[1]张先洁,孙国祥,汪小旵,等.基于超像素特征向量的果树冠层分割方法[J].江苏农业学报,2021,(03):724-730.[doi:doi:10.3969/j.issn.1000-4440.2021.03.023]
　ZHANG Xian-jie,SUN Guo-xiang,WANG Xiao-chan,et al.Segmentation method of fruit tree canopy based on super pixel feature vector[J].,2021,(03):724-730.[doi:doi:10.3969/j.issn.1000-4440.2021.03.023]
点击复制

基于超像素特征向量的果树冠层分割方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年03期
页码:
724-730
栏目:
园艺
出版日期:
2021-06-30

文章信息/Info

Title:
Segmentation method of fruit tree canopy based on super pixel feature vector
作者:
张先洁1; 孙国祥1; 汪小旵1; 2; 杨海慧1; 魏天翔1
（1.南京农业大学工学院，江苏南京210031；2.江苏省现代设施农业技术与装备工程实验室，江苏南京210031）
Author(s):
ZHANG Xian-jie1; SUN Guo-xiang1; WANG Xiao-chan1; 2; YANG Hai-hui1; WEI Tian-xiang1
(1.College of Engineering, Nanjing Agricultural University, Nanjing 210031, China;2.Laboratory of Modern Facility Agricultural Technology and Equipment Engineering in Jiangsu Province, Nanjing 210031, China)
关键词:
无人机; 植保; 果树冠层; 杂草; 超像素; 分割
Keywords:
unmanned aerial vehicle (UAV); plant protection; canopy of fruit trees; weed; super pixel; segmentation
分类号:
TP242.6+2;S252+.3
DOI:
doi:10.3969/j.issn.1000-4440.2021.03.023
文献标志码:
A
摘要:
针对无人机精确植保过程中，果树冠层区域颜色特征和杂草相似度较高、难以分割等问题，采用基于超像素特征向量的果树冠层分割方法，以消除不同杂草特征对树冠分离的干扰，减小农药喷雾区域，节省农药使用量。通过分析无人机采集合成的样本图像在HSV彩色空间上色调与饱和度的分布情况，选取合适的阈值范围，提取样本图像中包含果树冠层与杂草的绿色区域，将提取的绿色区域RGB图像转换生成Lab和HSV彩色空间模型下的图像，然后运用简单的线性迭代聚类（Simple linear iterative clustering，SLIC）超像素分割算法将RGB图像预设分割成250个超像素单元，结合超像素的分割信息与RGB图像、Lab图像、HSV图像以及灰度图，提取超像素单元的特征向量，随机选取25%的超像素样本的特征向量作为SVM分类器的训练集，利用SVM分类器对所有样本进行预测分类，实现果树冠层与杂草分割。将基于超像素特征向量的方法和基于光谱阈值、K-means聚类的2种方法进行对比分析，结果显示，基于超像素特征向量的方法在识别果树冠层位置方面生产者精度为90.83%，在提取果树冠层轮廓上F测度值为87.62%，总体分割性能优于后两种方法。说明，基于超像素特征向量的方法能够较为准确地分割果树冠层与杂草，为实现无人机在果园中精确植保提供重要支撑。
Abstract:
Aiming at the problem such as high similarity of color features between canopy area of fruit trees and weeds which are difficult to be segmented in the process of unmanned aerial vehicle (UAV) in precise plant protection, a canopy segmentation method based on super pixel feature vector was adopted to eliminate interference of different weed characteristics to crown separation, reduce the pesticide spray area and save pesticide usage. By analyzing the distribution of hue and saturation of sample images collected and synthesized by UAV in HSV color space, the appropriate threshold range was selected, the green area of the sample image including the canopy of fruit trees and weeds was extracted. The RGB image of the green area extracted was transformed to generate the image under Lab and HSV color space model, and simple linear iterative clustering (SLIC) super pixel segmentation algorithm was then used to divide the RGB image into 250 super pixel units by default. The feature vectors of super pixel unit was extracted by combining the segmentation information of super pixel with RGB image, Lab image, HSV image and gray scale image. Feature vectors of 25% super pixel samples were selected randomly as the training set of SVM classifier, SVM classifier was used in predicting and classifying all samples to realize the segmentation of fruit tree canopy and weeds. The method based on hyper pixel feature vector and methods based on spectral threshold and K-means clustering were compared. The results showed that, the producer accuracy of the method based on super pixel feature vector in recognizing position of fruit tree canopy was 90.83%, the F value for extracting contour of fruit tree canopy was 87.62%. The overall segmentation performance by the method based on hyper pixel feature vector was better than the latter two methods. It can be seen that, the method based on super pixel feature vector can segment fruit tree canopy and weeds accurately, which provides an important support for the realization of UAV in precise plant protection in the orchard.

参考文献/References:

[1]何勇,张艳超. 农用无人机现状与发展趋势[J].现代农机,2014(1):1-5.
[2]刘春鸽,赵丽伟. 我国植保无人机现状及发展建议[J].农业工程技术,2018,38(12):39-42.
[3]娄尚易,薛新宇,顾伟,等. 农用植保无人机的研究现状及趋势[J].农机化研究,2017,39(12):1-6，31.
[4]王大帅,张俊雄,李伟,等. 植保无人机动态变量施药系统设计与试验[J].农业机械学报,2017,48(5):86-93.
[5]陈盛德,兰玉彬,周志艳,等. 小型植保无人机喷雾参数对橘树冠层雾滴沉积分布的影响[J].华南农业大学学报,2017,38(5):97-102.
[6]刘剑君,贾世通,杜新武,等. 无人机低空施药技术发展现状与趋势[J].农业工程,2014,4(5):10-14.
[7]张云硕,史云天,董云哲,等. 农用植保无人机喷洒技术的研究[J].农业与技术,2015,35(21):46-47.
[8]WU J T，YANG J G，YANG H，et al.Extracting apple tree crown information from remote imagery using deep learning[J]. Computers and Electronics in Agriculture,2020,174:105504.
[9]CSILLIK O， JOHN C，ROBERT J，et al. Identification of citrus trees from unmanned aerial vehicle imagery using convolutional neural networks[J].Drones, 2018,2(4):39-54 .
[10]孙俊,谭文军,武小红,等. 多通道深度可分离卷积模型实时识别复杂背景下甜菜与杂草[J].农业工程学报,2019,35(12):184-190.
[11]王璨,武新慧,李志伟. 基于卷积神经网络提取多尺度分层特征识别玉米杂草[J].农业工程学报,2018,34(5):144-151.
[12]BERGE T W，GOLDBERG S，KASPERSEN K，et al. Towards machine vision based site-specific weed management in cereals[J]. Computers and Electronics in Agriculture,2012,81:79-86.
[13]HAMUDA E，GLAVIN M，JONES E . A survey of image processing techniques for plant extraction and segmentation in the field[J]. Computers and Electronics in Agriculture,2016,125:184-199.
[14]BAI X D，CAO Z G，WANG Y，et al. Crop segmentation from images by morphology modeling in the CIE L*a*b* color space[J]. Computers and Electronics in Agriculture,2013,99:21-34.
[15]CAMILO P，LEONARDO S，NELSON V. Weed recognition by SVM texture feature classification in outdoor vegetable crop images[J]. Ingeniería e Investigación, 2017, 37(1): 68-74.
[16]LE V，SELAM A，BENIAMIN A，et al. A novel method for detecting morphologically similar crops and weeds based on the combination of contour masks and filtered Local Binary Pattern operators[J]. Gigascience,2020,9(3) :1-16.
[17]程浈浈,祁力钧,程一帆,等. 基于M-LP特征加权聚类的果树冠层图像分割方法[J].农业机械学报,2020,51(4):191-198，260.
[18]RADHAKRISHNA A，APPU S，KEVIN S，et al. SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Trans on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.
[19]刘俊伟，陈鹏飞，张东彦，等. 基于时序SentineI-2影像的梨树县作物种植结构[J].江苏农业学报，2020,36(6):1428-1436.
[20]董松，徐晓辉，宋涛，等. 基于过渡区研究的黄瓜病害识别方法[J].南方农业学报，2019，50（9）：2119-2126.
[21]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,2019,35(5):1054-1060.
[22]林升梁,刘志. 基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007，35(2):163-167.
[23]陈崇成,李旭,黄洪宇. 基于无人机影像匹配点云的苗圃单木冠层三维分割[J].农业机械学报,2018,49(2):149-155，206.

相似文献/References:

[1]于堃,单捷,王志明,等.无人机遥感技术在小尺度土地利用现状动态监测中的应用[J].江苏农业学报,2019,(04):853.[doi:doi:10.3969/j.issn.1000-4440.2019.04.015]
　YU Kun,SHAN Jie,WANG Zhi ming,et al.Land use status monitoring in small scale by unmanned aerial vehicles (UAVs) observations[J].,2019,(03):853.[doi:doi:10.3969/j.issn.1000-4440.2019.04.015]
[2]陶惠林,冯海宽,徐良骥,等.基于无人机高光谱遥感数据的冬小麦生物量估算[J].江苏农业学报,2020,(05):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
　TAO Hui-lin,FENG Hai-kuan,XU Liang-ji,et al.Winter wheat biomass estimation based on hyperspectral remote sensing data of unmanned aerial vehicle(UAV)[J].,2020,(03):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
[3]郭松,常庆瑞,郑智康,等.基于无人机高光谱影像的玉米叶绿素含量估测[J].江苏农业学报,2022,38(04):976.[doi:doi:10.3969/j.issn.1000-4440.2022.04.014]
　GUO Song,CHANG Qing-rui,ZHENG Zhi-kang,et al.Estimation of maize chlorophyll content based on unmanned aerial vehicle (UAV) hyperspectral images[J].,2022,38(03):976.[doi:doi:10.3969/j.issn.1000-4440.2022.04.014]
[4]龚志远,李雪梅,李秋萍,等.兰州植物园植被春季物候无人机监测[J].江苏农业学报,2023,(08):1707.[doi:doi:10.3969/j.issn.1000-4440.2023.08.010]
　GONG Zhi-yuan,LI Xue-mei,LI Qiu-ping,et al.Unmanned aerial vehicle (UAV) monitoring of spring vegetation phenology in Lanzhou Botanical Garden[J].,2023,(03):1707.[doi:doi:10.3969/j.issn.1000-4440.2023.08.010]
[5]李瑞鑫,张宝林,潘丽杰,等.不同无人机飞行高度下玉米叶片叶绿素相对含量的无人机遥感反演及其指示叶位的识别[J].江苏农业学报,2024,(07):1234.[doi:doi:10.3969/j.issn.1000-4440.2024.07.010]
　LI Ruixin,ZHANG Baolin,PAN Lijie,et al.Unmanned aerial vehicle remote sensing inversion of relative chlorophyll content of maize leaves and identification of their indicator leaf at different flight altitudes[J].,2024,(03):1234.[doi:doi:10.3969/j.issn.1000-4440.2024.07.010]

备注/Memo

备注/Memo:
收稿日期：2021-01-19基金项目：国家重点研发计划项目(2017YFD0701400)作者简介：张先洁（1993-），男，江苏宿迁人，硕士研究生，主要从事农业电气化和自动化研究。(E-mail)873941071@qq.com通讯作者：汪小旵，(E-mail)wangxiaochan@njau.edu.cn
更新日期/Last Update: 2021-07-05