[1]李婕,李毅,张瑞杰,等.无人机遥感影像在油菜品种识别中的应用[J].江苏农业学报,2022,38(03):675-684.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
　LI Jie,LI Yi,ZHANG Rui-jie,et al.Application of UAV remote sensing image in rape variety identification[J].,2022,38(03):675-684.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
点击复制

无人机遥感影像在油菜品种识别中的应用()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
38
期数:
2022年03期
页码:
675-684
栏目:
农业信息工程
出版日期:
2022-06-30

文章信息/Info

Title:
Application of UAV remote sensing image in rape variety identification
作者:
李婕1; 李毅1; 张瑞杰2; 李俐俐2; 李礼2; 姚剑2; 乔江伟3
（1.湖北工业大学电气与电子工程学院，湖北武汉430068;2.武汉大学遥感信息工程学院，湖北武汉430070;3.中国农业科学院油料作物研究所，湖北武汉430062）
Author(s):
LI Jie1; LI Yi1; ZHANG Rui-jie2; LI Li-li2; LI Li2; YAO Jian2; QIAO Jiang-wei3
（1.School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China;2.School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430070, China;3.Oil Crops Research Institute, Chinese Academy of Agricultural Sciences, Wuhan 430062, China）
关键词:
油菜; 无人机遥感技术; 品种识别; 卷积神经网络; 注意力机制
Keywords:
rape; unmamed aerial vehicle (UAV) remote sensing technology; variety identification; convolutional neural network; attention mechanism
分类号:
TP75
DOI:
doi:10.3969/j.issn.1000-4440.2022.03.013
文献标志码:
A
摘要:
采用无人机遥感技术进行油菜品种识别，是产量预测及灾害评估的重要前提和基础。本研究利用无人机作为数据采集设备，以基地24个品种油菜苗期育种材料为识别数据，将无人机获取的影像进行拼接、裁剪、旋转等预处理，按照4∶1划分训练集和测试集，构建注意力机制引导的卷积神经网络搭建油菜影像识别网络模型，并采用总体准确率、Kappa系数等评价参数对识别结果进行评价。结果表明，本研究的网络模型识别准确率和Kappa系数分别达到了89.60%和0.889 4，高于5个经典网络模型。说明，注意力机制能够更加充分地提取无人机遥感影像的油菜特征，有效地提高卷积神经网络对不同品种油菜的识别精度。本研究网络模型弥补了传统油菜细分需要人力统计及现有方法设备成本高的缺陷，为采用无人机遥感技术进行作物品种识别提供技术支撑。
Abstract:
Using unmanned aerial vehicle (UAV) remote sensing technology to identify rape varieties is an important prerequisite and basis for yield prediction and disaster assessment. In this study, UAV was used as data acquisition equipment, and the breeding materials of 24 rape varieties at seedling stage in the base were used as identification data. The images obtained by the UAV were preprocessed such as splicing, clipping and rotation. The training set and test set were divided according to the ratio of 4∶1, and the convolutional neural network guided by attention mechanism was constructed to build the recognition model. The overall accuracy, Kappa coefficient and other evaluation parameters were used to evaluate the recognition results. The results showed that the recognition accuracy and Kappa coefficient of the network model constructed in this study reached 89.60% and 0.889 4, respectively, which were higher than those of the five classical network models. The attention mechanism can extract the rape features of UAV remote sensing images more fully, and effectively improve the recognition accuracy of convolutional neural network for different varieties of rape. The network model constructed in this study makes up for the shortcomings of human statistics and high cost of existing methods and equipment, and provides technical support for crop variety identification using UAV remote sensing technology.

参考文献/References:

[1]QIONG H, WEI H, YAN Y, et al. Rapeseed research and production in China[J]. The Crop Journal, 2017, 5(2): 127-135.
[2]刘成,冯中朝,肖唐华，等. 我国油菜产业发展现状、潜力及对策[J].中国油料作物学报, 2019, 41(4): 485-489.
[3]王晨宇,张亚民,吴伯彪，等. 基于无人机遥感的农作物自动分类研究[J]. 农业与技术, 2021, 41(1): 52-57.
[4]尹凡,刘燕,董晶晶，等. 基于冠层实测光谱的油菜品种识别[J]. 湖北农业科学, 2013, 52(23): 5866-5870.
[5]袁培森,李润隆,任守纲，等. 表示学习技术研究进展及其在植物表型中应用分析[J]. 农业机械学报, 2020, 51(6):1-14.
[6]JIANG Y, LI C. Convolutional neural networks for image-based high-throughput plant phenotyping: a review[J]. Plant Phenomics, 2020, 2(1): 1-22.
[7]MASJEDI A, CARPENTER N R, CRAWFORD M M, et al. Prediction of sorghum biomass using UAV time series data and recurrent neural networks[C]. Long Beach, America: IEEE/CVF, 2019.
[8]MASJEDI A, ZHAO J, ZHAO J, et al. Sorghum biomass prediction using UAV-Based remote sensing data and crop model simulation[C]. Valencia, Spain: IEEE, 2018.
[9]KOH J C O, HAYDEN M, DAETWYLER H, et al. Estimation of crop plant density at early mixed growth stages using UAV imagery[J]. Plant Methods, 2019, 15(1):1-9.
[10]BAUER A, BOSTROM A G, BALL J, et al. Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: a case study of lettuce production[J]. Horticulture Research, 2019, 6(1): 1-12.
[11]CANDIAGO S, REMONDINO F, GIGLIO M D, et al. Evaluating multispectral images and vegetation indices for precision farming applications from UAV images[J]. Remote Sensing, 2015, 7(4): 4026-4047.
[12]VERGER A, VIGNEAU N, CHRON C, et al. Green area index from an unmanned aerial system over wheat and rapeseed crops[J]. Remote Sensing of Environment, 2014, 152: 654-664.
[13]张丰,熊桢,寇宁. 高光谱遥感数据用于水稻精细分类研究[J]. 武汉理工大学学报, 2002, 24(10): 36-39.
[14]刘亮,姜小光,李显彬，等. 利用高光谱遥感数据进行农作物分类方法研究[J]. 中国科学院研究生院学报, 2006, 23(4):484-488.
[15]孙婷,田建平,胡新军，等. 基于高光谱成像技术的酿酒高粱品种分类[J]. 食品与发酵工业, 2021, 47(5):186-192.
[16]王林江,吴炳方,张淼，等. 关键生育期冬小麦和油菜遥感分类方法[J]. 地球信息科学学报, 2019, 21(7): 1121-1131.
[17]COLOMINA I, MOLINA P. Unmanned aerial systems for photogrammetry and remote sensing: a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 92: 79-97.
[18]陈小帮,左亚尧,王铭锋，等. 面向深度学习识别高空农作物的方法[J]. 计算机工程与设计, 2020, 41(2): 580-586.
[19]戴建国,张国顺,郭鹏，等. 基于无人机遥感可见光影像的北疆主要农作物分类方法[J]. 农业工程学报, 2018, 34(18): 122-128.
[20]BENDIG J, BOLTEN A, BENNERTZ S, et al. Estimating biomass of barley using crop surface models (CSMs) derived from UAV-based RGB imaging[J]. Remote Sensing, 2014, 6(11): 10395-10412.
[21]牛庆林,冯海宽,杨贵军，等. 基于无人机数码影像的玉米育种材料株高和LAI监测[J]. 农业工程学报, 2018, 34(5): 73-82.
[22]杨寿勇,张海阳,李成，等. 基于卷积神经网络模型的微藻种类识别[J]. 环境科学与技术, 2020, 43(S2):158-164.
[23]傅隆生,冯亚利,TOLA E,等. 基于卷积神经网络的田间多簇猕猴桃图像识别方法[J]. 农业工程学报, 2018, 34(2): 205-211.
[24]HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. Las Vegas, America: IEEE，2016: 770-778.
[25]HUANG G, LIU Z, MAATEN L V D, et al. Densely connected convolutional networks[C]. Honolulu, America: IEEE, 2017.
[26]XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated residual transformations for deep neural networks[C]. Honolulu, America: IEEE, 2017.
[27]TAN M, LE Q V. EfficientNet: Rethinking model scaling for convolutional neural networks[C]. Long Beach, America: ICML, 2019.
[28]ZHANG X, ZHOU X, LIN M, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]. Salt Lake City, America: IEEE/CVF, 2018.
[29]谢军,江朝晖,李博,等. 基于二次迁移模型的小样本茶树病害识别[J].江苏农业科学,2021,49(6):176-182.
[30]刘翱宇,吴云志,朱小宁,等. 基于深度残差网络的玉米病害识别[J].江苏农业学报,2021,37(1):67-74.

相似文献/References:

[1]付三雄,周晓婴,张 维,等.种植密度和施氮量对油菜产量、品质及机收性状的影响[J].江苏农业学报,2016,(03):548.[doi:10.3969/j.issn.1000-4440.2016.03.010]
　FU San-xiong,ZHOU Xiao-ying,ZHANG Wei,et al.Influences of planting density and nitrogen application rate on yield and quality and mechine harvest traits of rapeseed(Brassica napus L.)[J].,2016,(03):548.[doi:10.3969/j.issn.1000-4440.2016.03.010]
[2]陈魏涛,曹宏鑫,张保军,等.氮素营养诊断技术及其在油菜上的应用研究进展[J].江苏农业学报,2016,(04):953.[doi:10.3969/j.issn.100-4440.2016.04.038]
　CHEN Wei-tao,CAO Hong-xin,ZHANG Bao-jun,et al.Research progresses in nitrogen diagnosis technology and its application in rapeseed[J].,2016,(03):953.[doi:10.3969/j.issn.100-4440.2016.04.038]
[3]周晓婴,付三雄,陈松,等.甘蓝型油菜CRABS CLAW基因克隆及其RNA干扰载体的构建[J].江苏农业学报,2015,(04):737.[doi:10.3969/j.issn.1000-4440.2015.04.005]
　ZHOU Xiao-ying,FU San-xiong,CHEN Song,et al.Cloning of CRABS CLAW gene from Brassica napus and construction of its RNA interference vector[J].,2015,(03):737.[doi:10.3969/j.issn.1000-4440.2015.04.005]
[4]熊洁,邹晓芬,邹小云,等.干旱胁迫对不同基因型油菜农艺性状和产量的影响[J].江苏农业学报,2015,(03):494.[doi:10.3969/j.issn.1000-4440.2015.03.005]
　XIONG Jie,ZOU Xiao-fen,ZOU Xiao-yun,et al.Effects of drought stress on agronomic traits and yield of different rapeseed genotypes[J].,2015,(03):494.[doi:10.3969/j.issn.1000-4440.2015.03.005]
[5]熊洁,李书宇,邹晓芬,等.轻简化育苗移栽方式对油菜生长发育和产量的影响[J].江苏农业学报,2015,(02):317.[doi:10.3969/j.issn.1000-4440.2015.02.015]
　XIONG Jie,LI Shu-yu,ZOU Xiao-fen,et al.Effects of simplified seedling and transplanting patterns on growth and development and yield of rapeseed[J].,2015,(03):317.[doi:10.3969/j.issn.1000-4440.2015.02.015]
[6]李茹,陈国奇,张玉华,等.油菜和小麦秸秆水浸提液对千金子种子萌发和幼苗生长的影响及其应用[J].江苏农业学报,2018,(02):293.[doi:doi:10.3969/j.issn.1000-4440.2018.02.010]
　LI Ru,CHEN Guo-qi,ZHANG Yu-hua,et al.Influences of oilseed rape and wheat aquatic straw extract on Leptochloa chinensis seed germination and seedling growth, and the application potential[J].,2018,(03):293.[doi:doi:10.3969/j.issn.1000-4440.2018.02.010]
[7]葛道阔,曹宏鑫,杨余旺,等.干旱胁迫下油菜栽培模拟优化决策系统（Rape-CSODS）的订正及其检验[J].江苏农业学报,2019,(01):56.[doi:doi:10.3969/j.issn.1000-4440.2019.01.008]
　GE Dao-kuo,CAO Hong-xin,YANG Yu-wang,et al.Modification and verification of Rape-CSODS under drought stress[J].,2019,(03):56.[doi:doi:10.3969/j.issn.1000-4440.2019.01.008]
[8]岳绪国,葛永申,景德道,等.移栽密度和方式对不同类型油菜品种产量及构成的调控效应[J].江苏农业学报,2019,(01):63.[doi:doi:10.3969/j.issn.1000-4440.2019.01.009]
　YUE Xu-guo,GE Yong-shen,JING De-dao,et al.Effects of density and transplanting method on yield and yield components of different types of rapeseed[J].,2019,(03):63.[doi:doi:10.3969/j.issn.1000-4440.2019.01.009]
[9]程丽,胡茂龙,浦惠明,等.M342抗除草剂基因CAPS标记的开发与应用[J].江苏农业学报,2019,(02):241.[doi:doi:10.3969/j.issn.1000-4440.2019.02.001]
　CHENG Li,HU Mao-long,PU Hui-ming,et al.Development and application of the CAPS marker for herbicide-resistant gene in M342[J].,2019,(03):241.[doi:doi:10.3969/j.issn.1000-4440.2019.02.001]
[10]万倩,曹宏鑫,葛道阔,等.不同施肥量下花期渍水胁迫对油菜籽粒充实过程的定量影响[J].江苏农业学报,2020,(05):1144.[doi:doi:10.3969/j.issn.1000-4440.2020.05.011]
　WAN Qian,CAO Hong-xin,GE Dao-kuo,et al.Quantitative effects of waterlogging stress at florescence stage on the grain filling process of rape under different fertilization amounts[J].,2020,(03):1144.[doi:doi:10.3969/j.issn.1000-4440.2020.05.011]

备注/Memo

备注/Memo:
收稿日期：2021-09-09基金项目：国家重点研发计划项目（2017YFB1302401)；湖北省教育厅中青年人才项目（Q20201409）作者简介：李婕(1984-)，女，湖北宜昌人，博士，主要从事计算机视觉研究。 (E-mail)jielonline@163.com。李毅为共同第一作者。通讯作者：乔江伟,(E-mail)qiaojiangwei@caas.cn
更新日期/Last Update: 2022-07-07