|本期目录/Table of Contents|

[1]范宏,刘素红,陈吉军,等.基于深度学习的白喉乌头与牧草高精度分类研究[J].江苏农业科学,2021,49(12):173-180.
 Fan Hong,et al.Study on high-precision classification of Aconitum leucostomum Worosch and pasture based on deep learning[J].Jiangsu Agricultural Sciences,2021,49(12):173-180.
点击复制

基于深度学习的白喉乌头与牧草高精度分类研究(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第49卷
期数:
2021年第12期
页码:
173-180
栏目:
农业工程与信息技术
出版日期:
2021-06-20

文章信息/Info

Title:
Study on high-precision classification of Aconitum leucostomum Worosch and pasture based on deep learning
作者:
范宏12刘素红3陈吉军4沈江龙12乔雪丽12郑江华12
1.新疆大学资源与环境科学学院,新疆乌鲁木齐 830046; 2.新疆大学绿洲生态教育部重点实验室,新疆乌鲁木齐 830046;3.北京师范大学环境遥感与数字城市北京重点实验室,北京 100875; 4.新疆治蝗灭鼠指挥部办公室,新疆乌鲁木齐 830046
Author(s):
Fan Honget al
关键词:
卷积神经网络毒害草无人机影像图像识别白喉乌头牧草
Keywords:
-
分类号:
TP391.41;S127
DOI:
-
文献标志码:
A
摘要:
采用无人机获取白喉乌头危害草原区的1 cm空间分辨率的无人机数字正射影像,分别在5×5、10×10、20×20、40×40、80×80像素5个尺度下选取白喉乌头和普通牧草2类训练样本,使用VGG16、VGG19、ResNet50等3种模型对图像切片的特征进行学习,以获取图像切片的深层特征,进而实现对2类地物的分类提取。对比5个分割尺度下3种模型得到的分类精度,发现不同的分割尺度对分类精度有明显影响,随着分割尺度的增加分类精度呈现出先升高再降低的趋势,在40×40像素尺度下3种方法都得到了最高的分类精度,分别为95.31%、96.88%、93.75%,白喉乌头的分类验证精度分别为86.52%、92.77%、93.81%。对分类结果进行分析发现,在40×40像素的尺度下对应的地面实际范围是40 cm×40 cm,与白喉乌头的单株长宽接近,能较好地提取白喉乌头整株的深层特征。
Abstract:
-

参考文献/References:

[1]李宏,陈卫民,陈翔,等. 新疆伊犁草原毒害草种类及其发生与危害[J]. 草业科学,2010,27(11):171-173.
[2]温阿敏,郑江华,穆晨,等. 基于GF-1WFV数据的草原毒草白喉乌头空间分布监测与分析[J]. 新疆农业科学,2015,52(10):1939-1946.
[3]Felinks B,Pilarski M,Wiegleb G. Vegetation survey in the former brown coal mining area of eastern Germany by integrating remote sensing and ground-based methods[J]. Applied Vegetation Science,1998,1(2):233-240.
[4]Jia X P,Richards J A. Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification[J]. IEEE Transactions on Geoscience and Remote Sensing,1999,37(1):538-542.
[5]Nagler P L,Daughtry C S T,Goward S N. Plant litter and soil reflectance[J]. Remote Sensing of Environment,2000,71(2):207-215.
[6]郭芬芬,范建容,汤旭光,等. 基于HJ-1A高光谱数据的藏北高原草地分类方法对比[J]. 遥感信息,2013,28(1):77-82,88.
[7]杜欣,黄晓霞,李红旮,等. 基于投影寻踪学习网络算法的植物群落高分遥感分类研究[J]. 地球信息科学学报,2016,18(1):124-132.
[8]Chen J J,Yi S H,Qin Y,et al. Improving estimates of fractional vegetation cover based on UAV in alpine grassland on the Qinghai-Tibetan Plateau[J]. International Journal of Remote Sensing,2016,37(8):1922-1936.
[9]Walter V. Object-based classification of remote sensing data for change detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2004,58(3/4):225-238.
[10]易超人,邓燕妮. 多通道卷积神经网络图像识别方法[J]. 河南科技大学学报(自然科学版),2017,38(3):41-44.
[11]李云飞,符冉迪,金炜,等. 多通道卷积的图像超分辨率方法[J]. 中国图象图形学报,2017,22(12):1690-1700.
[12]He K M,Zhang X Y,Ren S Q,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[13]Sirinukunwattana K,Raza S E A,Tsang Y W,et al. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images[J]. IEEE Transactions on Medical Imaging,2016,35(5):1196-1206.
[14]段萌,王功鹏,牛常勇. 基于卷积神经网络的小样本图像识别方法[J]. 计算机工程与设计,2018,39(1):224-229.
[15]韩星烁,林伟. 深度卷积神经网络在图像识别算法中的研究与实现[J]. 微型机与应用,2017,36(21):54-56.
[16]Helmy A K,EL-Taweel G S. Regular gridding and segmentation for microarray images[J]. Computers & Electrical Engineering,2013,39(7):2173-2182.
[17]Zefler M D,Fergus R. Visualizing and understanding convolutional networks[C]//Fleet D,Pajdla T,Schiele B,et al. Proceeding of Computer Vision—ECCV 2004. Zurich:Springs,2014:818-833.
[18]Zhou X,Sun Z P,Liu S H,et al. A method for extracting the leaf litter distribution area in forest using chip feature[J]. International Journal of Remote Sensing,2018,39(15/16):5310-5329.
[19]张鲜花,安沙舟,王显瑞,等. 白喉乌头种群空间分布格局初步研究[J]. 草地学报,2012,20(3):428-433.
[20]黄慧萍,吴炳方,李苗苗,等. 高分辨率影像城市绿地快速提取技术与应用[J]. 遥感学报,2004,8(1):68-74.
[21]Simonyon K,Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science,2014:1-14.
[22]Krizhevsky A,Sutskever I,Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90.
[23]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]//IEEE. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2016:770-778.
[24]王景中,杨源,何云华. 基于多分类和ResNet的不良图片识别框架[J]. 计算机系统应用,2018,27(9):100-106.
[25]陈小娥,杨薇薇. 基于深度学习的车标识别算法的研究与实现[J]. 长春工程学院学报(自然科学版),2017,18(2):117-120.
[26]Gundersen H J G,Jensen E B. The efficiency of systematic sampling in stereology and its prediction[J]. Journal of Microscopy,1987,147(3):229-263.

相似文献/References:

[1]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241.
 Liang Wanjie,et al.Identification of rice insect pests based on CNN model[J].Jiangsu Agricultural Sciences,2017,45(12):241.
[2]赵建敏,李艳,李琦,等.基于卷积神经网络的马铃薯叶片病害识别系统[J].江苏农业科学,2018,46(24):251.
 Zhao Jianmin,et al.Potato leaf disease identification system based on convolutional neural network[J].Jiangsu Agricultural Sciences,2018,46(12):251.
[3]魏青迪,范昊,张承明.基于ECLDeeplab模型提取华北地区耕地的方法[J].江苏农业科学,2020,48(04):209.
 Wei Qingdi,et al.A method for extracting cultivated land in North China based on ECLDeeplab model[J].Jiangsu Agricultural Sciences,2020,48(12):209.
[4]陈峰,谷俊涛,李玉磊,等.基于机器视觉和卷积神经网络的东北寒地玉米害虫识别方法[J].江苏农业科学,2020,48(18):237.
 Chen Feng,et al.Recognition method of corn pests in northeast cold region based on machine vision and convolutional neural network[J].Jiangsu Agricultural Sciences,2020,48(12):237.
[5]陈旭君,王承祥,孙福,等.基于改进Faster R-CNN的田间植株幼苗检测方法[J].江苏农业科学,2021,49(4):159.
 Chen Xujun,et al.Detection method for plant seedlings in fields based on improved Faster R-CNN[J].Jiangsu Agricultural Sciences,2021,49(12):159.
[6]黎振,陆玲,熊方康.基于k-means分割和迁移学习的番茄病理识别[J].江苏农业科学,2021,49(12):156.
 Li Zhen,et al.Tomato pathological recognition based on k-means segmentation and transfer learning[J].Jiangsu Agricultural Sciences,2021,49(12):156.
[7]李萍,邵彧,齐国红,等.基于跨深度学习模型的作物病害检测方法[J].江苏农业科学,2022,50(8):193.
 Li Ping,et al.Crop disease detection method based on cross deep learning model[J].Jiangsu Agricultural Sciences,2022,50(12):193.
[8]李祥宇,任艳娜,马新明,等.面向小麦生育进程监测的卷积神经网络精简化研究[J].江苏农业科学,2022,50(8):199.
 Li Xiangyu,et al.Study on simplified convolutional neural network for monitoring wheat growth process[J].Jiangsu Agricultural Sciences,2022,50(12):199.
[9]蒋清健,姚勇,付志军,等.基于改进卷积神经网络算法的番茄叶片病害识别[J].江苏农业科学,2022,50(20):29.
 Jiang Qingjian,et al.Tomato leaf disease recognition based on improved convolutional neural network algorithm[J].Jiangsu Agricultural Sciences,2022,50(12):29.
[10]何前,郭峰林,方皓正,等.基于改进LeNet-5模型的玉米病害识别[J].江苏农业科学,2022,50(20):35.
 He Qian,et al.Study on maize disease recognition based on improved LeNet-5 model[J].Jiangsu Agricultural Sciences,2022,50(12):35.

备注/Memo

备注/Memo:
收稿日期:2020-11-06
基金项目:新疆维吾尔自治区高校科研计划(编号:XJEDU2019I010);2018年新疆治蝗灭鼠指挥办公室委托项目。
作者简介:范宏(1994—),男,安徽阜阳人,硕士研究生,主要研究方向为遥感与草原灾害防治。E-mail:1025288556@qq.com。
通信作者:郑江华,博士,教授,博士生导师,主要研究方向为遥感与地理信息系统应用研究。E-mail:zheng_jianghua@126.com。
更新日期/Last Update: 2021-06-20