients (r) were all greater than 0.55. The estimation models of nitrogen contents in different leaf positions based on the color-texture comprehensive characteristic parameters were better than the models based on the color or texture characteristic parameters. Among them, the nitrogen content estimation model of the 4th leaf from the bottom was the best, the model determination coefficient (R ²) was 0.875, the root mean square error (RMSE) was 1.324, and the relative error (RE) was 8.09%. Therefore, when using digital image processing for cotton nitrogen nutrition diagnosis, the best image characteristic parameters should be selected as r, G/(B+R), G/B, COR, ASM, and the best leaf position should be the 4th leaf from the bottom.

Key words: cotton, digital image, nitrogen nutrition diagnosis, color characteristic parameters, texture characteristic parameters

CLC Number:

S562

HONG Bo, ZHANG Ze, ZHANG Qiang, MA Yiru, YI Xiang, LV Xin. The Nitrogen Content in Cotton Leaves: Estimation Based on Digital Image[J]. Chinese Agricultural Science Bulletin, 2022, 38(9): 49-55.

Figures/Tables 4

References 30

[1]	刘海俊, 孙传范, 王海, 等. 便携式作物氮素监测仪性能水稻田间测试[J]. 农业机械学报, 2010, 41(9):80-84.
[2]	李鹏程, 郑苍松, 李彦宏, 等. 国内棉花氮素营养诊断和施肥研究进展[J]. 中国棉花, 2019, 46(6):1-5.
[3]	LEE K J, LEE B W. Estimation of rice growth and nitrogen nutrition status using color digital camera image analysis[J]. European journal of agronomy, 2013, 48:57-65. doi: 10.1016/j.eja.2013.02.011 URL
[4]	陈敏, 郑曙峰, 刘小玲, 等. 基于数码图像识别的棉花氮营养诊断研究[J]. 农学学报, 2017, 7(7):77-83.
[5]	李小正, 谢瑞芝, 王克如, 等. 利用神经网络提取棉花叶片数字图像氮素含量的初步研究[J]. 作物学报, 2007, 33(10):1662-1666.
[6]	贾良良, 范明生, 张福锁, 等. 应用数码相机进行水稻氮营养诊断[J]. 光谱与光谱分析, 2009, 29(8):2176-2179.
[7]	李岚涛, 张萌, 任涛, 等. 应用数字图像技术进行水稻氮素营养诊断[J]. 植物营养与肥料学报, 2015, 21(1):259-268.
[8]	WANG Y, WANG D, ZHANG G, et al. Estimating nitrogen status ofrice using the image segmentation of G-R thresholding method[J]. Field crops research, 2013, 149:33-39. doi: 10.1016/j.fcr.2013.04.007 URL
[9]	SABERIOON M M, AMIN M S M, ANUAR A R, et al. Assessment of rice leaf chlorophyll content using visible bands at differentgrowth stages at both the leaf and canopy scale[J]. International journal of applied earth observation and geoinformation, 2014, 32:35-45. doi: 10.1016/j.jag.2014.03.018 URL
[10]	WANG Y, WANG D, SHI P, et al. Estimating rice chlorophyll content and leaf nitrogen concentration with a digital still color camer under natural light[J]. Plant methods, 2014, 10:6. doi: 10.1186/1746-4811-10-6 URL
[12]	SCHARF P C, LORY J A. Calibrating corn color from aerial photographs to predict sidedress nitrogen need[J]. Agronomy journal, 2002, 94(3):397-404. doi: 10.2134/agronj2002.3970 URL
[13]	刘颖, 李志洪, 王强, 等. 利用数字图像技术进行玉米氮素营养诊断的研究[J]. 玉米科学, 2010, 18(4):147-149.
[14]	刘洪见, 曾爱平, 郑丽敏, 等. 基于数字图像处理技术的玉米氮肥营养状态诊断[J]. 农业网络信息, 2007(12):31-35.
[15]	LI Y, CHEN D, WALKER C N, et al. Estimating the nitrogen status of crops using a digital camera[J]. Field crops research, 2010, 118(3):221-227. doi: 10.1016/j.fcr.2010.05.011 URL
[16]	刘飞, 王莉, 何勇, 等. 应用多光谱图像技术获取黄瓜叶片氮量及叶片及指数[J]. 光学学报, 2009, 29(6):1616-1620.
[17]	李连君, 李海华, 刘兰英, 等. 数字图像技术在草莓氮素营养诊断中的应用研究[J]. 华南农业大学学报, 2010, 31(2):19-21.
[18]	易时来, 邓烈, 何绍兰, 等. 应用多光谱图像技术进行锦橙叶片氮含量监测[J]. 植物营养与肥料学报, 2012, 18(1):176-181.
[19]	宋述尧, 王秀峰, 刘洋, 等. 数字图像技术在黄瓜氮素营养诊断上的应用研究[J]. 吉林农业大学学报, 2008, 30(4):460-465.
[20]	宋翠薇, 李恺. 基于Matlab的图像信号降噪技术研究[J]. 舰船电子工程, 2018, 38(2):90-93.57/5000.
[21]	OTSU N. A threshold selection method from gray level histograms[J]. IEEE Trans on SMC, 1979, 9(1):62-69.
[22]	孙俊, 武小红, 张晓东, 等. 基于MFICSC算法的生菜图像目标聚类分割[J]. 农业工程学报, 2012, 28(13):149-153.
[23]	陈刚. MATLAB在数字图像处理中的应用[M]. 北京: 清华大学出版社, 2016: 179-184.
[24]	ABBAS Z, REHMAN M, NAJAM S, et al. An efficient gray-level co-occurrence matrix (GLCM) based approach towards classification of skin lesion[C/OL]// 2019 Amity International Con-ference on Artificial Intelligence (AICAI). (2019-02-01) [2019-11-01]. New York: IEEE, 2019:317-320.
[25]	SETIAWAN A S, WESLEY J, PURNAMA Y. Mammogram classification using law's texture energy measure and neural networks[J]. Procedia computer science, 2015, 59:92-97. doi: 10.1016/j.procs.2015.07.341 URL
[26]	鲍士旦. 土壤农化分析[M]. 3版. 北京: 中国农业出版社, 2000:264-256.
[27]	魏全全, 刘海波, 王珂, 等. 基于数字图像技术的冬油菜氮素营养诊断[J]. 中国农业科学, 2015, 48(19):3877-3886.
[28]	陈佳悦, 姚霞, 李瑞, 等. 基于图像处理的冬小麦氮素监测模型[J]. 农业工程学报, 2016, 32(4):164-168.
[29]	刘伟, 毛树春, 李亚兵, 等. 基于颜色特征进行棉花叶片氮素含量的估测[J]. 中国棉花, 2007, 34(11):22-23.
[30]	王晓静, 张炎, 王华强, 等. 地面数字图像技术在棉花氮素营养诊断中的初步研究[J]. 棉花学报, 2007, 19(2):106-113.

叶位	变量类型	模型关系式	决定系数(R²)
倒1叶	颜色	N(%)=-989.1+1519.6x₁+713.7x₂+126.8x₃	0.756
	纹理	N(%)=-3256.2+53420.2x₄+26933.2x₅	0.702
	颜色+纹理	N(%)=-1047.6+1562.3x₁+733.8x₂+124.3x₃+319.9x₄+181.9x₅	0.768
倒2叶	颜色	N(%)=-683.4+1207.6x₁+164.2x₂+208.6x₃	0.634
	纹理	N(%)=- 2246.7+64372.9x₅	0.601
	颜色+纹理	N(%)=-684.7+1207.9x₁+164.3x₂+208.4x₃+36.2x₅	0.693
倒3叶	颜色	N(%)=-392.6+34.3x₁+608.5x₂+92.6x₃	0.667
	纹理	N(%)= -6751.4+48971.6x₄	0.518
	颜色+纹理	N(%)=-393.9+34.3x₁+608.5x₂+92.6 x₃+9.8x₄	0.670
倒4叶	颜色	N(%)=-453.3+157.4x₁+555.8x₂+140.1x₃	0.856
	纹理	N(%)=-3510.5+35350.1x₄+16537.3x₅	0.763
	颜色+纹理	N(%)=-459.1+157.6x₁+556.7x₂+139.6x₃+16.1x₄+36.3x₅	0.875

叶位	变量类型	模型关系式	决定系数(R²)
倒1叶	颜色	N(%)=-989.1+1519.6x₁+713.7x₂+126.8x₃	0.756
	纹理	N(%)=-3256.2+53420.2x₄+26933.2x₅	0.702
	颜色+纹理	N(%)=-1047.6+1562.3x₁+733.8x₂+124.3x₃+319.9x₄+181.9x₅	0.768
倒2叶	颜色	N(%)=-683.4+1207.6x₁+164.2x₂+208.6x₃	0.634
	纹理	N(%)=- 2246.7+64372.9x₅	0.601
	颜色+纹理	N(%)=-684.7+1207.9x₁+164.3x₂+208.4x₃+36.2x₅	0.693
倒3叶	颜色	N(%)=-392.6+34.3x₁+608.5x₂+92.6x₃	0.667
	纹理	N(%)= -6751.4+48971.6x₄	0.518
	颜色+纹理	N(%)=-393.9+34.3x₁+608.5x₂+92.6 x₃+9.8x₄	0.670
倒4叶	颜色	N(%)=-453.3+157.4x₁+555.8x₂+140.1x₃	0.856
	纹理	N(%)=-3510.5+35350.1x₄+16537.3x₅	0.763
	颜色+纹理	N(%)=-459.1+157.6x₁+556.7x₂+139.6x₃+16.1x₄+36.3x₅	0.875

[1]	MA Yuanhua, YIN Caixia, WANG Hongyu, LIU Yuxuan, LIU Qiantong, ZHANG Ze. Estimation Model of Cotton Leaf Phosphorus Content Based on Hyperspectral Reflectance [J]. Chinese Agricultural Science Bulletin, 2023, 39(1): 123-132.
[2]	ZHOU Xianlin, QIN Qin, MENG Yongming, WANG Long, HU Chengcheng, ZHU Haiyong, LAI Bo. Effects of Different Amendments on Saline-alkali Soil Improvement and Cotton Growth in Xinjiang [J]. Chinese Agricultural Science Bulletin, 2022, 38(34): 91-96.
[3]	GUO Yanyun, WANG Xuejiao, WANG Sen, HUO Xunguo, HU Qirui, JI Chunrong. Cotton Phenology in Xinjiang: The Response to Climate Change and Sensitivity Analysis [J]. Chinese Agricultural Science Bulletin, 2022, 38(18): 113-121.
[4]	YANG Weijun, HUI Chao, CHEN Yuxin, SONG Shilong, SHI Chunling, CHEN Lei. Effects of Continuous Cropping Years on Organic Carbon Distribution in Soil Aggregates in Cotton Fields [J]. Chinese Agricultural Science Bulletin, 2022, 38(13): 104-108.
[5]	XU Min, JIN Lulu, SUN Liyuan, LI Ruichun, WANG Zisheng. Cotton Chemical Defoliant: Application Effect in Liaohe Basin Cotton Area [J]. Chinese Agricultural Science Bulletin, 2022, 38(12): 47-54.
[6]	Yin Guo, Lu Zhengying, Sun Lu, Zhang Yanbo, Li Shiyun. Chromosome Ploidy Analysis and Interspecific Hybridization of Abelmoschus manihot [J]. Chinese Agricultural Science Bulletin, 2021, 37(9): 16-21.
[7]	Liu Xiaowei, He Wenqing, Li Zhiqiang, Li Shengtai, Lv Jun. Effects of Degradable Plastic Film on Agronomic Characters and Yield of Cotton in Shihezi Reclamation Area [J]. Chinese Agricultural Science Bulletin, 2021, 37(7): 24-27.
[8]	Zhao Xinxin, Chen Huanxuan, Han Yingchun, Li Yabing, Feng Lu. Crop Growth Monitoring with Digital Images: A Review [J]. Chinese Agricultural Science Bulletin, 2021, 37(4): 146-153.
[9]	Chen Min, Zheng Shufeng, Xu Daoqing, Liu Xiaoling, Wang Wei, Li Shuying, Kan Huachun. Effects of One-off Reduced Fertilization of Slow-release Fertilizer on Nitrogen Accumulation and Yield of Machine-picked Cotton [J]. Chinese Agricultural Science Bulletin, 2021, 37(4): 19-24.
[10]	Lou Hui, Zhao Zengqiang, Zhu Jincheng, Zhang Wei. Melatonin Under Low Temperature Stress: Effects on Germination Characteristics of Cotton Seeds [J]. Chinese Agricultural Science Bulletin, 2021, 37(35): 13-19.
[11]	Wang Qian, Li Ziyu, Liu Jianguo. Characteristics of Amino Sugar Accumulation in Long-term Continuous Cropping Soil of Cotton in Xinjiang Oasis [J]. Chinese Agricultural Science Bulletin, 2021, 37(30): 59-64.
[12]	Zhang Dongdong, Zhou Kanshe, Dai Rui, Yuan Lei, Wang Jiarui, Bian Duo. The Estimation Model of Fractional Vegetation Cover of Maize Based on the Real Image of Farmland [J]. Chinese Agricultural Science Bulletin, 2021, 37(29): 84-91.
[13]	Li Qi, Guo Wenlei, Meng Qi, Yu Jinping, Liu Yixue, Zhang Wei. Control Effect and Safety of Pendimethalin-pyroxasulfone 27% EC Against Annual Weeds in Cotton Field [J]. Chinese Agricultural Science Bulletin, 2021, 37(25): 121-124.
[14]	Ji Weishuai, Chen Hongyan, Wang Shuting, Zhang Yuting. Modeling Method of Cotton Leaves SPAD at Flowering and Boll Stage in North China Plain Based on UAV Multi-Spectrum [J]. Chinese Agricultural Science Bulletin, 2021, 37(22): 143-150.
[15]	Li Jiangfeng, Erhemaiti·Halike , Wang Daguang, Zhang Xiaolong, Li Jie, Lou Shanwei. Quality Change of Cotton Boll in Different Development Stages [J]. Chinese Agricultural Science Bulletin, 2021, 37(21): 15-19.