Cotton Boll Growth Status Recognition Method under Complex Background Based on Semantic Segmentation

In order to quickly and accurately identify the state of cotton bells during different growth periods in complex backgrounds between cotton fields, this paper studied cotton and cotton bells under natural light, uses machine positions from different angles. We compare 4 classes of semantic segmentat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE) S. 50 - 54
Hauptverfasser: Lv, Qinkai, Wang, Haihui
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 04.11.2021
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In order to quickly and accurately identify the state of cotton bells during different growth periods in complex backgrounds between cotton fields, this paper studied cotton and cotton bells under natural light, uses machine positions from different angles. We compare 4 classes of semantic segmentation models such as PSPnet, FCN, deeplabv3+ and SegNet and propose an optimization algorithm for the structure of PSPnet models. Morphologies, size, and weed background positions were segmented for cotton bells and cotton, and cotton growth periods were classified and identified according to the state and type of segmentation. Based on the pspnet model, more and accurate cotton bell feature information was extracted in a complex background by using the context information of different regions as a prior knowledge and selecting ResNet50 as the backbone feature extraction network. At the same time, the improved model coding part incorporates the context coding module, complements more global prior knowledge, and integrates the cotton shallow features in the model decoding part, solving the problem of insufficient segmentation accuracy under the influence of the complex background. After training using 1400 images, 400 field cotton bell images were used as tests. The results show that the improved model outperformed the original model in accuracy and speed, the identification method that uses the segmentation results to judge the cotton bell growth stage is satisfied.
AbstractList In order to quickly and accurately identify the state of cotton bells during different growth periods in complex backgrounds between cotton fields, this paper studied cotton and cotton bells under natural light, uses machine positions from different angles. We compare 4 classes of semantic segmentation models such as PSPnet, FCN, deeplabv3+ and SegNet and propose an optimization algorithm for the structure of PSPnet models. Morphologies, size, and weed background positions were segmented for cotton bells and cotton, and cotton growth periods were classified and identified according to the state and type of segmentation. Based on the pspnet model, more and accurate cotton bell feature information was extracted in a complex background by using the context information of different regions as a prior knowledge and selecting ResNet50 as the backbone feature extraction network. At the same time, the improved model coding part incorporates the context coding module, complements more global prior knowledge, and integrates the cotton shallow features in the model decoding part, solving the problem of insufficient segmentation accuracy under the influence of the complex background. After training using 1400 images, 400 field cotton bell images were used as tests. The results show that the improved model outperformed the original model in accuracy and speed, the identification method that uses the segmentation results to judge the cotton bell growth stage is satisfied.
Author Lv, Qinkai
Wang, Haihui
Author_xml – sequence: 1
  givenname: Qinkai
  surname: Lv
  fullname: Lv, Qinkai
  email: 475377441@qq.com
  organization: Wuhan Institute of Technology,Wuhan,China
– sequence: 2
  givenname: Haihui
  surname: Wang
  fullname: Wang, Haihui
  email: 2580129116@qq.com
  organization: Wuhan Institute of Technology,Wuhan,China
BookMark eNotj91Kw0AQRlfQC619AkH2BRL3P8llG2oVKkKr12W7M0mDyW5Jtqhv74K9msN83xyYO3Ltg0dCHjnLOWfV07ZerLQ0rMgFEzyvjCxLo67IvCpKboxWopBM3BKoQ4zB02Xoe7oew3c80l208TzRLbrQ-i52KX7DeAxAzx5wpHUYTj3-0KV1X-0Y0jLhhEBTcYeD9bFzCdoBfTKl83ty09h-wvllzsjn8-qjfsk27-vXerHJOsFkzA6au-aglBFaQ6UEcGcRueEAVjCuQUnAsjJWG-5YAyAKhAQMK1CNdnJGHv69HSLuT2M32PF3f_ld_gHzK1XT
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/RCAE53607.2021.9638864
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665427302
1665427302
EndPage 54
ExternalDocumentID 9638864
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i203t-b51cfb446255d942d1caee161dda2015d43de896a561c0fdd27edc0f0e9d4f5c3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000766523000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jun 29 18:37:58 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-b51cfb446255d942d1caee161dda2015d43de896a561c0fdd27edc0f0e9d4f5c3
PageCount 5
ParticipantIDs ieee_primary_9638864
PublicationCentury 2000
PublicationDate 2021-Nov.-4
PublicationDateYYYYMMDD 2021-11-04
PublicationDate_xml – month: 11
  year: 2021
  text: 2021-Nov.-4
  day: 04
PublicationDecade 2020
PublicationTitle 2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE)
PublicationTitleAbbrev RCAE
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7963657
Snippet In order to quickly and accurately identify the state of cotton bells during different growth periods in complex backgrounds between cotton fields, this paper...
SourceID ieee
SourceType Publisher
StartPage 50
SubjectTerms Complex background
Context encoding
Cotton
Decoding
Encoding
Feature extraction
Image segmentation
PSPNet
Semantic segmentation
Semantics
Training
Title Cotton Boll Growth Status Recognition Method under Complex Background Based on Semantic Segmentation
URI https://ieeexplore.ieee.org/document/9638864
WOSCitedRecordID wos000766523000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8MwDI02xIEToA3xrRw40q1t0qY5wjTgwjQNkHab0tiBCdahrUP8fJyuDCFx4WYlliL5JbKd5NmMXahUiSixaWC0ywOphAhMHunAuszICEAYvW42oQaDbDzWwwa73HBhELH6fIYdL1Zv-TC3K39V1vWbJUtlkzWVStdcrZr0G4W6O-pd9RORhoqyvjjq1Mq_uqZUTuNm93_L7bH2D_uODzd-ZZ81sGgx6M1LCtP4NeHGbyl3Ll-4DxRXSz76_gNE0_dVQ2jumWEL7s_6G37ya2NfPXujABKXCJwUH3BGNp1aEp5nNf-oaLOnm_5j7y6oOyQE0zgUZZAnkXU5ZXSUGICWMUTWIFIQB2DIsycgBWCmU0NRkg0dQKwQSAhRg3SJFQdsq5gXeMh4ljiVxKHKXYpSWqeVgMhXpslywi2Mj1jLW2jyvi6CMamNc_z38Anb8SBUpD15yrbKxQrP2Lb9KKfLxXmF3Beu852u
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEG0QTfSkBozf9uDRhe623W6PQkCMQAhiwo10O10lymJgMf5822XFmHjxNmknaTKvzcy0fTMIXYtQUJ_r0FMyiT0mKPVU7EtPJ5FiPgBVct1sQvT70XgsByV0s-HCGGPyz2em5sT8LR_meuWuyupus0Qh20LbnLGArNlaBe3XJ7I-bN62OA2JsHlf4NcK9V99U3K30d7_34IHqPrDv8ODjWc5RCWTVhA055kN1HDDIofvbPacvWAXKq6WePj9C8hO9_KW0NhxwxbYnfY384kbSr86_kYKVlwawFbx0cysVafaCs-zgoGUVtFTuzVqdryiR4I3DQjNvJj7OoltTmdTA5AsAF8rY2wYB6Csb-fAKJhIhsrGSZokAIEwYAViJLCEa3qEyuk8NccIRzwRPCAiTkLDmE6koOC72jRRbJEjwQmqOAtN3tdlMCaFcU7_Hr5Cu51Rrzvp3vcfztCeAySn8LFzVM4WK3OBdvRHNl0uLnMUvwAOqKD1
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%3Abook&rft.genre=proceeding&rft.title=2021+4th+International+Conference+on+Robotics%2C+Control+and+Automation+Engineering+%28RCAE%29&rft.atitle=Cotton+Boll+Growth+Status+Recognition+Method+under+Complex+Background+Based+on+Semantic+Segmentation&rft.au=Lv%2C+Qinkai&rft.au=Wang%2C+Haihui&rft.date=2021-11-04&rft.pub=IEEE&rft.spage=50&rft.epage=54&rft_id=info:doi/10.1109%2FRCAE53607.2021.9638864&rft.externalDocID=9638864