A Deep learning method for accurate and fast identification of coral reef fishes in underwater images

Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our mode...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Ecological informatics Jg. 48; S. 238 - 244
Hauptverfasser:	Villon, Sébastien, Mouillot, David, Chaumont, Marc, Darling, Emily S., Subsol, Gérard, Claverie, Thomas, Villéger, Sébastien
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 01.11.2018 Elsevier
Schlagworte:	Artificial Intelligence Automated identification biodiversity Biodiversity and Ecology Computer Science Computer Vision and Pattern Recognition Convolutional neural network coral reefs corals Environmental Sciences fish humans Image Processing Machine Learning Marine fishes monitoring Neural and Evolutionary Computing protocols species identification Underwater pictures Automated identification Marine fishes Underwater pictures Convolutional neural network Machine learning Underwater images
ISSN:	1574-9541
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900,000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 s. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively. •Comparison between human experts and Deep Learning based method•Assessing the importance of post treatment with DL based methods•Importance of database adjustements•Real-life use cases for applied DL methods for fish identification
AbstractList	Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900,000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 s. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively. •Comparison between human experts and Deep Learning based method•Assessing the importance of post treatment with DL based methods•Importance of database adjustements•Real-life use cases for applied DL methods for fish identification Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900 000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 seconds. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively. Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900,000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 s. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively.
Author	Darling, Emily S. Claverie, Thomas Chaumont, Marc Mouillot, David Villon, Sébastien Subsol, Gérard Villéger, Sébastien
Author_xml	– sequence: 1 givenname: Sébastien surname: Villon fullname: Villon, Sébastien email: villon@lirmm.fr organization: MARBEC, University of Montpellier, CNRS, IRD, Ifremer, Montpellier, France – sequence: 2 givenname: David surname: Mouillot fullname: Mouillot, David organization: MARBEC, University of Montpellier, CNRS, IRD, Ifremer, Montpellier, France – sequence: 3 givenname: Marc orcidid: 0000-0002-4095-4410 surname: Chaumont fullname: Chaumont, Marc organization: LIRMM, University of Montpellier/CNRS, France – sequence: 4 givenname: Emily S. surname: Darling fullname: Darling, Emily S. organization: Department of Ecology and Evolutionary Biology, University of Toronto, Toronto, Canada – sequence: 5 givenname: Gérard surname: Subsol fullname: Subsol, Gérard organization: LIRMM, University of Montpellier/CNRS, France – sequence: 6 givenname: Thomas orcidid: 0000-0002-6258-4991 surname: Claverie fullname: Claverie, Thomas organization: MARBEC, University of Montpellier, CNRS, IRD, Ifremer, Montpellier, France – sequence: 7 givenname: Sébastien surname: Villéger fullname: Villéger, Sébastien organization: MARBEC, University of Montpellier, CNRS, IRD, Ifremer, Montpellier, France
BackLink	https://hal-lirmm.ccsd.cnrs.fr/lirmm-01884005$$DView record in HAL
BookMark	eNqFkDtrHDEQgFU4EL_-gQuVgXAbabXPFIHDeThwkMauxaw08s2xK10knYP_feRs0qRIKsHwfaPhu2BnPnhk7EaKSgrZvTtUaAJ5V9VCDpUYKyH6M3Yu277ZjG0jX7OLlA5CNGoY6nOGW_4R8chnhOjJP_IF8z5Y7kLkYMwpQkYOvgwgZU4WfSZHBjIFz4PjJkSYeUR03FHaY-Lk-clbjD-KGTkt8Ijpir1yMCe8_v1esofPn-5v7za7b1--3m53G9PUMpf76knItnZGNbLtADo5guprB0NvR9s3rh3bEYyq7TQZZadhNAr7abB26ERn1SV7u-7dw6yPsXwen3UA0nfbnZ4pLosuVYZGiPZJFvrNSh9j-H7ClPVCyeA8g8dwSrqWrepUX-CCvl9RE0NKEZ02lH9FyBFo1lLol_r6oNf6-qW-FqMu9Yvc_CX_Oe0_2odVw1LsiTDqZAi9QUsRTdY20L8X_AT3_aVb
CitedBy_id	crossref_primary_10_1002_ece3_72091 crossref_primary_10_1016_j_ecoinf_2025_103065 crossref_primary_10_1111_1365_2664_14725 crossref_primary_10_3390_s25061846 crossref_primary_10_1007_s11042_022_13437_3 crossref_primary_10_1016_j_dsp_2025_105131 crossref_primary_10_1016_j_ecoinf_2024_102499 crossref_primary_10_1007_s10462_021_10025_z crossref_primary_10_1016_j_microb_2025_100299 crossref_primary_10_1016_j_ecoinf_2024_102535 crossref_primary_10_1098_rsos_231678 crossref_primary_10_1007_s11042_022_12535_6 crossref_primary_10_3390_jmse12122326 crossref_primary_10_1016_j_fishres_2023_106916 crossref_primary_10_3389_fmars_2021_649123 crossref_primary_10_1002_cbdv_202201123 crossref_primary_10_1111_mms_13137 crossref_primary_10_3390_fishes8040182 crossref_primary_10_1007_s00227_023_04300_6 crossref_primary_10_1007_s10452_022_09988_0 crossref_primary_10_3390_su13116037 crossref_primary_10_3390_agriculture12121972 crossref_primary_10_1016_j_eswa_2025_128585 crossref_primary_10_1371_journal_pone_0263377 crossref_primary_10_1111_rec_13806 crossref_primary_10_1016_j_atech_2023_100289 crossref_primary_10_3390_electronics14152954 crossref_primary_10_1111_jfb_15793 crossref_primary_10_1371_journal_pbio_3001640 crossref_primary_10_1016_j_aquaculture_2022_738334 crossref_primary_10_1007_s10499_025_02069_7 crossref_primary_10_1371_journal_pone_0249593 crossref_primary_10_3389_fmars_2025_1476616 crossref_primary_10_3389_fmars_2021_658135 crossref_primary_10_1016_j_ecolind_2025_114025 crossref_primary_10_1111_geb_13025 crossref_primary_10_1016_j_eswa_2023_121841 crossref_primary_10_1016_j_ecoinf_2023_102371 crossref_primary_10_1111_faf_12666 crossref_primary_10_1016_j_envsoft_2024_106170 crossref_primary_10_1038_s41597_024_04267_z crossref_primary_10_1371_journal_pone_0324067 crossref_primary_10_1109_TNNLS_2022_3143887 crossref_primary_10_3389_fmars_2022_918504 crossref_primary_10_1002_rse2_205 crossref_primary_10_1016_j_procs_2025_03_104 crossref_primary_10_1007_s11831_020_09486_2 crossref_primary_10_3354_meps14631 crossref_primary_10_7717_peerj_13396 crossref_primary_10_3390_app142210122 crossref_primary_10_1016_j_ecoinf_2023_102108 crossref_primary_10_1109_ACCESS_2024_3468438 crossref_primary_10_7717_peerj_cs_2618 crossref_primary_10_1016_j_ecoinf_2025_103409 crossref_primary_10_21303_2461_4262_2022_002345 crossref_primary_10_1016_j_inffus_2022_12_012 crossref_primary_10_1002_rse2_209 crossref_primary_10_1016_j_atech_2022_100087 crossref_primary_10_1145_3575801 crossref_primary_10_3389_fevo_2024_1359201 crossref_primary_10_1093_icesjms_fsae194 crossref_primary_10_1111_eth_13143 crossref_primary_10_3389_fmars_2023_1151758 crossref_primary_10_1371_journal_pone_0284992 crossref_primary_10_3390_electronics10222882 crossref_primary_10_3354_meps14003 crossref_primary_10_1016_j_aquaeng_2020_102117 crossref_primary_10_1111_ele_14311 crossref_primary_10_1002_ece3_7656 crossref_primary_10_1002_2688_8319_12099 crossref_primary_10_1016_j_biocon_2022_109494 crossref_primary_10_1111_2041_210X_13901 crossref_primary_10_3390_su14127154 crossref_primary_10_1002_aqc_3432 crossref_primary_10_1016_j_anbehav_2021_04_018 crossref_primary_10_3389_fmars_2022_944582 crossref_primary_10_1016_j_ocecoaman_2025_107762 crossref_primary_10_1016_j_jenvman_2019_07_024 crossref_primary_10_3390_jmse8110924 crossref_primary_10_1016_j_dsr_2025_104517 crossref_primary_10_3390_app13063812 crossref_primary_10_1016_j_greeac_2023_100049 crossref_primary_10_1002_lom3_10557 crossref_primary_10_1007_s10115_023_01987_3 crossref_primary_10_1186_s13634_022_00950_8 crossref_primary_10_1016_j_aquaeng_2025_102570 crossref_primary_10_1016_j_fishres_2021_106033 crossref_primary_10_3390_s20030726 crossref_primary_10_1007_s11042_022_14318_5 crossref_primary_10_3390_electronics11213459 crossref_primary_10_1016_j_ecoinf_2022_101873 crossref_primary_10_3390_electronics11172701 crossref_primary_10_1007_s10452_022_09967_5 crossref_primary_10_3390_ani14030499 crossref_primary_10_1111_raq_12464 crossref_primary_10_1016_j_ecoinf_2022_101593 crossref_primary_10_1371_journal_pntd_0008904 crossref_primary_10_1007_s11042_024_18951_0 crossref_primary_10_1016_j_ecoinf_2023_102165 crossref_primary_10_1371_journal_pone_0267759 crossref_primary_10_1016_j_ecoinf_2023_102163 crossref_primary_10_1007_s11042_020_09371_x crossref_primary_10_1016_j_marpolbul_2024_116273 crossref_primary_10_3389_fmars_2020_00429 crossref_primary_10_3390_info15080437 crossref_primary_10_1002_lom3_10607 crossref_primary_10_3390_rs17152707 crossref_primary_10_1109_ACCESS_2023_3343120 crossref_primary_10_3390_s22020497 crossref_primary_10_3389_fmars_2021_640619 crossref_primary_10_1002_aqc_3254 crossref_primary_10_1002_ece3_11070 crossref_primary_10_3390_fishes7060335 crossref_primary_10_1088_2632_2153_ad65b5 crossref_primary_10_3389_fmars_2024_1356356 crossref_primary_10_1007_s11694_024_02381_5 crossref_primary_10_1371_journal_pone_0216030 crossref_primary_10_1016_j_aquaculture_2021_736724 crossref_primary_10_1016_j_marpol_2022_105015 crossref_primary_10_1007_s10661_020_08653_z crossref_primary_10_1111_raq_12726 crossref_primary_10_1155_2023_3224064 crossref_primary_10_3389_fmars_2021_823173 crossref_primary_10_1007_s10499_021_00684_8 crossref_primary_10_4173_mic_2021_1_1 crossref_primary_10_1016_j_eti_2022_102865 crossref_primary_10_1016_j_ecoinf_2024_102959 crossref_primary_10_3389_fmars_2023_1157370 crossref_primary_10_1111_2041_210X_13256 crossref_primary_10_1016_j_heliyon_2023_e16761 crossref_primary_10_3390_app12063158 crossref_primary_10_1007_s10462_021_10102_3 crossref_primary_10_1016_j_fishres_2021_106166 crossref_primary_10_1007_s00371_024_03630_w crossref_primary_10_1038_s41598_020_67573_7 crossref_primary_10_3390_jmse10121841 crossref_primary_10_1002_aqc_4040 crossref_primary_10_1007_s10462_025_11180_3 crossref_primary_10_1016_j_ecolind_2021_107957 crossref_primary_10_1016_j_quascirev_2022_107877 crossref_primary_10_1016_j_ecoinf_2021_101269 crossref_primary_10_1007_s10462_024_11074_w crossref_primary_10_3390_app12115401 crossref_primary_10_3390_d14100824 crossref_primary_10_1109_ACCESS_2022_3227046 crossref_primary_10_1016_j_fishres_2023_106924 crossref_primary_10_1111_cobi_13798 crossref_primary_10_3389_fmars_2023_1126301
Cites_doi	10.1145/2647868.2654889 10.1016/j.fishres.2010.10.011 10.1071/MF03130 10.1126/science.1059199 10.1007/BF00001740 10.1007/s00227-005-0090-6 10.2307/3797016 10.1016/j.visres.2007.12.009 10.1073/pnas.1708001115 10.1126/science.1085706 10.3354/meps07192 10.1371/journal.pbio.2000537 10.1080/10236240701393263 10.1111/mec.14350 10.1371/journal.pone.0081847 10.1098/rspb.2015.2694 10.1145/1877868.1877881 10.1109/ICCV.1999.790410 10.1111/2041-210X.12320 10.3844/jcssp.2010.1088.1094 10.1071/MF00010 10.1111/j.1095-8649.2001.tb00202.x 10.1038/nature18607 10.1038/nature22901 10.1038/nature14539 10.1126/science.1149345 10.4031/MTSJ.50.1.1 10.1016/j.fishres.2014.01.019 10.1111/gcb.13482 10.1007/BF00304730 10.1111/j.1461-0248.2011.01592.x 10.3354/ab00235 10.1016/j.neunet.2014.09.003 10.1016/j.ecoinf.2016.11.003 10.1111/1365-2664.13051
ContentType	Journal Article
Copyright	2018 Elsevier B.V. Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: 2018 Elsevier B.V. – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	AAYXX CITATION 7S9 L.6 1XC VOOES
DOI	10.1016/j.ecoinf.2018.09.007
DatabaseName	CrossRef AGRICOLA AGRICOLA - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef AGRICOLA AGRICOLA - Academic
DatabaseTitleList	AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	Ecology Computer Science Environmental Sciences
EndPage	244
ExternalDocumentID	oai:HAL:lirmm-01884005v1 10_1016_j_ecoinf_2018_09_007 S1574954118300694
GroupedDBID	--K --M .~1 0R~ 0SF 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ AABVA AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AATLK AAXUO ABFNM ABFYP ABGRD ABJNI ABLST ABMAC ABXDB ABYKQ ACDAQ ACGFS ACRLP ADBBV ADEZE ADMUD ADQTV AEBSH AEKER AENEX AEQOU AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AIEXJ AIKHN AITUG AJBFU AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BKOJK BLECG BLXMC CBWCG CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FIRID FNPLU FYGXN G-Q GBLVA HVGLF HZ~ IHE J1W KCYFY KOM M41 MO0 N9A N~3 O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SES SPCBC SSA SSJ SSZ T5K ~G- 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS GROUPED_DOAJ M~E ~HD 7S9 L.6 1XC VOOES
ID	FETCH-LOGICAL-c421t-952b0152fc34156aa619a372fa87d9d74f5959ac32dbbc3db89c3e7b8dd8606d3
ISICitedReferencesCount	176
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000453641900023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1574-9541
IngestDate	Tue Oct 14 20:06:52 EDT 2025 Sun Sep 28 09:23:02 EDT 2025 Sat Nov 29 03:11:31 EST 2025 Tue Nov 18 22:37:52 EST 2025 Fri Feb 23 02:26:31 EST 2024
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	Automated identification Marine fishes Underwater pictures Convolutional neural network Machine learning Underwater images
Language	English
License	Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c421t-952b0152fc34156aa619a372fa87d9d74f5959ac32dbbc3db89c3e7b8dd8606d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-4095-4410 0000-0002-6258-4991 0000-0003-0402-2605 0000-0002-1048-2838 0000-0002-7461-4932 0000-0002-2362-7178
OpenAccessLink	https://hal-lirmm.ccsd.cnrs.fr/lirmm-01884005
PQID	2153637005
PQPubID	24069
PageCount	7
ParticipantIDs	hal_primary_oai_HAL_lirmm_01884005v1 proquest_miscellaneous_2153637005 crossref_citationtrail_10_1016_j_ecoinf_2018_09_007 crossref_primary_10_1016_j_ecoinf_2018_09_007 elsevier_sciencedirect_doi_10_1016_j_ecoinf_2018_09_007
PublicationCentury	2000
PublicationDate	2018-11-01
PublicationDateYYYYMMDD	2018-11-01
PublicationDate_xml	– month: 11 year: 2018 text: 2018-11-01 day: 01
PublicationDecade	2010
PublicationTitle	Ecological informatics
PublicationYear	2018
Publisher	Elsevier B.V Elsevier
Publisher_xml	– name: Elsevier B.V – name: Elsevier
References	Lecun, Bengio, Hinton (bb0125) 2015; 521 Szegedy, Liu, Jia, Sermanet, Reed, Anguelov, Rabinovich (bb0225) 2015 Shortis, Ravanbakhsh, Shafait, Mian (bb0205) 2016; 50 Kulbicki, Parravicini, Bellwood, Arias-Gonzàlez, Chabanet, Floeter, Mouillot (bb0115) 2013; 8 Deiner, Bik, Mächler, Seymour, Lacoursière-Roussel, Altermatt, Pfrender (bb0040) 2017; 26 Rogers, Blanchard, Mumby (bb0185) 2017; 55 Willis (bb0260) 2001; 59 Joly, Goëau, Glotin, Spampinato, Bonnet, Vellinga, Müller (bb0100) 2016, September Pelletier, Leleu, Mou-Tham, Guillemot, Chabanet (bb0170) 2011; 107 Matabos, Hoeberechts, Doya, Aguzzi, Nephin, Reimchen, Fernandez-Arcaya (bb0150) 2017 Graham, Chabanet, Evans, Jennings, Letourneur, Aaron MacNeil, Wilson (bb0055) 2011; 14 National Academy of Sciences, 201708001. Alsmadi, Omar, Noah, Almarashdeh (bb0005) 2010; 6 Hughes, Barnes, Bellwood, Cinner, Cumming, Jackson, Palumbi (bb0080) 2017; 546 Willis, Babcock (bb0265) 2000; 51 Langlois, Harvey, Fitzpatrick, Meeuwig, Shedrawi, Watson (bb0120) 2010; 9 ( Siddiqui, Salman, Malik, Shafait, Mian, Shortis, Harvey (bb0210) 2017 Froese, Pauly (bb0050) 2000 Thresher, Gunn (bb0235) 1986; 17 Krizhevsky, Sutskever, Hinton (bb0105) 2012 Mouillot, Villéger, Parravicini, Kulbicki, Arias-González, Bender, Bellwood (bb0155) 2014; 111(38) Chapman, Atkinson (bb0025) 1986; 11 Harvey, Fletcher, Shortis, Kendrick (bb0065) 2004; 55 Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on (Vol. 2, pp. 1150–1157). Ieee. Li, X., Shang, M., Qin, H., & Chen, L. (2015, October). Fast accurate fish detection and recognition of underwater images with fast r-cnn. In (pp. 1–5). IEEE. Scott, Dixson (bb0200) 2016; 283 Cinner, J. E., Maire, E., Huchery, C., MacNeil, M. A., Graham, N. A., Mora, C., ... & D'Agata, S. (2018). Gravity of Human Impacts Mediates Coral Reef Conservation Gains. Robinson, Williams, Edwards, McPherson, Yeager, Vigliola, Baum (bb0180) 2017; 23 Cinner, Huchery, MacNeil, Graham, McClanahan, Maina, Allison (bb0030) 2016; 535 (pp. 675–678). ACM. Schmidhuber (bb0195) 2015; 61 Harvey, Cappo, Butler, Hall, Kendrick (bb0070) 2007; 350 Francour, Liret, Harvey (bb0045) 1999; 23 2018). Sale, Sharp (bb0190) 1983; 2 Spampinato, C., Giordano, D., Di Salvo, R., Chen-Burger, Y. H. J., Fisher, R. B., & Nadarajan, G. (2010, October). Automatic fish classification for underwater species behavior understanding. In Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams (pp. 45–50). ACM. Taquet, Diringer (bb0230) 2007 Mallet, Pelletier (bb0145) 2014; 154 Norman, Holmberg, Arzoumanian, Reynolds, Wilson, Rob, Pierce, Gleiss, de la Parra, Galvan, Ramirez-Macias, Robinson, Fox, Graham, Rowat, Potenski, Levine, Mckinney, Hoffmayer, Dove, Hueter, Ponzo, Araujo, Aca, David, Rees, Duncan, Rohner, Prebble, Hearn, Acuna, Berumen, Vázquez, Green, Bach, Schmidt, Beatty, Morgan (bb0160) 2017; 10 Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., ... & Darrell, T. (2014, November). Caffe: Convolutional architecture for fast feature embedding. In Villon, Chaumont, Subsol, Villéger, Claverie, Mouillot (bb0240) 2016, October Watson, Harvey (bb0245) 2007; 40 Weinstein (bb0255) 2015; 6 Krueck, Ahmadia, Possingham, Riginos, Treml, Mumby (bb0110) 2017; 15 Jackson, Kirby, Berger, Bjorndal, Botsford, Bourque, Hughes (bb0085) 2001; 293 Watson, Harvey, Anderson, Kendrick (bb0250) 2005; 148 Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (bb0220) 2014; 15 Brock (bb0015) 1954; 18 Price Tack (bb0175) 2016; 36 Blanc, Lingrand, Precioso (bb0010) 2014, November Pandolfi, Bradbury, Sala, Hughes, Bjorndal, Cooke, Warner (bb0165) 2003; 301 Levi (bb0130) 2008; 48 Cappo, Harvey, Malcolm, Speare (bb0020) 2003 Halpern, Walbridge, Selkoe, Kappel, Micheli, D'Agrosa, Fujita (bb0060) 2008; 319 Francour (10.1016/j.ecoinf.2018.09.007_bb0045) 1999; 23 Shortis (10.1016/j.ecoinf.2018.09.007_bb0205) 2016; 50 10.1016/j.ecoinf.2018.09.007_bb0035 Pelletier (10.1016/j.ecoinf.2018.09.007_bb0170) 2011; 107 10.1016/j.ecoinf.2018.09.007_bb0075 Villon (10.1016/j.ecoinf.2018.09.007_bb0240) 2016 Taquet (10.1016/j.ecoinf.2018.09.007_bb0230) 2007 Mouillot (10.1016/j.ecoinf.2018.09.007_bb0155) 2014; 111(38) Jackson (10.1016/j.ecoinf.2018.09.007_bb0085) 2001; 293 Willis (10.1016/j.ecoinf.2018.09.007_bb0265) 2000; 51 Levi (10.1016/j.ecoinf.2018.09.007_bb0130) 2008; 48 Halpern (10.1016/j.ecoinf.2018.09.007_bb0060) 2008; 319 Sale (10.1016/j.ecoinf.2018.09.007_bb0190) 1983; 2 Joly (10.1016/j.ecoinf.2018.09.007_bb0100) 2016 Hughes (10.1016/j.ecoinf.2018.09.007_bb0080) 2017; 546 Harvey (10.1016/j.ecoinf.2018.09.007_bb0070) 2007; 350 Krueck (10.1016/j.ecoinf.2018.09.007_bb0110) 2017; 15 Mallet (10.1016/j.ecoinf.2018.09.007_bb0145) 2014; 154 Pandolfi (10.1016/j.ecoinf.2018.09.007_bb0165) 2003; 301 Weinstein (10.1016/j.ecoinf.2018.09.007_bb0255) 2015; 6 Langlois (10.1016/j.ecoinf.2018.09.007_bb0120) 2010; 9 Alsmadi (10.1016/j.ecoinf.2018.09.007_bb0005) 2010; 6 10.1016/j.ecoinf.2018.09.007_bb0095 Harvey (10.1016/j.ecoinf.2018.09.007_bb0065) 2004; 55 Watson (10.1016/j.ecoinf.2018.09.007_bb0250) 2005; 148 Rogers (10.1016/j.ecoinf.2018.09.007_bb0185) 2017; 55 Blanc (10.1016/j.ecoinf.2018.09.007_bb0010) 2014 10.1016/j.ecoinf.2018.09.007_bb0135 Kulbicki (10.1016/j.ecoinf.2018.09.007_bb0115) 2013; 8 Graham (10.1016/j.ecoinf.2018.09.007_bb0055) 2011; 14 Cinner (10.1016/j.ecoinf.2018.09.007_bb0030) 2016; 535 Willis (10.1016/j.ecoinf.2018.09.007_bb0260) 2001; 59 10.1016/j.ecoinf.2018.09.007_bb0215 Froese (10.1016/j.ecoinf.2018.09.007_bb0050) 2000 Siddiqui (10.1016/j.ecoinf.2018.09.007_bb0210) 2017 Krizhevsky (10.1016/j.ecoinf.2018.09.007_bb0105) 2012 Srivastava (10.1016/j.ecoinf.2018.09.007_bb0220) 2014; 15 Brock (10.1016/j.ecoinf.2018.09.007_bb0015) 1954; 18 10.1016/j.ecoinf.2018.09.007_bb0140 Robinson (10.1016/j.ecoinf.2018.09.007_bb0180) 2017; 23 Lecun (10.1016/j.ecoinf.2018.09.007_bb0125) 2015; 521 Price Tack (10.1016/j.ecoinf.2018.09.007_bb0175) 2016; 36 Deiner (10.1016/j.ecoinf.2018.09.007_bb0040) 2017; 26 Schmidhuber (10.1016/j.ecoinf.2018.09.007_bb0195) 2015; 61 Norman (10.1016/j.ecoinf.2018.09.007_bb0160) 2017; 10 Cappo (10.1016/j.ecoinf.2018.09.007_bb0020) 2003 Scott (10.1016/j.ecoinf.2018.09.007_bb0200) 2016; 283 Thresher (10.1016/j.ecoinf.2018.09.007_bb0235) 1986; 17 Matabos (10.1016/j.ecoinf.2018.09.007_bb0150) 2017 Watson (10.1016/j.ecoinf.2018.09.007_bb0245) 2007; 40 Szegedy (10.1016/j.ecoinf.2018.09.007_bb0225) 2015 Chapman (10.1016/j.ecoinf.2018.09.007_bb0025) 1986; 11
References_xml	– volume: 293 start-page: 629 year: 2001 end-page: 637 ident: bb0085 article-title: Historical overfishing and the recent collapse of coastal ecosystems publication-title: Science – volume: 10 start-page: 298 year: 2017 end-page: 304 ident: bb0160 article-title: Undersea Constellations: the Global Biology of an Endangered Marine Megavertebrate further Informed through Citizen Science publication-title: Bioscience – volume: 350 start-page: 245 year: 2007 end-page: 254 ident: bb0070 article-title: Bait attraction affects the performance of remote underwater video stations in assessment of demersal fish community structure publication-title: Mar. Ecol. Prog. Ser. – reference: (pp. 675–678). ACM. – volume: 55 start-page: 1041 year: 2017 end-page: 1049 ident: bb0185 article-title: Fisheries productivity under progressive coral reef degradation publication-title: J. Appl. Ecol. – reference: ( – reference: Cinner, J. E., Maire, E., Huchery, C., MacNeil, M. A., Graham, N. A., Mora, C., ... & D'Agata, S. (2018). Gravity of Human Impacts Mediates Coral Reef Conservation Gains. – volume: 51 start-page: 755 year: 2000 end-page: 763 ident: bb0265 article-title: A baited underwater video system for the determination of relative density of carnivorous reef fish publication-title: Mar. Freshw. Res. – volume: 18 start-page: 297 year: 1954 end-page: 308 ident: bb0015 article-title: A preliminary report on a method of estimating reef fish populations publication-title: J. Wildl. Manag. – volume: 23 start-page: 155 year: 1999 end-page: 168 ident: bb0045 article-title: Comparison of fish abundance estimates made by remote underwater video and visual census publication-title: Naturalista sicil – volume: 535 start-page: 416 year: 2016 ident: bb0030 article-title: Bright spots among the world's coral reefs publication-title: Nature – reference: Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on (Vol. 2, pp. 1150–1157). Ieee. – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: bb0220 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: The Journal of Machine Learning Research – year: 2007 ident: bb0230 article-title: Poissons de l'océan Indien et de la mer Rouge – year: 2016, October ident: bb0240 article-title: Coral reef fish detection and recognition in underwater videos by supervised machine learning: Comparison between Deep Learning and HOG+ SVM methods publication-title: International Conference on Advanced Concepts for Intelligent Vision Systems (pp. 160–171) – start-page: 1097 year: 2012 end-page: 1105 ident: bb0105 article-title: Imagenet Classification with Deep Convolutional Neural Networks. InAdvances in Neural Information Processing Systems – volume: 111(38) start-page: 13757 year: 2014 end-page: 13762 ident: bb0155 article-title: Functional over-redundancy and high functional vulnerability in global fish faunas on tropical reefs publication-title: Proceedings of the National Academy of Sciences – volume: 48 start-page: 635 year: 2008 end-page: 654 ident: bb0130 article-title: Crowding—an essential bottleneck for object recognition: a mini-review publication-title: Vis. Res. – volume: 55 start-page: 573 year: 2004 end-page: 580 ident: bb0065 article-title: A comparison of underwater visual distance estimates made by scuba divers and a stereo-video system: implications for underwater visual census of reef fish abundance publication-title: Mar. Freshw. Res. – reference: Li, X., Shang, M., Qin, H., & Chen, L. (2015, October). Fast accurate fish detection and recognition of underwater images with fast r-cnn. In (pp. 1–5). IEEE. – start-page: 286 year: 2016, September end-page: 310 ident: bb0100 article-title: LifeCLEF 2016: multimedia life species identification challenges publication-title: International Conference of the Cross-Language Evaluation Forum for European Languages – volume: 26 start-page: 5872 year: 2017 end-page: 5895 ident: bb0040 article-title: Environmental DNA metabarcoding: Transforming how we survey animal and plant communities publication-title: Mol. Ecol. – start-page: fsx109 year: 2017 ident: bb0210 article-title: Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data publication-title: ICES J. Mar. Sci. – volume: 2 start-page: 37 year: 1983 end-page: 42 ident: bb0190 article-title: Correction for bias in visual transect censuses of coral reef fishes publication-title: Coral Reefs – volume: 9 start-page: 155 year: 2010 end-page: 168 ident: bb0120 article-title: Cost-efficient sampling of fish assemblages: comparison of baited video sta=tions and diver video transects publication-title: Aquat. Biol. – reference: 2018). – reference: Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., ... & Darrell, T. (2014, November). Caffe: Convolutional architecture for fast feature embedding. In – volume: 17 start-page: 93 year: 1986 end-page: 116 ident: bb0235 article-title: Comparative analysis of visual census techniques for highly mobile, reef-associated piscivores (Carangidae) publication-title: Environ. Biol. Fish – start-page: 1 year: 2014, November end-page: 6 ident: bb0010 article-title: Fish species recognition from video using SVM classifier. In Proceedings of the 3rd ACM International Workshop on Multimedia Analysis for Ecological Data – volume: 6 start-page: 1088 year: 2010 ident: bb0005 article-title: Fish recognition based on robust features extraction from size and shape measurements using neural network publication-title: J. Comput. Sci. – volume: 8 year: 2013 ident: bb0115 article-title: Global biogeography of reef fishes: a hierarchical quantitative delineation of regions publication-title: PLoS One – start-page: 1 year: 2015 end-page: 9 ident: bb0225 article-title: Going Deeper with Convolutions. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 455 year: 2003 end-page: 464 ident: bb0020 article-title: Potential of Video Techniques to Monitor Diversity, Abundance and Size of Fish in Studies of Marine Protected Areas. Aquatic Protected Areas-What Works Best and how Do we Know – volume: 40 start-page: 85 year: 2007 end-page: 103 ident: bb0245 article-title: Behaviour of temperate and sub-tropical reef fishes towards a stationary SCUBA diver publication-title: Mar. Freshw. Behav. Physiol. – volume: 6 start-page: 357 year: 2015 end-page: 362 ident: bb0255 article-title: MotionMeerkat: Integrating motion video detection and ecological monitoring (S Dray, Ed.) publication-title: Methods Ecol. Evol. – volume: 107 start-page: 84 year: 2011 end-page: 93 ident: bb0170 article-title: Comparison of visual census and high definition video transects for monitoring coral reef fish assemblages publication-title: Fish. Res. – volume: 301 start-page: 955 year: 2003 end-page: 958 ident: bb0165 article-title: Global trajectories of the long-term decline of coral reef ecosystems publication-title: Science – volume: 319 start-page: 948 year: 2008 end-page: 952 ident: bb0060 article-title: A global map of human impact on marine ecosystems publication-title: Science – year: 2000 ident: bb0050 article-title: FishBase 2000: Concepts Designs and Data Sources(Vol. 1594) – volume: 283 year: 2016 ident: bb0200 article-title: Reef fishes can recognize bleached habitat during settlement: sea anemone bleaching alters anemonefish host selection publication-title: Proc. R. Soc. B – volume: 546 start-page: 82 year: 2017 ident: bb0080 article-title: Coral reefs in the Anthropocene publication-title: Nature – volume: 23 start-page: 1009 year: 2017 end-page: 1022 ident: bb0180 article-title: Fishing degrades size structure of coral reef fish communities publication-title: Glob. Chang. Biol. – year: 2017 ident: bb0150 article-title: Expert, Crowd publication-title: Students or Algorithm: Who Holds the Key to Deep-Sea Imagery ‘Big data'processing?.Methods in Ecology and Evolution – reference: Spampinato, C., Giordano, D., Di Salvo, R., Chen-Burger, Y. H. J., Fisher, R. B., & Nadarajan, G. (2010, October). Automatic fish classification for underwater species behavior understanding. In Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams (pp. 45–50). ACM. – volume: 11 start-page: l year: 1986 end-page: 14 ident: bb0025 article-title: Fish behaviour in relation to divers publication-title: Prog Underw Sci – volume: 36 start-page: 145 year: 2016 end-page: 151 ident: bb0175 article-title: AnimalFinder: a semi-automated system for animal detection in time-lapse camera trap images publication-title: Ecol. Inform. – volume: 154 start-page: 44 year: 2014 end-page: 62 ident: bb0145 article-title: Underwater video techniques for observing coastal marine biodiversity: a review of sixty years of publications (1952–2012) publication-title: Fish. Res. – volume: 148 start-page: 415 year: 2005 end-page: 425 ident: bb0250 article-title: A comparison of temperate reef fish assemblages recorded by three underwater stereo-video techniques publication-title: Mar. Biol. – volume: 61 start-page: 85 year: 2015 end-page: 117 ident: bb0195 article-title: Deep learning in neural networks: an overview publication-title: Neural Netw. – volume: 50 start-page: 4 year: 2016 end-page: 16 ident: bb0205 article-title: Progress in the automated identification, measurement, and counting of fish in underwater image sequences publication-title: Mar. Technol. Soc. J. – reference: National Academy of Sciences, 201708001. – volume: 15 year: 2017 ident: bb0110 article-title: Marine reserve targets to sustain and rebuild unregulated fisheries publication-title: PLoS Biol. – volume: 59 start-page: 1408 year: 2001 end-page: 1411 ident: bb0260 article-title: Visual census methods underestimate density and diversity of cryptic reef fishes publication-title: J. Fish Biol. – volume: 521 start-page: 436 year: 2015 ident: bb0125 article-title: Deep learning publication-title: Nature – volume: 14 start-page: 341 year: 2011 end-page: 348 ident: bb0055 article-title: Extinction vulnerability of coral reef fishes publication-title: Ecol. Lett. – ident: 10.1016/j.ecoinf.2018.09.007_bb0095 doi: 10.1145/2647868.2654889 – volume: 107 start-page: 84 issue: 1 year: 2011 ident: 10.1016/j.ecoinf.2018.09.007_bb0170 article-title: Comparison of visual census and high definition video transects for monitoring coral reef fish assemblages publication-title: Fish. Res. doi: 10.1016/j.fishres.2010.10.011 – volume: 55 start-page: 573 issue: 6 year: 2004 ident: 10.1016/j.ecoinf.2018.09.007_bb0065 article-title: A comparison of underwater visual distance estimates made by scuba divers and a stereo-video system: implications for underwater visual census of reef fish abundance publication-title: Mar. Freshw. Res. doi: 10.1071/MF03130 – volume: 293 start-page: 629 issue: 5530 year: 2001 ident: 10.1016/j.ecoinf.2018.09.007_bb0085 article-title: Historical overfishing and the recent collapse of coastal ecosystems publication-title: Science doi: 10.1126/science.1059199 – volume: 17 start-page: 93 issue: 2 year: 1986 ident: 10.1016/j.ecoinf.2018.09.007_bb0235 article-title: Comparative analysis of visual census techniques for highly mobile, reef-associated piscivores (Carangidae) publication-title: Environ. Biol. Fish doi: 10.1007/BF00001740 – volume: 148 start-page: 415 year: 2005 ident: 10.1016/j.ecoinf.2018.09.007_bb0250 article-title: A comparison of temperate reef fish assemblages recorded by three underwater stereo-video techniques publication-title: Mar. Biol. doi: 10.1007/s00227-005-0090-6 – start-page: 1 year: 2015 ident: 10.1016/j.ecoinf.2018.09.007_bb0225 – year: 2007 ident: 10.1016/j.ecoinf.2018.09.007_bb0230 – volume: 18 start-page: 297 issue: 3 year: 1954 ident: 10.1016/j.ecoinf.2018.09.007_bb0015 article-title: A preliminary report on a method of estimating reef fish populations publication-title: J. Wildl. Manag. doi: 10.2307/3797016 – volume: 48 start-page: 635 issue: 5 year: 2008 ident: 10.1016/j.ecoinf.2018.09.007_bb0130 article-title: Crowding—an essential bottleneck for object recognition: a mini-review publication-title: Vis. Res. doi: 10.1016/j.visres.2007.12.009 – year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0150 article-title: Expert, Crowd – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 10.1016/j.ecoinf.2018.09.007_bb0220 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: The Journal of Machine Learning Research – start-page: 286 year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0100 article-title: LifeCLEF 2016: multimedia life species identification challenges – ident: 10.1016/j.ecoinf.2018.09.007_bb0035 doi: 10.1073/pnas.1708001115 – start-page: fsx109 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0210 article-title: Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data publication-title: ICES J. Mar. Sci. – start-page: 1097 year: 2012 ident: 10.1016/j.ecoinf.2018.09.007_bb0105 – volume: 10 start-page: 298 issue: 6 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0160 article-title: Undersea Constellations: the Global Biology of an Endangered Marine Megavertebrate further Informed through Citizen Science publication-title: Bioscience – volume: 301 start-page: 955 issue: 5635 year: 2003 ident: 10.1016/j.ecoinf.2018.09.007_bb0165 article-title: Global trajectories of the long-term decline of coral reef ecosystems publication-title: Science doi: 10.1126/science.1085706 – volume: 350 start-page: 245 year: 2007 ident: 10.1016/j.ecoinf.2018.09.007_bb0070 article-title: Bait attraction affects the performance of remote underwater video stations in assessment of demersal fish community structure publication-title: Mar. Ecol. Prog. Ser. doi: 10.3354/meps07192 – volume: 15 issue: 1 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0110 article-title: Marine reserve targets to sustain and rebuild unregulated fisheries publication-title: PLoS Biol. doi: 10.1371/journal.pbio.2000537 – volume: 40 start-page: 85 year: 2007 ident: 10.1016/j.ecoinf.2018.09.007_bb0245 article-title: Behaviour of temperate and sub-tropical reef fishes towards a stationary SCUBA diver publication-title: Mar. Freshw. Behav. Physiol. doi: 10.1080/10236240701393263 – volume: 26 start-page: 5872 issue: 21 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0040 article-title: Environmental DNA metabarcoding: Transforming how we survey animal and plant communities publication-title: Mol. Ecol. doi: 10.1111/mec.14350 – ident: 10.1016/j.ecoinf.2018.09.007_bb0075 – volume: 8 issue: 12 year: 2013 ident: 10.1016/j.ecoinf.2018.09.007_bb0115 article-title: Global biogeography of reef fishes: a hierarchical quantitative delineation of regions publication-title: PLoS One doi: 10.1371/journal.pone.0081847 – volume: 283 issue: 1831 year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0200 article-title: Reef fishes can recognize bleached habitat during settlement: sea anemone bleaching alters anemonefish host selection publication-title: Proc. R. Soc. B doi: 10.1098/rspb.2015.2694 – volume: 11 start-page: l year: 1986 ident: 10.1016/j.ecoinf.2018.09.007_bb0025 article-title: Fish behaviour in relation to divers publication-title: Prog Underw Sci – ident: 10.1016/j.ecoinf.2018.09.007_bb0215 doi: 10.1145/1877868.1877881 – ident: 10.1016/j.ecoinf.2018.09.007_bb0140 doi: 10.1109/ICCV.1999.790410 – volume: 6 start-page: 357 year: 2015 ident: 10.1016/j.ecoinf.2018.09.007_bb0255 article-title: MotionMeerkat: Integrating motion video detection and ecological monitoring (S Dray, Ed.) publication-title: Methods Ecol. Evol. doi: 10.1111/2041-210X.12320 – year: 2000 ident: 10.1016/j.ecoinf.2018.09.007_bb0050 – volume: 6 start-page: 1088 issue: 10 year: 2010 ident: 10.1016/j.ecoinf.2018.09.007_bb0005 article-title: Fish recognition based on robust features extraction from size and shape measurements using neural network publication-title: J. Comput. Sci. doi: 10.3844/jcssp.2010.1088.1094 – volume: 51 start-page: 755 issue: 8 year: 2000 ident: 10.1016/j.ecoinf.2018.09.007_bb0265 article-title: A baited underwater video system for the determination of relative density of carnivorous reef fish publication-title: Mar. Freshw. Res. doi: 10.1071/MF00010 – volume: 23 start-page: 155 year: 1999 ident: 10.1016/j.ecoinf.2018.09.007_bb0045 article-title: Comparison of fish abundance estimates made by remote underwater video and visual census publication-title: Naturalista sicil – ident: 10.1016/j.ecoinf.2018.09.007_bb0135 – volume: 59 start-page: 1408 issue: 5 year: 2001 ident: 10.1016/j.ecoinf.2018.09.007_bb0260 article-title: Visual census methods underestimate density and diversity of cryptic reef fishes publication-title: J. Fish Biol. doi: 10.1111/j.1095-8649.2001.tb00202.x – volume: 535 start-page: 416 issue: 7612 year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0030 article-title: Bright spots among the world's coral reefs publication-title: Nature doi: 10.1038/nature18607 – volume: 546 start-page: 82 issue: 7656 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0080 article-title: Coral reefs in the Anthropocene publication-title: Nature doi: 10.1038/nature22901 – start-page: 455 year: 2003 ident: 10.1016/j.ecoinf.2018.09.007_bb0020 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.ecoinf.2018.09.007_bb0125 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 319 start-page: 948 issue: 5865 year: 2008 ident: 10.1016/j.ecoinf.2018.09.007_bb0060 article-title: A global map of human impact on marine ecosystems publication-title: Science doi: 10.1126/science.1149345 – volume: 50 start-page: 4 issue: 1 year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0205 article-title: Progress in the automated identification, measurement, and counting of fish in underwater image sequences publication-title: Mar. Technol. Soc. J. doi: 10.4031/MTSJ.50.1.1 – volume: 154 start-page: 44 year: 2014 ident: 10.1016/j.ecoinf.2018.09.007_bb0145 article-title: Underwater video techniques for observing coastal marine biodiversity: a review of sixty years of publications (1952–2012) publication-title: Fish. Res. doi: 10.1016/j.fishres.2014.01.019 – year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0240 article-title: Coral reef fish detection and recognition in underwater videos by supervised machine learning: Comparison between Deep Learning and HOG+ SVM methods – volume: 23 start-page: 1009 issue: 3 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0180 article-title: Fishing degrades size structure of coral reef fish communities publication-title: Glob. Chang. Biol. doi: 10.1111/gcb.13482 – volume: 111(38) start-page: 13757 year: 2014 ident: 10.1016/j.ecoinf.2018.09.007_bb0155 article-title: Functional over-redundancy and high functional vulnerability in global fish faunas on tropical reefs – volume: 2 start-page: 37 issue: 1 year: 1983 ident: 10.1016/j.ecoinf.2018.09.007_bb0190 article-title: Correction for bias in visual transect censuses of coral reef fishes publication-title: Coral Reefs doi: 10.1007/BF00304730 – volume: 14 start-page: 341 issue: 4 year: 2011 ident: 10.1016/j.ecoinf.2018.09.007_bb0055 article-title: Extinction vulnerability of coral reef fishes publication-title: Ecol. Lett. doi: 10.1111/j.1461-0248.2011.01592.x – volume: 9 start-page: 155 year: 2010 ident: 10.1016/j.ecoinf.2018.09.007_bb0120 article-title: Cost-efficient sampling of fish assemblages: comparison of baited video sta=tions and diver video transects publication-title: Aquat. Biol. doi: 10.3354/ab00235 – volume: 61 start-page: 85 year: 2015 ident: 10.1016/j.ecoinf.2018.09.007_bb0195 article-title: Deep learning in neural networks: an overview publication-title: Neural Netw. doi: 10.1016/j.neunet.2014.09.003 – volume: 36 start-page: 145 year: 2016 ident: 10.1016/j.ecoinf.2018.09.007_bb0175 article-title: AnimalFinder: a semi-automated system for animal detection in time-lapse camera trap images publication-title: Ecol. Inform. doi: 10.1016/j.ecoinf.2016.11.003 – volume: 55 start-page: 1041 issue: 3 year: 2017 ident: 10.1016/j.ecoinf.2018.09.007_bb0185 article-title: Fisheries productivity under progressive coral reef degradation publication-title: J. Appl. Ecol. doi: 10.1111/1365-2664.13051 – start-page: 1 year: 2014 ident: 10.1016/j.ecoinf.2018.09.007_bb0010
SSID	ssj0043882
Score	2.5704472
Snippet	Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and...
SourceID	hal proquest crossref elsevier
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	238
SubjectTerms	Artificial Intelligence Automated identification biodiversity Biodiversity and Ecology Computer Science Computer Vision and Pattern Recognition Convolutional neural network coral reefs corals Environmental Sciences fish humans Image Processing Machine Learning Marine fishes monitoring Neural and Evolutionary Computing protocols species identification Underwater pictures
Title	A Deep learning method for accurate and fast identification of coral reef fishes in underwater images
URI	https://dx.doi.org/10.1016/j.ecoinf.2018.09.007 https://www.proquest.com/docview/2153637005 https://hal-lirmm.ccsd.cnrs.fr/lirmm-01884005
Volume	48
WOSCitedRecordID	wos000453641900023&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
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 1574-9541 databaseCode: AIEXJ dateStart: 20060101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0043882 providerName: Elsevier – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources issn: 1574-9541 databaseCode: M~E dateStart: 20060101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://road.issn.org omitProxy: false ssIdentifier: ssj0043882 providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9NAFB6FAhIXxKqGTYPUW-UqnvF6jFBQD1AhtaDeRuNZwFXiRIkdyoV_wn_lzeYmqaD0gBRZ0Wjs2H5f3jLz3vcQOkg5yU1yeyT1SEdJqlXEwRBGKeWUCPAAspGwzSbyk5Pi_Lz8NBj8CrUw62neNMXlZbn4r6KGMRC2KZ29hbj7i8IAfAehwxHEDsd_EvwYdIhahHYQX32PaJctKURnqCHsjoHmq_awlj5bqPcchS3ZXyqlD7XJl7f5sqbSbPmdG0LFegYaaLW1oC96BeppWNuNFPovddjZP3Wb8mA3DZVrL-l5Z2a0Own2NuGgg5cWKorExpr61DdimdjFmdOjzaWLuPA1fBvaFkBSpo75KqhjR7wZ9KmjfvGmmTiqyGta3y1AXBxBwA7jJl-vsOS1rp_uNsn2jvHrUxJDttsFc1dh5ipsVDLLVXCX5Glp9P7Hn5Ng6BNa2F5k_VOEykybPnj9Xv7k-dz5ZlJwdzwB696cPUIPfVyCxw5Pj9FANU_QfSfaH0-RGmODKhxQhR2qMIgbB1RhQBU2qMLbqMJzjS2qsEEVdqjCdYOvUIUdqp6hz-8nZ--OI9-hIxIJiVt4alKBP0m0oGYhgHMIxznNieZFLkuZJzot05ILSmRVCSqrohRU5VUhZQGRs6TP0V4zb9Q-wtxYmwwCDp1AhA5uZJxJnZFYES7hkw4RDW-PCU9fb7qoTNnfJDdEUX_WwtG33DA_D4Jh3gV1riUDrN1w5gHIsf8Rw9p-PP7ApvVyNmMwrQBjma7jIXobBM1AkZvdOd6oebdi4HvTjOYw68Utb_olenD173qF9tplp16je2Ld1qvlG4vZ33ZZwr0
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=A+Deep+learning+method+for+accurate+and+fast+identification+of+coral+reef+fishes+in+underwater+images&rft.jtitle=Ecological+informatics&rft.au=Villon%2C+S%C3%A9bastien&rft.au=Mouillot%2C+David&rft.au=Chaumont%2C+Marc&rft.au=Darling%2C+Emily+S.&rft.date=2018-11-01&rft.issn=1574-9541&rft.volume=48&rft.spage=238&rft.epage=244&rft_id=info:doi/10.1016%2Fj.ecoinf.2018.09.007&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ecoinf_2018_09_007
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1574-9541&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1574-9541&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1574-9541&client=summon