Repository logo
 
Publication

Automatic detection and classification of honey bee comb cells using deep learning

2020Journal article Open access
Simple item page
dc.contributor.authorAlves, Thiago da Silva
dc.contributor.authorPinto, M. Alice
dc.contributor.authorVentura, Paulo J.C.
dc.contributor.authorNeves, Cátia J.
dc.contributor.authorBiron, David G.
dc.contributor.authorCandido Junior, Arnaldo
dc.contributor.authorPaula Filho, Pedro L. de
dc.contributor.authorRodrigues, Pedro João
dc.date.accessioned2018-02-19T10:00:00Z
dc.date.accessioned2020-06-22T10:18:38Z
dc.date.available2018-01-19T10:00:00Z
dc.date.available2020-06-22T10:18:38Z
dc.date.issued2020
dc.description.abstractIn a scenario of worldwide honey bee decline, assessing colony strength is becoming increasingly important for sustainable beekeeping. Temporal counts of number of comb cells with brood and food reserves offers researchers data for multiple applications, such as modelling colony dynamics, and beekeepers information on colony strength, an indicator of colony health and honey yield. Counting cells manually in comb images is labour intensive, tedious, and prone to error. Herein, we developed a free software, named DeepBee©, capable of automatically detecting cells in comb images and classifying their contents into seven classes. By distinguishing cells occupied by eggs, larvae, capped brood, pollen, nectar, honey, and other, DeepBee© allows an unprecedented level of accuracy in cell classification. Using Circle Hough Transform and the semantic segmentation technique, we obtained a cell detection rate of 98.7%, which is 16.2% higher than the best result found in the literature. For classification of comb cells, we trained and evaluated thirteen different convolutional neural network (CNN) architectures, including: DenseNet (121, 169 and 201); InceptionResNetV2; InceptionV3; MobileNet; MobileNetV2; NasNet; NasNetMobile; ResNet50; VGG (16 and 19) and Xception. MobileNet revealed to be the best compromise between training cost, with ~9 s for processing all cells in a comb image, and accuracy, with an F1-Score of 94.3%. We show the technical details to build a complete pipeline for classifying and counting comb cells and we made the CNN models, source code, and datasets publicly available. With this effort, we hope to have expanded the frontier of apicultural precision analysis by providing a tool with high performance and source codes to foster improvement by third parties (https://github.com/AvsThiago/DeepBeesource).
dc.description.sponsorshipThis research was developed in the framework of the project “BeeHope - Honeybee conservation centers in Western Europe: an innovative strategy using sustainable beekeeping to reduce honeybee decline”, funded through the 2013-2014 BiodivERsA/FACCE-JPI Joint call for research proposals, with the national funders FCT (Portugal), CNRS (France), and MEC (Spain).
dc.description.versioninfo:eu-repo/semantics/publishedVersionen_EN
dc.identifier.citationAlves, Thiago S.; Pinto, M. Alice; Ventura, Paulo; Neves, Cátia J.; Biron, David G.; Junior, Arnaldo C.; De Paula Filho, Pedro L.; Rodrigues, Pedro J. (2020). Automatic detection and classification of honey bee comb cells using deep learning. Computers and Electronics in Agriculture. ISSN 0168-1699. 170, p. 1-14en_EN
dc.identifier.doi10.1016/j.compag.2020.105244en_EN
dc.identifier.issn0168-1699
dc.identifier.urihttp://hdl.handle.net/10198/22321
dc.language.isoeng
dc.peerreviewedyesen_EN
dc.subjectApis mellifera L.en_EN
dc.subjectCell classificationen_EN
dc.subjectDeep learningen_EN
dc.subjectDeepBee softwareen_EN
dc.subjectMachine learningen_EN
dc.subjectSemantic segmentationen_EN
dc.titleAutomatic detection and classification of honey bee comb cells using deep learningen_EN
dc.typejournal article
dspace.entity.typePublication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/BiodivERsA%2F0002%2F2014/PT
oaire.fundingStream3599-PPCDT
person.familyNamePinto
person.familyNameSoares Rodrigues
person.givenNameMaria Alice
person.givenNamePedro João
person.identifier.ciencia-idF814-A1D0-8318
person.identifier.ciencia-id1316-21BB-9015
person.identifier.orcid0000-0001-9663-8399
person.identifier.orcid0000-0002-0555-2029
person.identifier.scopus-author-id8085507800
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccessen_EN
rcaap.typearticleen_EN
relation.isAuthorOfPublication0667fe04-7078-483d-9198-56d167b19bc5
relation.isAuthorOfPublication6c5911a6-b62b-4876-9def-60096b52383a
relation.isAuthorOfPublication.latestForDiscovery0667fe04-7078-483d-9198-56d167b19bc5
relation.isProjectOfPublication8fc0bb12-466c-4296-884c-17d34d732f5d
relation.isProjectOfPublication.latestForDiscovery8fc0bb12-466c-4296-884c-17d34d732f5d

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
65.pdf
Size:
5.92 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.75 KB
Format:
Plain Text
Description:
Download

Collections

CIMO - Artigos em Revistas Indexados à WoS/Scopus