AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Cerne (Online) |
Texto Completo: | https://cerne.ufla.br/site/index.php/CERNE/article/view/2104 |
Resumo: | Light Detection and Ranging (LiDAR) derived individual tree crown attributes have the potential of progressing ecology and forest dynamics studies and reduce field inventory costs. In this study seven methods for individual tree detection (ITD) were evaluated in a tropical forest under sustainable forest management, situated in the State of Rondônia, Brazil. An automated tree matching procedure was developed in order to minimize the error when matching individual tree count from LiDAR and field data. The ITD results were expressed in recall, precision, and F score, for the purpose of comparing methods. A local maxima-based algorithm showed best performance among the four methods, detecting 48% of trees with 46% of precision. Omission of trees was the leading source of error, caused primarily by overlapped trees in lower vegetation. However, errors of over-segmentation were relevant, caused by large and heterogeneous crowns that were considered as more than one individual. The complexity of tropical forests in the Amazon is certainly a challenge for current tree detection algorithms. We suggested that the future studies should consider testing multi-layer ITD workflows for improving the accuracy of tree detection. |
id |
UFLA-3_a40ae53b1cb38cc468dffdbfcf778456 |
---|---|
oai_identifier_str |
oai:cerne.ufla.br:article/2104 |
network_acronym_str |
UFLA-3 |
network_name_str |
Cerne (Online) |
repository_id_str |
|
spelling |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATAAutomatic Processes, Brazilian Amazon Forest, Crown Delineation, LiDAR TechnologyLight Detection and Ranging (LiDAR) derived individual tree crown attributes have the potential of progressing ecology and forest dynamics studies and reduce field inventory costs. In this study seven methods for individual tree detection (ITD) were evaluated in a tropical forest under sustainable forest management, situated in the State of Rondônia, Brazil. An automated tree matching procedure was developed in order to minimize the error when matching individual tree count from LiDAR and field data. The ITD results were expressed in recall, precision, and F score, for the purpose of comparing methods. A local maxima-based algorithm showed best performance among the four methods, detecting 48% of trees with 46% of precision. Omission of trees was the leading source of error, caused primarily by overlapped trees in lower vegetation. However, errors of over-segmentation were relevant, caused by large and heterogeneous crowns that were considered as more than one individual. The complexity of tropical forests in the Amazon is certainly a challenge for current tree detection algorithms. We suggested that the future studies should consider testing multi-layer ITD workflows for improving the accuracy of tree detection.CERNECERNE2019-11-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://cerne.ufla.br/site/index.php/CERNE/article/view/2104CERNE; Vol. 25 No. 3 (2019); 273-282CERNE; v. 25 n. 3 (2019); 273-2822317-63420104-7760reponame:Cerne (Online)instname:Universidade Federal de Lavras (UFLA)instacron:UFLAenghttps://cerne.ufla.br/site/index.php/CERNE/article/view/2104/1144Copyright (c) 2019 CERNEinfo:eu-repo/semantics/openAccessMillikan, Pedro Henrique KarantinoSilva, Carlos AlbertoRodriguez, Luiz Carlos Estravizde Oliveira, Tupiara Mergene Carvalho, Mariana Peres de Lima ChavesCarvalho, Samuel de Padua Chaves e2019-11-14T11:12:47Zoai:cerne.ufla.br:article/2104Revistahttps://cerne.ufla.br/site/index.php/CERNEPUBhttps://cerne.ufla.br/site/index.php/CERNE/oaicerne@dcf.ufla.br||cerne@dcf.ufla.br2317-63420104-7760opendoar:2024-05-21T19:54:40.836710Cerne (Online) - Universidade Federal de Lavras (UFLA)true |
dc.title.none.fl_str_mv |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
title |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
spellingShingle |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA Millikan, Pedro Henrique Karantino Automatic Processes, Brazilian Amazon Forest, Crown Delineation, LiDAR Technology |
title_short |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
title_full |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
title_fullStr |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
title_full_unstemmed |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
title_sort |
AUTOMATED INDIVIDUAL TREE DETECTION IN AMAZON TROPICAL FOREST FROM AIRBORNE LASER SCANNING DATA |
author |
Millikan, Pedro Henrique Karantino |
author_facet |
Millikan, Pedro Henrique Karantino Silva, Carlos Alberto Rodriguez, Luiz Carlos Estraviz de Oliveira, Tupiara Mergen e Carvalho, Mariana Peres de Lima Chaves Carvalho, Samuel de Padua Chaves e |
author_role |
author |
author2 |
Silva, Carlos Alberto Rodriguez, Luiz Carlos Estraviz de Oliveira, Tupiara Mergen e Carvalho, Mariana Peres de Lima Chaves Carvalho, Samuel de Padua Chaves e |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Millikan, Pedro Henrique Karantino Silva, Carlos Alberto Rodriguez, Luiz Carlos Estraviz de Oliveira, Tupiara Mergen e Carvalho, Mariana Peres de Lima Chaves Carvalho, Samuel de Padua Chaves e |
dc.subject.por.fl_str_mv |
Automatic Processes, Brazilian Amazon Forest, Crown Delineation, LiDAR Technology |
topic |
Automatic Processes, Brazilian Amazon Forest, Crown Delineation, LiDAR Technology |
description |
Light Detection and Ranging (LiDAR) derived individual tree crown attributes have the potential of progressing ecology and forest dynamics studies and reduce field inventory costs. In this study seven methods for individual tree detection (ITD) were evaluated in a tropical forest under sustainable forest management, situated in the State of Rondônia, Brazil. An automated tree matching procedure was developed in order to minimize the error when matching individual tree count from LiDAR and field data. The ITD results were expressed in recall, precision, and F score, for the purpose of comparing methods. A local maxima-based algorithm showed best performance among the four methods, detecting 48% of trees with 46% of precision. Omission of trees was the leading source of error, caused primarily by overlapped trees in lower vegetation. However, errors of over-segmentation were relevant, caused by large and heterogeneous crowns that were considered as more than one individual. The complexity of tropical forests in the Amazon is certainly a challenge for current tree detection algorithms. We suggested that the future studies should consider testing multi-layer ITD workflows for improving the accuracy of tree detection. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-11-12 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://cerne.ufla.br/site/index.php/CERNE/article/view/2104 |
url |
https://cerne.ufla.br/site/index.php/CERNE/article/view/2104 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://cerne.ufla.br/site/index.php/CERNE/article/view/2104/1144 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2019 CERNE info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2019 CERNE |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
CERNE CERNE |
publisher.none.fl_str_mv |
CERNE CERNE |
dc.source.none.fl_str_mv |
CERNE; Vol. 25 No. 3 (2019); 273-282 CERNE; v. 25 n. 3 (2019); 273-282 2317-6342 0104-7760 reponame:Cerne (Online) instname:Universidade Federal de Lavras (UFLA) instacron:UFLA |
instname_str |
Universidade Federal de Lavras (UFLA) |
instacron_str |
UFLA |
institution |
UFLA |
reponame_str |
Cerne (Online) |
collection |
Cerne (Online) |
repository.name.fl_str_mv |
Cerne (Online) - Universidade Federal de Lavras (UFLA) |
repository.mail.fl_str_mv |
cerne@dcf.ufla.br||cerne@dcf.ufla.br |
_version_ |
1799874943771475968 |