Estimation of vegetation height with drone-acquired images using artificial intelligence techniques
DOI:
https://doi.org/10.26848/rbgf.v17.5.p3736-3749Keywords:
Mangrove, Modeling, Remote sensing, UAVAbstract
Geotechnologies are recent tools that can be used to assess forest conditions, with advantages over other techniques due to the speed and practicality of gathering data on vegetation structure. The use of UAVs (Unmanned Aerial Vehicles) stands out among other remote sensing techniques, as it has the potential to generate high-quality, high-resolution data. The research aims to estimate the canopy height of a mangrove forest fragment using drone images. The images were associated with geoprocessing software that allowed the creation of point clouds and orthomosaics. In a fragment of mangrove forest, twelve trees were randomly chosen to be used as reference points, their heights were estimated, and their geographical coordinates were recorded using GPS. The values were approximated using three types of machine learning: linear equations in Excel, regression trees in Rstudio, and a Python interpreter. The results showed a good approximation with the tree height data estimated in the field, with a correlation index of 0.90 and RMSE of 1.34 meters. This could, for example, be applied in future research with larger samples of species or in other types of vegetation.
Downloads
References
Andrade, A. C. D. (2008). Gestão de áreas verdes em ambientes urbanos:(uma contribuição á análise e resolução de conflitos sócioambientais) (Master's thesis, Universidade Federal de Pernambuco).
de Almeida, D. R. A., Broadbent, E., Zambrano, A. A., Christopher, S., & Brancalion, S. (2019). Monitoramento da estrutura de plantios de restauração florestal estabelecidos sob diferentes intensidades de manejo usando drone-lidar. Disponível em: https://proceedings.science/sbsr-2019/trabalhos/monitoramento-da-estrutura-de-plantios-de-restauracao-florestal-estabelecidos-so?lang=pt-br
Boa morte, C. L.; Salvo, D. G. D.; Coelho, R. C. S.; Barros, R. S (2018). “Avaliação da qualidade de ortofotomosaico e mde gerado a partir de vant multirotor”. 40ª Jornada Giulio Massarani de Iniciação Científica, Artística e Cultural da UFRJ.
Morte, C. D. L. B., de Carvalho, L. F. S. G., & de Barros, R. S. (2020). Uso de vant como ferramenta para estimativa de altura de dossel em manguezal: um estudo investigativo em guaratiba, rio de janeiro, brasil. Revista Tamoios, 16(3). Doi: https://doi.org/10.12957/tamoios.2020.55745
Bueno, J. O. A., Bourscheidt, V., Pezzopane, J. R. M., BERNARDI, A. D. C., & Crestana, S. (2019). Metodologia para estimar altura de árvores com base em imagens aéreas capturadas por drone.
Jorge, L. D. C., & Inamasu, R. Y. (2014). Uso de veículos aéreos não tripulados (VANT) em agricultura de precisão.
Câmara, G., & MEDEIROS, J. S. D. (2005). Modelagem de dados em geoprocessamento. Sistemas de Informação Geográfica: aplicações na agricultura (ED Assad & EE Sano, eds). EMBRAPA, Brasília, 47-66.
Dandois, JP, & Ellis, EC (2013). Mapeamento tridimensional de alta resolução espacial da dinâmica espectral da vegetação usando visão computacional. Remote Sensing of Environment , 136 , 259-276. Doi: https://doi.org/10.1016/j.rse.2013.04.005
Galvincio, J. D. Popescu, S. C (2016). Medindo a altura individual das árvores e o diâmetro da copa para árvores de mangue com dados LiDAR aerotransportados. International Journal of Advanced Engineering, Management and Science, 2 (5), 239456. Doi: https://ijaems.com/detail/measuring-individual-tree-height-and-crown-diameter-for-mangrove-trees-with-airborne-lidar-data/
Graça, N. L. S. de S., A. Mitishita, E., & Gonçalves, J. E.. (2017). Use of uav platform as an autonomous tool for estimating expansion on invaded agricultural land. Boletim De Ciências Geodésicas, 23(3), 509–519. https://doi.org/10.1590/S1982-21702017000300034
Hufkens, K., Friedl, M., Sonnentag, O., Braswell, BH, Milliman, T., & Richardson, AD (2012). Vinculando medições de sensoriamento remoto próximo à superfície e por satélite da fenologia da floresta decídua de folha larga. Sensoriamento Remoto do Meio Ambiente , 117 , 307-321. Doi:10.1016/j.rse.2011.10.006
AlmeidA, R., Júnior, C. (2018). Atlas dos Manguezais do Brasil. Ministério do Meio Ambiente, Instituto Chico Mendes de Conservação da Biodiversidade, Brasília.
Iizuka, K., Yonehara, T., Itoh, M., & Kosugi, Y. (2017). Estimation of tree height and diameter at breast height (DBH) from digital surface models and orthophotos obtained with an unmanned aerial system for a Japanese cypress (Chamaecyparis obtusa) forest. Remote Sensing, 10(1), 13. https://doi.org/10.3390/rs10010013
De Queiroga Miranda, R., Nóbrega, R. L. B., de Moura, M. S. B., Raghavan, S., & Galvíncio, J. D. (2020). Realistic and simplified models of vegetation and leaf area indices for a seasonally dry tropical forest. International Journal of Applied Earth Observation and Geoinformation, 85, 101992. https://doi.org/10.1016/j.jag.2019.101992
Ortega-Farías, S., Ortega-Salazar, S., Poblete, T., Kilic, A., Allen, R., Poblete-Echeverría, C., ... & Sepúlveda, D. (2016). Estimation of energy balance components in a drip-irrigated olive orchard using thermal and multispectral cameras placed on a helicopter-based unmanned aerial vehicle (UAV). Remote Sensing, 8(8), 638. https://doi.org/10.3390/rs8080638
De Souza Pereira, F. R. (2016). LiDAR and optical remote sensing applied to above-ground biomass estimation in mangroves: A case study in the Guapimirim APA, RJ. Unpublished Master’s thesis, Universidade Federal do Rio de Janeiro.
Pessoa, M. C. P. Y., Luchiari Junior, A., & Fernandes, E. N. (1997). Principais modelos matemáticos e simuladores utilizados para análise de impactos ambientais das atividades agrícolas. Relatório técnico não publicado.
Puliti, S., Ene, L. T., Gobakken, T., & Næsset, E. (2017). Use of partial-cover UAV data in sampling for large-scale forest inventories. Remote Sensing of Environment, 194, 115-126. https://doi.org/10.1016/j.rse.2017.03.01
Pontes, F., & Freitas, S. (2015). Anais XVII Simpósio Brasileiro de Sensoriamento Remoto - SBSR, João Pessoa-PB, Brasil, n. 1, p. 6381–6388, 25 a 29 de abril de 2015, INPE.
Ribeiro, G. G., Pesck, V. A., Dlugosz, F. L., Stepka, T. F., Konkol, I., & Lisboa, G. D. S. (2019). Determinação de altura em Pinus taeda L. utilizando veículo aéreo não tripulado. Nativa, 7(4), 431-436. https://doi.org/10.31413/nativa.v7i4.7512
Schaeffer-Novelli, Y. (2008). Situação atual do grupo de ecossistemas: Manguezal, marisma e apicum, incluindo os principais vetores de pressão e as perspectivas para sua conservação e uso sustentável. Brasília: Agência Nacional de Petróleo, Gás Natural e Biocombustíveis.
Soares, C. P. B., de Paula Neto, F., & de Souza, A. L. (2011). Dendrometria e Inventário Florestal (2ª ed.). Viçosa: Editora UFV.
Richardson, A. D., Braswell, B. H., Hollinger, D. Y., Jenkins, J. P., & Ollinger, S. V. (2009). Near-surface remote sensing of spatial and temporal variation in canopy phenology. Ecological Applications, 19(6), 1417-1428. https://doi.org/10.1890/08-2022.1
RuleQuest Research. (2020). Data mining with Cubist. Retrieved from https://www.rulequest.com/cubist-info.html
Da Motta Sobrinho, M. A., & de Andrade, A. C. (2009). O desafio da conservação de manguezais em áreas urbanas: Identificação e análise de conflitos socioambientais no Manguezal do Pina–Recife–PE–Brasil. Revista Unimontes Científica, 11(1/2), 8-16.
Souza, C. P. D. (2012). Políticas públicas ambientais e gestão do ecossistema manguezal da Bacia do Pina–Recife/PE:
Análise do licenciamento ambiental do Sistema Viário Via Mangue (Master's thesis, Universidade Federal de Pernambuco).
Rabadán, M. Á. V., Peña, J. S., & Adán, F. S. (2016). Estimation of diameter and height of individual trees for Pinus sylvestris L. based on crown delineation using airborne LiDAR data and the National Forest Inventory. Forest Systems, 25(1), e001. https://doi.org/10.5424/fs/2016251-08324
Veras, L. (1996). Ecossistemas de manguezais: Potencialidades e possibilidades. Recife: Secretaria de Planejamento Urbano e Ambiental.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 José Vinícius De Sousa Florêncio, Maria do Socorro Bezerra de Araújo, Josiclêda Domiciano Galvincio, Rodrigo De Queiroga Miranda
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with Revista Brasileira de Geografia Física agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted to make their work available online before or during the editorial process, on academic social networks, digital repositories, or preprint servers. After publication in Revista Brasileira de Geografia Física, authors are expected to update the preprint or postprint versions on the platforms where they were originally made available, providing a link to the final published version and any other relevant information, with proper recognition of authorship and the initial publication in this journal.
You are free to:
Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
