키넥트 깊이 정보와 컨볼루션 신경망을 이용한 개별 돼지의 탐지

Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is s...

Full description

Saved in:
Bibliographic Details
Published in한국콘텐츠학회논문지 Vol. 18; no. 2; pp. 1 - 10
Main Authors 이준희(Junhee Lee), 이종욱(Jonguk Lee), 박대희(Daihee Park), 정용화(Yongwha Chung)
Format Journal Article
LanguageKorean
Published 한국콘텐츠학회 2018
Subjects
Online AccessGet full text
ISSN1598-4877
2508-6723

Cover

Abstract Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is still challenging problem. In this paper, we propose a new Kinect camera and deep learning-based monitoring system for the detection of the individual pigs. The proposed system is characterized as follows. 1) The background subtraction method and depth-threshold are used to detect only standing-pigs in the Kinect-depth image. 2) The standing-pigs are detected by using YOLO (You Only Look Once) which is the fastest and most accurate model in deep learning algorithms. Our experimental results show that this method is effective for detecting individual pigs in real time in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (average 99.40% detection accuracies). 혼잡한 돈방에서 사육되는 이유자돈들의 공격적인 이상행동들은 축산농가의 경제적 손실을 야기할 뿐만 아니라 동물복지입장에서도 바람직하지 않다. 이러한 문제점의 해결책으로, 최근 IT기반의 연구들이 소개되고 있으나 혼잡한 돈방에서의 돼지 객체 탐지는 여전히 도전적인 문제로 알려져 있다. 본 논문에서는 개별 돼지의 탐지를 위한 키넥트 카메라와 딥러닝 기반의 새로운 모니터링 시스템을 제안한다. 제안된 시스템은 다음과 같다. 1) 키넥트 카메라로부터 취득한 깊이 영상에서 배경 차영상 기법과 깊이 임계값을 이용하여 서있는 돼지만을 탐지한다, 2) 딥러닝 알고리즘 중 최근 가장 빠르고 높은 정확도를 보이는 YOLO(You Only Look Once)를 이용하여 서있는 돼지들을 탐지한다. 본 연구의 실험 결과에 의하면, 제안된 시스템은 경제적인 비용(저가의 키넥트 센서)과 시스템 정확도(평균 99.40% 객체 검출율과 탐지 정확도)로 개별 돼지 객체들을 실시간으로 탐지할 수 있음을 실험적으로 확인하였다.
AbstractList Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is still challenging problem. In this paper, we propose a new Kinect camera and deep learning-based monitoring system for the detection of the individual pigs. The proposed system is characterized as follows. 1) The background subtraction method and depth-threshold are used to detect only standing-pigs in the Kinect-depth image. 2) The standing-pigs are detected by using YOLO (You Only Look Once) which is the fastest and most accurate model in deep learning algorithms. Our experimental results show that this method is effective for detecting individual pigs in real time in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (average 99.40% detection accuracies). 혼잡한 돈방에서 사육되는 이유자돈들의 공격적인 이상행동들은 축산농가의 경제적 손실을 야기할 뿐만 아니라 동물복지입장에서도 바람직하지 않다. 이러한 문제점의 해결책으로, 최근 IT기반의 연구들이 소개되고 있으나 혼잡한 돈방에서의 돼지 객체 탐지는 여전히 도전적인 문제로 알려져 있다. 본 논문에서는 개별 돼지의 탐지를 위한 키넥트 카메라와 딥러닝 기반의 새로운 모니터링 시스템을 제안한다. 제안된 시스템은 다음과 같다. 1) 키넥트 카메라로부터 취득한 깊이 영상에서 배경 차영상 기법과 깊이 임계값을 이용하여 서있는 돼지만을 탐지한다, 2) 딥러닝 알고리즘 중 최근 가장 빠르고 높은 정확도를 보이는 YOLO(You Only Look Once)를 이용하여 서있는 돼지들을 탐지한다. 본 연구의 실험 결과에 의하면, 제안된 시스템은 경제적인 비용(저가의 키넥트 센서)과 시스템 정확도(평균 99.40% 객체 검출율과 탐지 정확도)로 개별 돼지 객체들을 실시간으로 탐지할 수 있음을 실험적으로 확인하였다.
Author 박대희(Daihee Park)
이준희(Junhee Lee)
이종욱(Jonguk Lee)
정용화(Yongwha Chung)
Author_xml – sequence: 1
  fullname: 이준희(Junhee Lee)
– sequence: 2
  fullname: 이종욱(Jonguk Lee)
– sequence: 3
  fullname: 박대희(Daihee Park)
– sequence: 4
  fullname: 정용화(Yongwha Chung)
BookMark eNpFjj1Lw0AAhg-pYK39D7c4Bu4jl9yNpdbPYpfiGs4kB6E1SqODW9G61EGXQpUGCiqtm9gOivUP9S7_wYCC0_sMDw_vOijEp3G4AoqEIW45LqEFUMRMcMvmrrsGykkSHSPEKHKwQ4rgKLt61r2XrP8Bl599k86hGQ_0bG4eutB8TfVsoZ-m5mYIze14-f6tJ6lJezD3zONrNhjB5dtIz3pQ3y3MpGvSIcyu73PaAKtKtpOw_Lcl0NyuNau7Vr2xs1et1K2Wk98LKQ5sqYTyJSXCdWzhKB_5LmecBBIRJXmoJCMUCSU48xHCChFMkK0k5orREtj8zbai5Dzy4iBpe_uVgwZBmGNEmGMzIij-9-KLTnQSBpH0znKQnUvvsLFVQy4VeZ_THwOVdLA
ContentType Journal Article
DBID DBRKI
TDB
JDI
DEWEY 005.7
DatabaseName DBPIA - 디비피아
누리미디어 DBpia
[Open Access] KoreaScience
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
DocumentTitle_FL Individual Pig Detection Using Kinect Depth Information and Convolutional Neural Network
EISSN 2508-6723
EndPage 10
ExternalDocumentID JAKO201810256452931
NODE07399858
GroupedDBID .UV
ALMA_UNASSIGNED_HOLDINGS
DBRKI
TDB
JDI
ID FETCH-LOGICAL-k608-e31d4af9fca32976496fc0c78582da02fa8efa52309f985c001f021204fa18f53
ISSN 1598-4877
IngestDate Fri Dec 22 12:03:42 EST 2023
Thu Feb 06 13:25:24 EST 2025
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Issue 2
Keywords YOLO
Convolutional Neural Network
Individual Pig Detection
키넥트 깊이정보
욜로
컨볼루션 신경망
개별 돼지 탐지
Kinect Depth Information
Language Korean
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-k608-e31d4af9fca32976496fc0c78582da02fa8efa52309f985c001f021204fa18f53
Notes KISTI1.1003/JNL.JAKO201810256452931
OpenAccessLink http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO201810256452931&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
PageCount 10
ParticipantIDs kisti_ndsl_JAKO201810256452931
nurimedia_primary_NODE07399858
PublicationCentury 2000
PublicationDate 2018
PublicationDateYYYYMMDD 2018-01-01
PublicationDate_xml – year: 2018
  text: 2018
PublicationDecade 2010
PublicationTitle 한국콘텐츠학회논문지
PublicationTitleAlternate The Journal of the Korea Contents Association
PublicationYear 2018
Publisher 한국콘텐츠학회
Publisher_xml – name: 한국콘텐츠학회
SSID ssib005306162
ssib036279156
ssib001107260
ssib053377518
ssib030194663
ssib044738273
Score 1.6435341
Snippet Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology...
SourceID kisti
nurimedia
SourceType Open Access Repository
Publisher
StartPage 1
Title 키넥트 깊이 정보와 컨볼루션 신경망을 이용한 개별 돼지의 탐지
URI https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE07399858
http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO201810256452931&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
Volume 18
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpR1Na9RANNRe1IMoKn6WHJxTWUkmM5uZY5JNKRVbD1XqacnHxEplK9pF8CBF66Ue9FKo0oWCSutNbA-K9eqPabL_wfcmcZulgl-X7OzM-5r3Mpn35tMwrsQicpXkSYMrK2owqaBJUaEaKWWKSjtWaYz7na9PNydvsqk5Pjdy5Htt1VJ3Kb6aPP7lvpJ_sSrkgV1xl-xfWHZAFDIgDfaFJ1gYnn9kYxK2iKDEYyT0iWDE4zrHI74YJyH8SPwTBkS2iM_GMeVZRHIE9x3I0mUAZOky3yee-FkWYMJzdE5ABCdSaCDhIw0kTonf0kAu0i-5iJKL5qcTHvEkCgVMZVAKBRIEFRcNDqJPaH4BkhJWRUDzA4oOkdagrO5LD8hqqpx4WggfMTUirxB9oSUugUthPCK0CABTVVSDDXGBt3CoKqBlUZJpITgVU93OvMINUao2nDKMQpFDqQbfRpTFzp3uwiEUXytFmwXkGubSiu4ilxt6TfsQm8qUdSVLIhng3AY2j-aj8WBef8plfWin6oewGf6nAuv9mcTx4uqmHKXzwOkVjaZbbvM-3AkOxiLKHs2uuUbVAuTh88mnZ1ohTvdKwXHPPSZwBe2T8MArty2X1qJwDmGqfXBKJXQxeMnBoJsAl8qV9sERT4y5jqh52RCguDhZqE9CrqoHoSXGW3ePG0c7XbwXAz6uNT9x9qRxogrwTK9sraeMkYXF08at_tN3-cr7_upnc__LatHbNYvNtXxnt3i9bBZft_OdvfztdvF83SxebO5_-pZv9YreiglwxZsP_bUNc__jRr6zYuYv94qt5aK3bvafvYLUGWN2IpwNJhvVjSaNhSYoXTl2yqJMZknkUIgDmGxmiZW4oDmaRhbNIqGyCOdpZAbqTEB1GV7BYLEsskXGnbPGaGexo84ZpnIVjXmW8jijLJEyslKueKpoElkxdbLzxphWSLuTPrzXnvKuzeALZmOEg0stHBsABppq3y9PtmnXbXnhdwAXjWNIsxyPvGSMLj3oqsvgoS_FY9r-PwCxL7kR
linkProvider ISSN International Centre
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=%ED%82%A4%EB%84%A5%ED%8A%B8+%EA%B9%8A%EC%9D%B4+%EC%A0%95%EB%B3%B4%EC%99%80+%EC%BB%A8%EB%B3%BC%EB%A3%A8%EC%85%98+%EC%8B%A0%EA%B2%BD%EB%A7%9D%EC%9D%84+%EC%9D%B4%EC%9A%A9%ED%95%9C+%EA%B0%9C%EB%B3%84+%EB%8F%BC%EC%A7%80%EC%9D%98+%ED%83%90%EC%A7%80&rft.jtitle=%ED%95%9C%EA%B5%AD%EC%BD%98%ED%85%90%EC%B8%A0%ED%95%99%ED%9A%8C%EB%85%BC%EB%AC%B8%EC%A7%80&rft.au=%EC%9D%B4%EC%A4%80%ED%9D%AC%28Junhee+Lee%29&rft.au=%EC%9D%B4%EC%A2%85%EC%9A%B1%28Jonguk+Lee%29&rft.au=%EB%B0%95%EB%8C%80%ED%9D%AC%28Daihee+Park%29&rft.au=%EC%A0%95%EC%9A%A9%ED%99%94%28Yongwha+Chung%29&rft.date=2018&rft.pub=%ED%95%9C%EA%B5%AD%EC%BD%98%ED%85%90%EC%B8%A0%ED%95%99%ED%9A%8C&rft.issn=1598-4877&rft.eissn=2508-6723&rft.volume=18&rft.issue=2&rft.spage=1&rft.epage=10&rft.externalDocID=NODE07399858
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1598-4877&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1598-4877&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1598-4877&client=summon