Classificação de espécies de árvores em imagens de cenário urbano usando Redes Neurais Convolucionais com Triplet Loss
Resumo
A catalogação de espécies arbóreas é fundamental para a conservação da biodiversidade e o planejamento urbano, porém métodos presenciais possuem alto custo e alcance limitado. Buscando mitigar essas barreiras, o presente trabalho investiga o uso de Deep Learning para classificação de 14 espécies de árvores em imagens de contexto urbano via aprendizado de similaridade com Triplet loss e módulos de atenção. Os resultados demonstram que métodos de similaridade podem obter maior precisão com menos dados e custo computacional, destacando-se a rede EfficientNet-B5 com Triplet Loss, que alcançou F1-score médio de 0,881 e maior robustez em classes desafiadoras e com poucas amostras, como Holocalyx balansae e Ligustrum lucidum.Referências
Adam, K. D. B. J. et al. (2014). A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 1412(6).
Cetin, Z., Yilmaz, A., and Ozcan, G. (2022). Deep learning-based tree species classification using street view images in urban environments. Urban Forestry Urban Greening, 74:127638.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778.
Hoffer, E. and Ailon, N. (2015). Deep metric learning using triplet network. In International Workshop on Similarity-Based Pattern Recognition, pages 84–92. Springer.
Hossain, M. A., Tayef, G., and Subhan, N. (2026). Hybridsolarnet: A lightweight and explainable efficientnet-cbam architecture for real-time solar panel fault detection. arXiv preprint arXiv:2601.02928.
Hou, Q., Zhou, D., and Feng, J. (2021). Coordinate attention for efficient mobile network design. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13713–13722.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Jodas, D. S., Yojo, T., Brazolin, S., Velasco, G. D. N., and Papa, J. P. (2022). Detection of trees on street-view images using a convolutional neural network. International Journal of Neural Systems, 32(01):2150042.
Kattenborn, T., Leitold, V., Schiefer, F., and Feilhauer, H. (2021). Review on convolutional neural networks (cnn) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173:24–49.
Kaya, M. and Bilge, H. Ş. (2019). Deep metric learning: A survey. Symmetry, 11(9):1066.
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022.
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A convnet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11976–11986.
Osako, L. S., Barbosa, W. N., et al. (2021). Individual tree crown segmentation and species classification in subtropical forest using airborne lidar data and convnets. Remote Sensing, 13(18):3714.
Passos, L. A., Jodas, D. S., Akaki, A. S., and Papa, J. P. (2022). Multiclass oversampling via optimum-path forest for tree species classification from street-view perspectives. Computers and Electronics in Agriculture.
Schroff, F., Kalenichenko, D., and Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823.
Silva, A. et al. (2023). Classificação de coberturas e espécies de árvores em ambientes urbanos tropicais utilizando redes neurais convolucionais e conceitos de conjuntos fechados e abertos: Revisão bibliográfica. Revista de Teledetecção.
Snell, J., Swersky, K., and Zemel, R. (2016). Prototypical networks for few-shot learning.
Sohn, K. (2016). Improved deep metric learning with multi-class n-pair loss objective. Advances in neural information processing systems, 29.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), volume 30.
Woo, S., Park, J., Lee, J.-Y., and Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pages 3–19.
Yang, T., Zhou, S., Huang, Z., Xu, A., Ye, J., and Yin, J. (2023). Urban street tree dataset for image classification and instance segmentation. Computers and Electronics in Agriculture, 209:107852.
Zhu, X. X., Tuia, D., Mou, L., Xia, G.-S., Zhang, L., Xu, F., and Fraundorfer, F. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4):8–36.
Cetin, Z., Yilmaz, A., and Ozcan, G. (2022). Deep learning-based tree species classification using street view images in urban environments. Urban Forestry Urban Greening, 74:127638.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778.
Hoffer, E. and Ailon, N. (2015). Deep metric learning using triplet network. In International Workshop on Similarity-Based Pattern Recognition, pages 84–92. Springer.
Hossain, M. A., Tayef, G., and Subhan, N. (2026). Hybridsolarnet: A lightweight and explainable efficientnet-cbam architecture for real-time solar panel fault detection. arXiv preprint arXiv:2601.02928.
Hou, Q., Zhou, D., and Feng, J. (2021). Coordinate attention for efficient mobile network design. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13713–13722.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Jodas, D. S., Yojo, T., Brazolin, S., Velasco, G. D. N., and Papa, J. P. (2022). Detection of trees on street-view images using a convolutional neural network. International Journal of Neural Systems, 32(01):2150042.
Kattenborn, T., Leitold, V., Schiefer, F., and Feilhauer, H. (2021). Review on convolutional neural networks (cnn) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173:24–49.
Kaya, M. and Bilge, H. Ş. (2019). Deep metric learning: A survey. Symmetry, 11(9):1066.
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022.
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A convnet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11976–11986.
Osako, L. S., Barbosa, W. N., et al. (2021). Individual tree crown segmentation and species classification in subtropical forest using airborne lidar data and convnets. Remote Sensing, 13(18):3714.
Passos, L. A., Jodas, D. S., Akaki, A. S., and Papa, J. P. (2022). Multiclass oversampling via optimum-path forest for tree species classification from street-view perspectives. Computers and Electronics in Agriculture.
Schroff, F., Kalenichenko, D., and Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823.
Silva, A. et al. (2023). Classificação de coberturas e espécies de árvores em ambientes urbanos tropicais utilizando redes neurais convolucionais e conceitos de conjuntos fechados e abertos: Revisão bibliográfica. Revista de Teledetecção.
Snell, J., Swersky, K., and Zemel, R. (2016). Prototypical networks for few-shot learning.
Sohn, K. (2016). Improved deep metric learning with multi-class n-pair loss objective. Advances in neural information processing systems, 29.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), volume 30.
Woo, S., Park, J., Lee, J.-Y., and Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pages 3–19.
Yang, T., Zhou, S., Huang, Z., Xu, A., Ye, J., and Yin, J. (2023). Urban street tree dataset for image classification and instance segmentation. Computers and Electronics in Agriculture, 209:107852.
Zhu, X. X., Tuia, D., Mou, L., Xia, G.-S., Zhang, L., Xu, F., and Fraundorfer, F. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4):8–36.
Publicado
19/07/2026
Como Citar
BELFORT, Filipe Correia et al.
Classificação de espécies de árvores em imagens de cenário urbano usando Redes Neurais Convolucionais com Triplet Loss. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 179-190.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.23584.
