基于Dog-Leg正则化自适应压缩采样的植株图像重构

TN911.72; 目标植株的图像压缩与重构在农作物生长状态检测、田间管理和果树病虫害识别等方面有重要作用.传统的图像压缩感知方法存在重构精度低、时间长等问题.针对这些情况,该文提出一种基于Dog-Leg最小二乘的正则化自适应压缩采样匹配追踪(regularized adaptive compressed sampling matching pursuit based on Dog-Leg,DLRaCSMP)算法.该算法以压缩采样匹配追踪(compressive sampling matching pursuit,CoSaMP)算法为基础,在迭代过程中采用正则化处理,确保支撑集选取的准确性,并...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 35; no. 12; pp. 191 - 199
Main Authors 沈跃, 李尚龙, 刘慧, 刘加林
Format Journal Article
LanguageChinese
Published 江苏大学电气信息工程学院,镇江,212013 15.06.2019
Subjects
算法
显著性特征图
图像重构
最小二乘法
边缘检测
压缩感知
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2019.12.023

Cover

Abstract TN911.72; 目标植株的图像压缩与重构在农作物生长状态检测、田间管理和果树病虫害识别等方面有重要作用.传统的图像压缩感知方法存在重构精度低、时间长等问题.针对这些情况,该文提出一种基于Dog-Leg最小二乘的正则化自适应压缩采样匹配追踪(regularized adaptive compressed sampling matching pursuit based on Dog-Leg,DLRaCSMP)算法.该算法以压缩采样匹配追踪(compressive sampling matching pursuit,CoSaMP)算法为基础,在迭代过程中采用正则化处理,确保支撑集选取的准确性,并结合变步长自适应思想和Dog-Leg最小二乘算法,在实现稀疏度自适应的同时,提高重构速率;选用Kinect获取目标植株的彩色图像,分别采用HSV彩色空间的亮度和色调特征及Sobel算子的轮廓特征输入至Itti模型中融合构建显著性特征图,以简化复杂背景和突出目标植株.试验结果表明,该算法在采样率为0.50时植株原始图像和显著性特征图的重构时间分别为2.14和1.75 s,较CoSaMP算法分别缩短6.57和6.31 s,重构效率比CoSaMP算法平均分别提高75.5％和77.9％;图像峰值信噪比分别高达35.16和38.93 dB,较CoSaMP算法分别提高6.12和5.75 dB,且重构精度比CoSaMP算法平均分别提高21.6％和15.5％,可以实现植株图像的快速精确重构.
AbstractList TN911.72; 目标植株的图像压缩与重构在农作物生长状态检测、田间管理和果树病虫害识别等方面有重要作用.传统的图像压缩感知方法存在重构精度低、时间长等问题.针对这些情况,该文提出一种基于Dog-Leg最小二乘的正则化自适应压缩采样匹配追踪(regularized adaptive compressed sampling matching pursuit based on Dog-Leg,DLRaCSMP)算法.该算法以压缩采样匹配追踪(compressive sampling matching pursuit,CoSaMP)算法为基础,在迭代过程中采用正则化处理,确保支撑集选取的准确性,并结合变步长自适应思想和Dog-Leg最小二乘算法,在实现稀疏度自适应的同时,提高重构速率;选用Kinect获取目标植株的彩色图像,分别采用HSV彩色空间的亮度和色调特征及Sobel算子的轮廓特征输入至Itti模型中融合构建显著性特征图,以简化复杂背景和突出目标植株.试验结果表明,该算法在采样率为0.50时植株原始图像和显著性特征图的重构时间分别为2.14和1.75 s,较CoSaMP算法分别缩短6.57和6.31 s,重构效率比CoSaMP算法平均分别提高75.5％和77.9％;图像峰值信噪比分别高达35.16和38.93 dB,较CoSaMP算法分别提高6.12和5.75 dB,且重构精度比CoSaMP算法平均分别提高21.6％和15.5％,可以实现植株图像的快速精确重构.
Author 刘加林
李尚龙
刘慧
沈跃
AuthorAffiliation 江苏大学电气信息工程学院,镇江,212013
AuthorAffiliation_xml – name: 江苏大学电气信息工程学院,镇江,212013
Author_FL Liu Hui
Liu Jialin
Li Shanglong
Shen Yue
Author_FL_xml – sequence: 1
  fullname: Shen Yue
– sequence: 2
  fullname: Li Shanglong
– sequence: 3
  fullname: Liu Hui
– sequence: 4
  fullname: Liu Jialin
Author_xml – sequence: 1
  fullname: 沈跃
– sequence: 2
  fullname: 李尚龙
– sequence: 3
  fullname: 刘慧
– sequence: 4
  fullname: 刘加林
BookMark eNo9j81Kw0AcxPdQwVr7GOIpcf-72WRzU-onBLzoueRjN7TIBlxEvYkWImjrRQQVtKAXC56FID6Nm5q3MKJ4mYE5zG9mDjVUpgRCC4BtAN9jS327p7WyAWNiuRx8m-BagNiY0AZq_uezqK11L8IMqIexA020bB6Lz2K0mqVWINLy9cmc35rLm698Up2cmuLajC6m7y9Vnpfjt-ndoHweluOJuf8wZ1dVPiwfBvNoRoZ7WrT_vIV219d2OptWsL2x1VkJLA31CMtlUhIWEweHnGDmJCSGJHRcj-MQeCJIzBIhKZNU1ipiH7hwIi6wz0Tky4S20OJv72GoZKjSbj872Fc1sauO0_go-nkMpEbRbymIY5o
ClassificationCodes TN911.72
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.11975/j.issn.1002-6819.2019.12.023
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Agriculture
DocumentTitle_FL Plant image reconstruction based on Dog-Leg regularized adaptive compression sampling
EndPage 199
ExternalDocumentID nygcxb201912023
GrantInformation_xml – fundername: 江苏省国际科技合作项目; 江苏省重点研发计划; 江苏省自然科学基金; 江苏高校青蓝工程资助; 镇江市重点研发计划; 江苏高校优势学科
  funderid: (BZ2017067); (BE2018372); (BK20181443); 江苏高校青蓝工程资助; (NY2018001); 江苏高校优势学科
GroupedDBID -04
2B.
4A8
5XA
5XE
92G
92I
93N
ABDBF
ABJNI
ACGFO
ACGFS
ACUHS
AEGXH
AIAGR
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CHDYS
CW9
EOJEC
FIJ
IPNFZ
OBODZ
PSX
RIG
TCJ
TGD
TUS
U1G
U5N
ID FETCH-LOGICAL-s1023-65ff25c240a82054d2c1da46780a18de2c5def35f3ff35ec918e4b8e095eb9fd3
ISSN 1002-6819
IngestDate Thu May 29 04:08:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 12
Keywords 算法
显著性特征图
图像重构
最小二乘法
边缘检测
压缩感知
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1023-65ff25c240a82054d2c1da46780a18de2c5def35f3ff35ec918e4b8e095eb9fd3
PageCount 9
ParticipantIDs wanfang_journals_nygcxb201912023
PublicationCentury 2000
PublicationDate 2019-06-15
PublicationDateYYYYMMDD 2019-06-15
PublicationDate_xml – month: 06
  year: 2019
  text: 2019-06-15
  day: 15
PublicationDecade 2010
PublicationTitle 农业工程学报
PublicationTitle_FL Transactions of the Chinese Society of Agricultural Engineering
PublicationYear 2019
Publisher 江苏大学电气信息工程学院,镇江,212013
Publisher_xml – name: 江苏大学电气信息工程学院,镇江,212013
SSID ssib051370041
ssj0041925
ssib001101065
ssib023167668
Score 2.264269
Snippet TN911.72; 目标植株的图像压缩与重构在农作物生长状态检测、田间管理和果树病虫害识别等方面有重要作用.传统的图像压缩感知方法存在重构精度低、时间长等问题.针对这些情况,该文提出一种基于Dog-Leg最小二乘的正则化自适应压缩采样匹配追踪(regularized adaptive compressed...
SourceID wanfang
SourceType Aggregation Database
StartPage 191
Title 基于Dog-Leg正则化自适应压缩采样的植株图像重构
URI https://d.wanfangdata.com.cn/periodical/nygcxb201912023
Volume 35
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Na9RAFB_6AaIH8ZP6SQ_OMTWTZJKZm5PdLEXUUwu9lSSTrKcttFvQnkQLW9DWiwgqaEEvFjwLRfxrzNb-F743mf2glvoBy5CdefPe783L5L0JbyaE3AoYy8GP5A7PWOkEWmsnhSpHp6mOAq4znuJC8f6DcH4xuLvElyYmt8aylta72Vy-cey-kv-xKtSBXXGX7D9YdsgUKuAa7AslWBjKv7IxTTiVLRormgRYiqS50nbuFW2ahFQ1qfKRQggqpbloUBnSRFARUQV9JKY5CA-boLMMDE1CRUyTiMYNqqShifCHDF0aR9gkQVJgaiAQbdomZAhoYhonho9PRWvQ3dBI4ByMx8KGDOobBr1AtogEsHGUooRBwo0iIXIQCpoGdwhWxB4qBwpBJ-GPt8gmaoLsXMNXIiwpRyT1sAjDFkREx7RwI9C12Ov83sELEtyTFTr1FlFzSxs4DK2RGNyoPMcBUtGYDhGOcswNsWtGHP62qGIGB6OqdeIQSDSk8mBamGtuDVPL9RoQH7j1llvrZtAPhcI6C-uH6mNbBvPNG_MqrP6gmQ1QWD1av_s-GXHj_FDE3FAEpi9K88q73th95HjxzuN2_ihDGsDo-ZNk2osiTHiYVnEzbo1Ca4ZvD4bPfg9PUAhHS1XOfPxQwjC9CpMLuMk0sDBOEToAefskiGbzXKdMO-2xOG_hHDlrF2izqp5t58nExsML5Ixqr9pDaoqL5E71Yf_H_o6da_0vH6utN9WL1z97e4dPnlb7r6qd5wffPh_2ev3drwdvN_uftvu7e9W779Wzl4e97f77zUtksZUsNOYd-yUSZw2PNnFCXpYezyH6TSFi5oH2cqZTiDGEmzKhCy_nuih9XvollEUumSiCTBSwfikyWWr_MpnqrHSKGTLrhzKHRUAZZkIEvtBpJlMeFi4sbKTOi-gKmbX6L9snzdryERtd_TPJNXJ6NBWuk6nu6npxA6LnbnbTGvYXljKTpw
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EDog-Leg%E6%AD%A3%E5%88%99%E5%8C%96%E8%87%AA%E9%80%82%E5%BA%94%E5%8E%8B%E7%BC%A9%E9%87%87%E6%A0%B7%E7%9A%84%E6%A4%8D%E6%A0%AA%E5%9B%BE%E5%83%8F%E9%87%8D%E6%9E%84&rft.jtitle=%E5%86%9C%E4%B8%9A%E5%B7%A5%E7%A8%8B%E5%AD%A6%E6%8A%A5&rft.au=%E6%B2%88%E8%B7%83&rft.au=%E6%9D%8E%E5%B0%9A%E9%BE%99&rft.au=%E5%88%98%E6%85%A7&rft.au=%E5%88%98%E5%8A%A0%E6%9E%97&rft.date=2019-06-15&rft.pub=%E6%B1%9F%E8%8B%8F%E5%A4%A7%E5%AD%A6%E7%94%B5%E6%B0%94%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E9%95%87%E6%B1%9F%2C212013&rft.issn=1002-6819&rft.volume=35&rft.issue=12&rft.spage=191&rft.epage=199&rft_id=info:doi/10.11975%2Fj.issn.1002-6819.2019.12.023&rft.externalDocID=nygcxb201912023
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fnygcxb%2Fnygcxb.jpg