Identification of native palms (Arecaceae) in tropical forest areas based on Convolutional Neural Network with UAV Images
DOI:
https://doi.org/10.26848/rbgf.v16.5.p2360-2374Keywords:
Segmentation, deep learning, CNN, palm trees, remote sensing.Abstract
Palm trees are important components for maintaining biodiversity and ecosystems in tropical forests. Additionally, they are widely used by extractive communities for various purposes, such as food, medicine, and commerce. However, traditional approaches to identifying and mapping their distribution have reported low accuracy rates and high financial and operational costs. To address this problem, artificial neural networks, especially convolutional neural networks, are being used for pattern recognition in images, particularly those collected by low-cost remote equipment such as drones. Such networks have shown high accuracy rates in identifying forest species. This study proposes a method to classify native palm trees of the Arecaceae family in tropical forest areas using images acquired by a low-cost unmanned aerial vehicle and a convolutional neural network. The method achieved more accurate results than conventional approaches, with an accuracy of 95.86%, precision metrics of 99.57%, and recall and precision metrics of 95.95%. Thus, maps derived from these low-cost systems can be useful for supporting community forest management and monitoring projects in the Amazon.
Downloads
References
Acre, Governo do Estado. (2006). Programa estadual de Zoneamento Ecológico-Econômico do estado do Acre. Zoneamento ecológico-econômico do Acre Fase II: Documento síntese – Escala, v. 1, n. 250.000.
Alvez-Valles, C. M., Balslev, H., Garcia-Villacorta, R., Carvalho, F. A., & Menini Neto, L. (2018). Palm species richness, latitudinal gradients, sampling effort, and deforestation in the Amazon region. Acta Botanica Brasilica, 32(4), 527–539. https://doi.org/10.1590/0102-33062018abb0091. DOI: https://doi.org/10.1590/0102-33062017abb0400
Balslev, H., Kahn, F., Millán, B., Svenning, J.-C., Kristiansen, T., Borchsenius, F., Pedersen, D., & Eiserhardt, W. L. (2011). Species diversity and growth forms in tropical American palm communities. The Botanical Review, 77, 381–425. DOI: https://doi.org/10.1007/s12229-011-9084-x
Bengio, Y., Boulanger-Lewandowski, N., & Pascanu, R. (2012). Advances in optimizing recurrent networks. arXiv. https://arxiv.org/abs/1212.0901. DOI: https://doi.org/10.1109/ICASSP.2013.6639349
Branson, S., Wegner, J. D., Hall, D., Lang, N., & Schindler, K. (2014). Beyond counting: New perspectives on optical remote sensing for conservation. Remote Sensing, 6(11), 11089–11102. https://doi.org/10.3390/rs61111089.
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv. https://arxiv.org/abs/1802.02611. DOI: https://doi.org/10.1007/978-3-030-01234-2_49
Cheng, Y. (1995). Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 790–799. https://doi.org/10.1109/34.400568. DOI: https://doi.org/10.1109/34.400568
Comaniciu, D., & Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 603–619. https://doi.org/10.1109/34.1000236. DOI: https://doi.org/10.1109/34.1000236
Culman, M., Delalieux, S., & Van Tricht, K. (2020). Individual palm tree detection using deep learning on RGB imagery to support tree inventory. Remote Sensing, 12(21), 3476. https://doi.org/10.3390/rs12213476. DOI: https://doi.org/10.3390/rs12213476
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition (pp. 248–255). https://doi.org/10.1109/CVPR.2009.5206848. DOI: https://doi.org/10.1109/CVPR.2009.5206848
Fassnacht, F. E., Latifi, H., Sterenczak, K., Modzelewska, A., Lefsky, M., Waser, L. T., Straub, C., & Ghosh, A. (2016). Review of studies on tree species classification from remotely sensed data. Remote Sensing of Environment, 186, 64–87. https://doi.org/10.1016/j.rse.2016.08.013. DOI: https://doi.org/10.1016/j.rse.2016.08.013
Fernandes, B. J. T. (2013). Redes neurais com extração implícita de características para reconhecimento de padrões visuais [Neural networks with implicit feature extraction for visual pattern recognition]. Universidade Federal de Pernambuco. https://repositorio.ufpe.br/handle/123456789/12245.
Ferreira, E. J. L. (2006). Manual das palmeiras do Acre, Brasil [Manual of the palms of Acre, Brazil]. Instituto Nacional de Pesquisas da Amazônia. https://www.nybg.org/bsci/acre/www1/manual%5Ctextunderscore%7B%7Dpalmeiras.html.
Ferreira, M. P., Wagner, F. H., Aragão, L. E. O. C., Shimabukuro, Y. E., & De Souza Filho, C. R. (2019). Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis. ISPRS Journal of Photogrammetry and Remote Sensing, 149, 119–131. https://doi.org/10.1016/j.isprsjprs.2019.01.019. DOI: https://doi.org/10.1016/j.isprsjprs.2019.01.019
Gibril, M. B. A., Shafri, H. Z. M., Shanableh, A., Al-Ruzouq, R., Wayayok, A., & Hashim, S. J. (2021). Deep convolutional neural network for large-scale date palm tree mapping from UAV-based images. Remote Sensing, 13(14), 2787. https://doi.org/10.3390/rs13142787. DOI: https://doi.org/10.3390/rs13142787
Gomes, J. P., Condé, T. M., Santos, R. L., Dionisio, L. F. S., Duarte, O. R., Miranda, D. L. C. de, & Silva, F. D. (2016). Efeitos de gradientes ambientais na fitossociologia de assembleias de palmeiras no Sudeste de Roraima, Brasil [Effects of environmental gradients on the phytosociology of palm assemblages in southeastern Roraima, Brazil]. Nativa, 4(5), 317–327. https://doi.org/10.31413/nativa.v4i5.3581. DOI: https://doi.org/10.14583/2318-7670.v04n05a08
Gonzalez, R. C., & Woods, R. E. (2000). Processamento de imagens digitais [Digital image processing]. Editora Blucher.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. IEEE. DOI: https://doi.org/10.1109/CVPR.2016.90
Husch, B., Beers, T. W., & Kershaw JR, J. A. (2003). Forest mensuration. John Wiley & Sons.
INMET, Instituto Nacional de Meteorologia. (2020)
Khaing, S. H., & Sein, M. M. (2021). Toddy Palm Trees Classification and Counting Using Drone Video: Retuning Hyperparameter Mask-RCNN. In 2021 7th International Conference on Control, Automation and Robotics (ICCAR) (pp. 196-200). IEEE. https://doi.org/10.1109/ICCAR52225.2021.9463466. DOI: https://doi.org/10.1109/ICCAR52225.2021.9463466
Lang, S. (2008). Object-based image analysis for remote sensing applications: modeling reality – dealing with complexity. In T. Blaschke, S. Lang, & G. J. Hay (Eds.), Object-Based Image Analysis (pp. 3-22). Springer. https://doi.org/10.1007/978-3-540-77058-9_1. DOI: https://doi.org/10.1007/978-3-540-77058-9_1
Letsoin, S. M. A., Purwestri, R. C., Rahmawan, F., & Herak, D. (2022). Recognition of Sago Palm Trees Based on Transfer Learning. Remote Sensing, 14(19), 4932. https://doi.org/10.3390/rs14194932. DOI: https://doi.org/10.3390/rs14194932
Li, W., Dong, R., Fu, H., & Yu, L. (2019). Large-Scale Oil Palm Tree Detection from High-Resolution Satellite Images Using Two-Stage Convolutional Neural Networks. Remote Sensing, 11(1), 11. https://doi.org/10.3390/rs11010011. DOI: https://doi.org/10.3390/rs11010011
Lorenzi, H., Noblick, L. R., Kahn, F., & Ferreira, E. (2010). Flora Brasileira Lorenzi: Arecaceae (Palmeiras). Nova Odessa.
Macía, M. J., Armesilla, P. J., Cámara-Leret, R., Paniagua-Zambrana, N., Villalba, S., Balslev, H., & Pardo-de-Santayana, M. (2011). Palm uses in northwestern South America: a quantitative review. The Botanical Review, 77(4), 462–570. https://doi.org/10.1007/s12229-011-9086-8. DOI: https://doi.org/10.1007/s12229-011-9086-8
Marin, W., Mondragon, I. F., & Colorado, J. D. (2022). Aerial Identification of Amazonian Palms in High-Density Forest Using Deep Learning. Forests, 13(5), 655. https://doi.org/10.3390/f13050655. DOI: https://doi.org/10.3390/f13050655
Mittermeier, R. A., Fonseca, G., Rylands, A., & Brandon, K. (2005). Uma breve história da conservação da biodiversidade no Brasil. Megadiversidade, 1(1), 14-21.
Mohamed Barakat A. Gibril, Helmi Zulhaidi Mohd Shafri, Rami Al-Ruzouq, Abdallah Shanableh, Faten Nahas, & Saeed Al Mansoori. (2023). Large-Scale Date Palm Tree Segmentation from Multiscale UAV-Based and Aerial Images Using Deep Vision Transformers. Drones, 7(2), 93. https://doi.org/10.1080/10106049.2022.2142966. DOI: https://doi.org/10.3390/drones7020093
Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press.
Otero, V., Van De Kerchove, R., Satyanarayana, B., Martínez-Espinosa, C., Fisol, M. A. B., Ibrahim, M. R. B., Sulong, I., Mohd-Lokman, H., Lucas, R., & Dahdouh-Guebas, F. (2018). Managing mangrove forests from the sky: Forest inventory using field data and Unmanned Aerial Vehicle (UAV) imagery in the Matang Mangrove Forest Reserve, Peninsular Malaysia. Forest Ecology and Management, 411, 35–45. https://doi.org/10.1016/j.foreco.2017.12.049. DOI: https://doi.org/10.1016/j.foreco.2017.12.049
Peck, M., Mariscal, A., Padbury, M., Cane, T., Kniveton, D., & Chinchero, M. A. (2012). Identifying tropical Ecuadorian Andean trees from inter-crown pixel distributions in hyperspatial aerial imagery. Applied Vegetation Science, 15(4), 548–559. https://doi.org/10.1111/j.1654-109X.2012.01196.x. DOI: https://doi.org/10.1111/j.1654-109X.2012.01196.x
Saldana Ochoa, K., & Guo, Z. (2019). A framework for the management of agricultural resources with automated aerial imagery detection. Computers and Electronics in Agriculture, 162, 53–69. https://doi.org/10.1016/j.compag.2019.03.028. DOI: https://doi.org/10.1016/j.compag.2019.03.028
SFB, Serviço Florestal Brasileiro. (2010). Florestas do Brasil em resumo - 2010: Dados de 2005-2010. Ministério do Meio Ambiente.
Shimodaira, H. (2000). Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2), 227–244. https://doi.org/10.1016/S0378-3758(00)00115-4. DOI: https://doi.org/10.1016/S0378-3758(00)00115-4
Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv. https://arxiv.org/abs/1409.1556.
Sun, Y., Liu, Y., Wang, G., & Zhang, H. (2017). Deep Learning for Plant Identification in Natural Environment. Computational Intelligence and Neuroscience, 2017, 7361042. https://doi.org/10.1155/2017/7361042. DOI: https://doi.org/10.1155/2017/7361042
Wahed, Z., Joseph, A., Zen, H., & Kipli, K. (2022). Sago Palm Detection and its Maturity Identification Based on Improved Convolution
Neural Network. Pertanika Journal of Science & Technology, 30(2). https://doi.org/10.47836/pjst.30.2.20. DOI: https://doi.org/10.47836/pjst.30.2.20
Weinstein, B. G., Marconi, S., Bohlman, S., Zare, A., & White, E. (2019). Individual Tree-Crown Detection in RGB Imagery Using Semi-Supervised Deep Learning Neural Networks. Remote Sensing, 11(11). https://doi.org/10.3390/rs11111309. DOI: https://doi.org/10.3390/rs11111309
Zhu, X. X., Tuia, D., Mou, L., Xia, G. S., Zhang, L., Xu, F., & Fraundorfer, F. (2018). Deep learning in remote sensing: a review. arXiv. https://doi.org/10.48550/arXiv.1710.03959.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Brazilian Journal of Physical Geography
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.
