Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3389/fpls.2021.758455 http://hdl.handle.net/11449/218529 |
Resumo: | Availability of and access to wood identification expertise or technology is a critical component for the design and implementation of practical, enforceable strategies for effective promotion, monitoring and incentivisation of sustainable practices and conservation efforts in the forest products value chain. To address this need in the context of the multi-billion-dollar North American wood products industry 22-class, image-based, deep learning models for the macroscopic identification of North American diffuse porous hardwoods were trained for deployment on the open-source, field-deployable XyloTron platform using transverse surface images of specimens from three different xylaria and evaluated on specimens from a fourth xylarium that did not contribute training data. Analysis of the model performance, in the context of the anatomy of the woods considered, demonstrates immediate readiness of the technology developed herein for field testing in a human-in-the-loop monitoring scenario. Also proposed are strategies for training, evaluating, and advancing the state-of-the-art for developing an expansive, continental scale model for all the North American hardwoods. |
id |
UNSP_6ebee5c163012831af78a80d1a65d3b6 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/218529 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoodswood identificationillegal logging and timber tradeXyloTroncomputer visionmachine learningdeep learningdiffuse porous hardwoodssustainable wood productsAvailability of and access to wood identification expertise or technology is a critical component for the design and implementation of practical, enforceable strategies for effective promotion, monitoring and incentivisation of sustainable practices and conservation efforts in the forest products value chain. To address this need in the context of the multi-billion-dollar North American wood products industry 22-class, image-based, deep learning models for the macroscopic identification of North American diffuse porous hardwoods were trained for deployment on the open-source, field-deployable XyloTron platform using transverse surface images of specimens from three different xylaria and evaluated on specimens from a fourth xylarium that did not contribute training data. Analysis of the model performance, in the context of the anatomy of the woods considered, demonstrates immediate readiness of the technology developed herein for field testing in a human-in-the-loop monitoring scenario. Also proposed are strategies for training, evaluating, and advancing the state-of-the-art for developing an expansive, continental scale model for all the North American hardwoods.Univ Wisconsin, Dept Bot, Madison, WI 53706 USAUS Forest Serv, Forest Prod Lab, Ctr Wood Anat Res, USDA, 1 Gifford Pinchot Dr, Madison, WI 53705 USAMississippi State Univ, Dept Sustainable Bioprod, Starkville, MS USAPurdue Univ, Dept Forestry & Nat Resources, W Lafayette, IN 47907 USAUniv Estadual Paulista, Dept Ciencias Biol Bot, Botucatu, SP, BrazilUniv Estadual Paulista, Dept Ciencias Biol Bot, Botucatu, SP, BrazilFrontiers Media SaUniv WisconsinUS Forest ServMississippi State UnivPurdue UnivUniversidade Estadual Paulista (UNESP)Ravindran, PrabuOwens, Frank C.Wade, Adam C.Shmulsky, RubinWiedenhoeft, Alex C.2022-04-28T17:21:29Z2022-04-28T17:21:29Z2022-01-21info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article13http://dx.doi.org/10.3389/fpls.2021.758455Frontiers In Plant Science. Lausanne: Frontiers Media Sa, v. 12, 13 p., 2022.1664-462Xhttp://hdl.handle.net/11449/21852910.3389/fpls.2021.758455WOS:000752614400001Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengFrontiers In Plant Scienceinfo:eu-repo/semantics/openAccess2022-04-28T17:21:29Zoai:repositorio.unesp.br:11449/218529Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:31:51.016199Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
title |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
spellingShingle |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods Ravindran, Prabu wood identification illegal logging and timber trade XyloTron computer vision machine learning deep learning diffuse porous hardwoods sustainable wood products |
title_short |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
title_full |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
title_fullStr |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
title_full_unstemmed |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
title_sort |
Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods |
author |
Ravindran, Prabu |
author_facet |
Ravindran, Prabu Owens, Frank C. Wade, Adam C. Shmulsky, Rubin Wiedenhoeft, Alex C. |
author_role |
author |
author2 |
Owens, Frank C. Wade, Adam C. Shmulsky, Rubin Wiedenhoeft, Alex C. |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Univ Wisconsin US Forest Serv Mississippi State Univ Purdue Univ Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Ravindran, Prabu Owens, Frank C. Wade, Adam C. Shmulsky, Rubin Wiedenhoeft, Alex C. |
dc.subject.por.fl_str_mv |
wood identification illegal logging and timber trade XyloTron computer vision machine learning deep learning diffuse porous hardwoods sustainable wood products |
topic |
wood identification illegal logging and timber trade XyloTron computer vision machine learning deep learning diffuse porous hardwoods sustainable wood products |
description |
Availability of and access to wood identification expertise or technology is a critical component for the design and implementation of practical, enforceable strategies for effective promotion, monitoring and incentivisation of sustainable practices and conservation efforts in the forest products value chain. To address this need in the context of the multi-billion-dollar North American wood products industry 22-class, image-based, deep learning models for the macroscopic identification of North American diffuse porous hardwoods were trained for deployment on the open-source, field-deployable XyloTron platform using transverse surface images of specimens from three different xylaria and evaluated on specimens from a fourth xylarium that did not contribute training data. Analysis of the model performance, in the context of the anatomy of the woods considered, demonstrates immediate readiness of the technology developed herein for field testing in a human-in-the-loop monitoring scenario. Also proposed are strategies for training, evaluating, and advancing the state-of-the-art for developing an expansive, continental scale model for all the North American hardwoods. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-04-28T17:21:29Z 2022-04-28T17:21:29Z 2022-01-21 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3389/fpls.2021.758455 Frontiers In Plant Science. Lausanne: Frontiers Media Sa, v. 12, 13 p., 2022. 1664-462X http://hdl.handle.net/11449/218529 10.3389/fpls.2021.758455 WOS:000752614400001 |
url |
http://dx.doi.org/10.3389/fpls.2021.758455 http://hdl.handle.net/11449/218529 |
identifier_str_mv |
Frontiers In Plant Science. Lausanne: Frontiers Media Sa, v. 12, 13 p., 2022. 1664-462X 10.3389/fpls.2021.758455 WOS:000752614400001 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Frontiers In Plant Science |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
13 |
dc.publisher.none.fl_str_mv |
Frontiers Media Sa |
publisher.none.fl_str_mv |
Frontiers Media Sa |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128667376680960 |