Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation

The detection and sizing of fruits with computer vision methods is of interest because it provides relevant information to improve the management of orchard farming. However, the presence of partially occluded fruits limits the performance of existing methods, making reliable fruit sizing a challeng...

Descripción completa

Detalles Bibliográficos
Autores: Gené Mola, Jordi, Ferrer Ferrer, Mar, Gregorio López, Eduard, Blok, Pieter, Hemming, Jochen, Morros Rubió, Josep Ramon, Rosell Polo, Joan Ramon, Vilaplana Besler, Verónica, Ruiz Hidalgo, Javier
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10459.1/463463
Acceso en línea:https://doi.org/10.1016/j.compag.2023.107854
https://hdl.handle.net/10459.1/463463
Access Level:acceso abierto
Palabra clave:Fruit detection
Fruit measurement
Yield estimation
Fruit visibility
Deep learning
Precision agriculture
id ES_601ecedf4a1dbb81b05b689d35c8a9e8
oai_identifier_str oai:recercat.cat:10459.1/463463
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
title Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
spellingShingle Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
Gené Mola, Jordi
Fruit detection
Fruit measurement
Yield estimation
Fruit visibility
Deep learning
Precision agriculture
title_short Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
title_full Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
title_fullStr Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
title_full_unstemmed Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
title_sort Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation
dc.creator.none.fl_str_mv Gené Mola, Jordi
Ferrer Ferrer, Mar
Gregorio López, Eduard
Blok, Pieter
Hemming, Jochen
Morros Rubió, Josep Ramon
Rosell Polo, Joan Ramon
Vilaplana Besler, Verónica
Ruiz Hidalgo, Javier
author Gené Mola, Jordi
author_facet Gené Mola, Jordi
Ferrer Ferrer, Mar
Gregorio López, Eduard
Blok, Pieter
Hemming, Jochen
Morros Rubió, Josep Ramon
Rosell Polo, Joan Ramon
Vilaplana Besler, Verónica
Ruiz Hidalgo, Javier
author_role author
author2 Ferrer Ferrer, Mar
Gregorio López, Eduard
Blok, Pieter
Hemming, Jochen
Morros Rubió, Josep Ramon
Rosell Polo, Joan Ramon
Vilaplana Besler, Verónica
Ruiz Hidalgo, Javier
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Fruit detection
Fruit measurement
Yield estimation
Fruit visibility
Deep learning
Precision agriculture
topic Fruit detection
Fruit measurement
Yield estimation
Fruit visibility
Deep learning
Precision agriculture
description The detection and sizing of fruits with computer vision methods is of interest because it provides relevant information to improve the management of orchard farming. However, the presence of partially occluded fruits limits the performance of existing methods, making reliable fruit sizing a challenging task. While previous fruit segmentation works limit segmentation to the visible region of fruits (known as modal segmentation), in this work we propose an amodal segmentation algorithm to predict the complete shape, which includes its visible and occluded regions. To do so, an end-to-end convolutional neural network (CNN) for sim ultaneous modal and amodal instance segmentation was implemented. The predicted amodal masks were used to estimate the fruit diameters in pixels. Modal masks were used to identify the visible region and measure the distance between the apples and the camera using the depth image. Finally, the fruit diameters in millimetres (mm) were computed by applying the pinhole camera model. The method was developed with a Fuji apple dataset consisting of 3925 RGB-D images acquired at different growth stages with a total of 15,335 annotated apples, and was subsequently tested in a case study to measure the diameter of Elstar apples at different growth stages. Fruit detection results showed an F1-score of 0.86 and the fruit diameter results reported a mean absolute error (MAE) of 4.5 mm and R2 = 0.80 irrespective of fruit visibility. Besides the diameter estimation, modal and amodal masks were used to automatically determine the percentage of visibility of measured apples. This feature was used as a confidence value, improving the diameter estimation to MAE = 2.93 mm and R2 = 0.91 when limiting the size estimation to fruits detected with a visibility higher than 60%. The main advantages of the present methodology are its robustness for measuring partially occluded fruits and the capability to determine the visibility percentage. The main limitation is that depth images were generated by means of photogrammetry methods, which limits the efficiency of data acquisition. To overcome this limitation, future works should consider the use of commercial RGB-D sensors. The code and the dataset used to evaluate the method have been made publicly available at https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing.
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://doi.org/10.1016/j.compag.2023.107854
https://hdl.handle.net/10459.1/463463
url https://doi.org/10.1016/j.compag.2023.107854
https://hdl.handle.net/10459.1/463463
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-094222-B-I00
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-117142GB-I00
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica, Técnica y de Innovación 2021-2023/PID2021-126648OB-I00
Reproducció del document publicat a https://doi.org/10.1016/j.compag.2023.107854
Computers and Electronics in Agriculture, 2023, vol. 209, 107854
https://repositori.udl.cat/handle/10459.1/464013
dc.rights.none.fl_str_mv cc-by (c) Jordi Gené Mola et al., 2023
Attribution 4.0 International
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/4.0/
rights_invalid_str_mv cc-by (c) Jordi Gené Mola et al., 2023
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409270033809408
spelling Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimationGené Mola, JordiFerrer Ferrer, MarGregorio López, EduardBlok, PieterHemming, JochenMorros Rubió, Josep RamonRosell Polo, Joan RamonVilaplana Besler, VerónicaRuiz Hidalgo, JavierFruit detectionFruit measurementYield estimationFruit visibilityDeep learningPrecision agricultureThe detection and sizing of fruits with computer vision methods is of interest because it provides relevant information to improve the management of orchard farming. However, the presence of partially occluded fruits limits the performance of existing methods, making reliable fruit sizing a challenging task. While previous fruit segmentation works limit segmentation to the visible region of fruits (known as modal segmentation), in this work we propose an amodal segmentation algorithm to predict the complete shape, which includes its visible and occluded regions. To do so, an end-to-end convolutional neural network (CNN) for sim ultaneous modal and amodal instance segmentation was implemented. The predicted amodal masks were used to estimate the fruit diameters in pixels. Modal masks were used to identify the visible region and measure the distance between the apples and the camera using the depth image. Finally, the fruit diameters in millimetres (mm) were computed by applying the pinhole camera model. The method was developed with a Fuji apple dataset consisting of 3925 RGB-D images acquired at different growth stages with a total of 15,335 annotated apples, and was subsequently tested in a case study to measure the diameter of Elstar apples at different growth stages. Fruit detection results showed an F1-score of 0.86 and the fruit diameter results reported a mean absolute error (MAE) of 4.5 mm and R2 = 0.80 irrespective of fruit visibility. Besides the diameter estimation, modal and amodal masks were used to automatically determine the percentage of visibility of measured apples. This feature was used as a confidence value, improving the diameter estimation to MAE = 2.93 mm and R2 = 0.91 when limiting the size estimation to fruits detected with a visibility higher than 60%. The main advantages of the present methodology are its robustness for measuring partially occluded fruits and the capability to determine the visibility percentage. The main limitation is that depth images were generated by means of photogrammetry methods, which limits the efficiency of data acquisition. To overcome this limitation, future works should consider the use of commercial RGB-D sensors. The code and the dataset used to evaluate the method have been made publicly available at https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing.This work was partly funded by the Departament de Recerca i Universitats de la Generalitat de Catalunya (grant 2021 LLAV 00088), the Spanish Ministry of Science, Innovation and Universities (grants RTI2018-094222-B-I00 [PAgFRUIT project], PID2021-126648OB-I00 [PAgPROTECT project] and PID2020-117142GB-I00 [DeeLight project] by MCIN/AEI/10.13039/501100011033 and by “ERDF, a way of making Europe”, by the European Union). The work of Jordi Gen´e Mola was supported by the Spanish Ministry of Universities through a Margarita Salas postdoctoral grant funded by the European Union - NextGenerationEU. We would also like to thank Nufri (especially Santiago Salamero and Oriol Morreres) for their support during data acquisition, and Pieter van Dalfsen and Dirk de Hoog from Wageningen University & Research for additional data collection used in the case study.Elsevier2023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://doi.org/10.1016/j.compag.2023.107854https://hdl.handle.net/10459.1/463463reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-094222-B-I00info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-117142GB-I00info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica, Técnica y de Innovación 2021-2023/PID2021-126648OB-I00Reproducció del document publicat a https://doi.org/10.1016/j.compag.2023.107854Computers and Electronics in Agriculture, 2023, vol. 209, 107854https://repositori.udl.cat/handle/10459.1/464013cc-by (c) Jordi Gené Mola et al., 2023Attribution 4.0 Internationalinfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/4.0/oai:recercat.cat:10459.1/4634632026-05-29T05:05:01Z
score 15.81155