The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture

GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. There...

Full description

Saved in:
Bibliographic Details
Main Authors: Skovsen, Soren, Dyrmann, Mads, Mortensen, Anders K., Laursen, Morten S., Gislum, Rene, Eriksen, Jorgen, Farkhani, Sadaf, Karstoft, Henrik, Jorgensen, Rasmus N.
Format: Conference Proceeding
Language:English
Subjects:
Agriculture
Biomass
Cameras
Image segmentation
Semantics
Soil
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c292t-ad0e23a3d6a6903c8f9e6622a1295463d425f299eac6ea1c4a56cca704a4da013
cites
container_end_page 2684
container_issue
container_start_page 2676
container_title
container_volume
creator Skovsen, Soren
Dyrmann, Mads
Mortensen, Anders K.
Laursen, Morten S.
Gislum, Rene
Eriksen, Jorgen
Farkhani, Sadaf
Karstoft, Henrik
Jorgensen, Rasmus N.
description GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. Therefore, the overall challenge is related to predicting the species composition in the canopy image and in the biomass. The dataset is collected with three different acquisition systems with ground sampling distances of 4-8 px/mm. The observed mixed crops vary both in setting (field vs plot trial), seed compositions, yield, years since establishment and time of the season. Synthetic training images with pixel-wise hierarchical and instance labels are provided for supervised training. 31 600 unlabeled images are additionally provided for pre-training, semi-supervised training or unsupervised training. Furthermore, this paper provides challenges of semantic segmentation and prediction of the biomass compositions and a baseline model for this dataset.
doi_str_mv 10.1109/CVPRW.2019.00325
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9025377</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9025377</ieee_id><sourcerecordid>9025377</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-ad0e23a3d6a6903c8f9e6622a1295463d425f299eac6ea1c4a56cca704a4da013</originalsourceid><addsrcrecordid>eNotzEFLwzAUwPEoCM65u-AlX6Dz5aVJl-Ooug0Gitv0OB_paxfpupF0wr69gp7-hx_8hbhTMFYK3EP5_vr2MUZQbgyg0VyIG1XgRKEBay7FAJWFrDDKXotRSl8AoGBijNMD8bnesZxFSqlsD98c5WJPDctH6ilxL-tDlCveU9cHL6mr5DxwpOh3wVMrV0f2gZPcdBXH1P966BoZOjltYvCntj9FvhVXNbWJR_8dis3z07qcZ8uX2aKcLjOPDvuMKmDUpCtL1oH2k9qxtYik0Jnc6ipHU6NzTN4yKZ-Tsd5TATnlFYHSQ3H_9w3MvD3GsKd43jpAo4tC_wALrlUN</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture</title><source>IEEE Xplore All Conference Series</source><creator>Skovsen, Soren ; Dyrmann, Mads ; Mortensen, Anders K. ; Laursen, Morten S. ; Gislum, Rene ; Eriksen, Jorgen ; Farkhani, Sadaf ; Karstoft, Henrik ; Jorgensen, Rasmus N.</creator><creatorcontrib>Skovsen, Soren ; Dyrmann, Mads ; Mortensen, Anders K. ; Laursen, Morten S. ; Gislum, Rene ; Eriksen, Jorgen ; Farkhani, Sadaf ; Karstoft, Henrik ; Jorgensen, Rasmus N.</creatorcontrib><description>GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. Therefore, the overall challenge is related to predicting the species composition in the canopy image and in the biomass. The dataset is collected with three different acquisition systems with ground sampling distances of 4-8 px/mm. The observed mixed crops vary both in setting (field vs plot trial), seed compositions, yield, years since establishment and time of the season. Synthetic training images with pixel-wise hierarchical and instance labels are provided for supervised training. 31 600 unlabeled images are additionally provided for pre-training, semi-supervised training or unsupervised training. Furthermore, this paper provides challenges of semantic segmentation and prediction of the biomass compositions and a baseline model for this dataset.</description><identifier>EISSN: 2160-7516</identifier><identifier>EISBN: 1728125065</identifier><identifier>EISBN: 9781728125060</identifier><identifier>DOI: 10.1109/CVPRW.2019.00325</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Agriculture ; Biomass ; Cameras ; Image segmentation ; Semantics ; Soil ; Training</subject><ispartof>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019, p.2676-2684</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-ad0e23a3d6a6903c8f9e6622a1295463d425f299eac6ea1c4a56cca704a4da013</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9025377$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,23909,23910,25118,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9025377$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Skovsen, Soren</creatorcontrib><creatorcontrib>Dyrmann, Mads</creatorcontrib><creatorcontrib>Mortensen, Anders K.</creatorcontrib><creatorcontrib>Laursen, Morten S.</creatorcontrib><creatorcontrib>Gislum, Rene</creatorcontrib><creatorcontrib>Eriksen, Jorgen</creatorcontrib><creatorcontrib>Farkhani, Sadaf</creatorcontrib><creatorcontrib>Karstoft, Henrik</creatorcontrib><creatorcontrib>Jorgensen, Rasmus N.</creatorcontrib><title>The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture</title><title>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</title><addtitle>CVPRW</addtitle><description>GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. Therefore, the overall challenge is related to predicting the species composition in the canopy image and in the biomass. The dataset is collected with three different acquisition systems with ground sampling distances of 4-8 px/mm. The observed mixed crops vary both in setting (field vs plot trial), seed compositions, yield, years since establishment and time of the season. Synthetic training images with pixel-wise hierarchical and instance labels are provided for supervised training. 31 600 unlabeled images are additionally provided for pre-training, semi-supervised training or unsupervised training. Furthermore, this paper provides challenges of semantic segmentation and prediction of the biomass compositions and a baseline model for this dataset.</description><subject>Agriculture</subject><subject>Biomass</subject><subject>Cameras</subject><subject>Image segmentation</subject><subject>Semantics</subject><subject>Soil</subject><subject>Training</subject><issn>2160-7516</issn><isbn>1728125065</isbn><isbn>9781728125060</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotzEFLwzAUwPEoCM65u-AlX6Dz5aVJl-Ooug0Gitv0OB_paxfpupF0wr69gp7-hx_8hbhTMFYK3EP5_vr2MUZQbgyg0VyIG1XgRKEBay7FAJWFrDDKXotRSl8AoGBijNMD8bnesZxFSqlsD98c5WJPDctH6ilxL-tDlCveU9cHL6mr5DxwpOh3wVMrV0f2gZPcdBXH1P966BoZOjltYvCntj9FvhVXNbWJR_8dis3z07qcZ8uX2aKcLjOPDvuMKmDUpCtL1oH2k9qxtYik0Jnc6ipHU6NzTN4yKZ-Tsd5TATnlFYHSQ3H_9w3MvD3GsKd43jpAo4tC_wALrlUN</recordid><startdate>20190601</startdate><enddate>20190601</enddate><creator>Skovsen, Soren</creator><creator>Dyrmann, Mads</creator><creator>Mortensen, Anders K.</creator><creator>Laursen, Morten S.</creator><creator>Gislum, Rene</creator><creator>Eriksen, Jorgen</creator><creator>Farkhani, Sadaf</creator><creator>Karstoft, Henrik</creator><creator>Jorgensen, Rasmus N.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20190601</creationdate><title>The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture</title><author>Skovsen, Soren ; Dyrmann, Mads ; Mortensen, Anders K. ; Laursen, Morten S. ; Gislum, Rene ; Eriksen, Jorgen ; Farkhani, Sadaf ; Karstoft, Henrik ; Jorgensen, Rasmus N.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-ad0e23a3d6a6903c8f9e6622a1295463d425f299eac6ea1c4a56cca704a4da013</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Agriculture</topic><topic>Biomass</topic><topic>Cameras</topic><topic>Image segmentation</topic><topic>Semantics</topic><topic>Soil</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Skovsen, Soren</creatorcontrib><creatorcontrib>Dyrmann, Mads</creatorcontrib><creatorcontrib>Mortensen, Anders K.</creatorcontrib><creatorcontrib>Laursen, Morten S.</creatorcontrib><creatorcontrib>Gislum, Rene</creatorcontrib><creatorcontrib>Eriksen, Jorgen</creatorcontrib><creatorcontrib>Farkhani, Sadaf</creatorcontrib><creatorcontrib>Karstoft, Henrik</creatorcontrib><creatorcontrib>Jorgensen, Rasmus N.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Skovsen, Soren</au><au>Dyrmann, Mads</au><au>Mortensen, Anders K.</au><au>Laursen, Morten S.</au><au>Gislum, Rene</au><au>Eriksen, Jorgen</au><au>Farkhani, Sadaf</au><au>Karstoft, Henrik</au><au>Jorgensen, Rasmus N.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture</atitle><btitle>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</btitle><stitle>CVPRW</stitle><date>2019-06-01</date><risdate>2019</risdate><spage>2676</spage><epage>2684</epage><pages>2676-2684</pages><eissn>2160-7516</eissn><eisbn>1728125065</eisbn><eisbn>9781728125060</eisbn><coden>IEEPAD</coden><abstract>GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. Therefore, the overall challenge is related to predicting the species composition in the canopy image and in the biomass. The dataset is collected with three different acquisition systems with ground sampling distances of 4-8 px/mm. The observed mixed crops vary both in setting (field vs plot trial), seed compositions, yield, years since establishment and time of the season. Synthetic training images with pixel-wise hierarchical and instance labels are provided for supervised training. 31 600 unlabeled images are additionally provided for pre-training, semi-supervised training or unsupervised training. Furthermore, this paper provides challenges of semantic segmentation and prediction of the biomass compositions and a baseline model for this dataset.</abstract><pub>IEEE</pub><doi>10.1109/CVPRW.2019.00325</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2160-7516
ispartof 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019, p.2676-2684
issn 2160-7516
language eng
recordid cdi_ieee_primary_9025377
source IEEE Xplore All Conference Series
subjects Agriculture
Biomass
Cameras
Image segmentation
Semantics
Soil
Training
title The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-23T21%3A11%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=The%20GrassClover%20Image%20Dataset%20for%20Semantic%20and%20Hierarchical%20Species%20Understanding%20in%20Agriculture&rft.btitle=2019%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)&rft.au=Skovsen,%20Soren&rft.date=2019-06-01&rft.spage=2676&rft.epage=2684&rft.pages=2676-2684&rft.eissn=2160-7516&rft.coden=IEEPAD&rft_id=info:doi/10.1109/CVPRW.2019.00325&rft.eisbn=1728125065&rft.eisbn_list=9781728125060&rft_dat=%3Cieee_CHZPO%3E9025377%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c292t-ad0e23a3d6a6903c8f9e6622a1295463d425f299eac6ea1c4a56cca704a4da013%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9025377&rfr_iscdi=true