UAV and ML-based AçaíPalm Monitoring in the Amazon: Facilitating YOLOv8 Usage in Agricultural Practices

• Prince Nyarko PCT Guamá
• Ilan Correa PCT Guamá
• Hervé Rogez PCT Guamá
• Aldebaro Klautau PCT Guamá

DOI: https://doi.org/10.5753/wcama.2025.9208

Abstract

This study explores the application of deep learning to detect and count açaípalm trees (Euterpe oleracea) in the Amazon using UAV imagery. A YOLOv8n model was trained on a georeferenced dataset collected across three municipalities at Northeast of the state of Pará, Brazil, achieving a mean average precision of 0.809 at IoU 0.5 (mAP50) and 0.312 at mAP50–95. The model was integrated into a web platform to enable non-experts, such as farmers and conservationists, to upload imagery and receive annotated results in real time. This facilitates more scalable and sustainable monitoring of açaípopulations and supports forest conservation efforts.

References

Bansal, P. and Ouda, A. (2022). Study on integration of fastapi and machine learning for continuous authentication of behavioral biometrics. In 2022 International Symposium on Networks, Computers and Communications (ISNCC), pages 1–6.

Castro, P., Borges, J., Klautau, S., Pinheiro, S., Shibata, L., Lins, S., and Klautau, A. (2020). Uav-based crop monitoring through multispectral image processing using open-source tools. In Proceedings of the XXXVIII Brazilian Symposium on Telecommunications and Signal Processing (SBrT), pages 22–25, Florianópolis, SC.

Euler, A. M. C. (2020). Aspectos socioeconômicos e ambientais do açaizeiro no estado do amapá. II Jornada de Botânica e Ecologia, II Jornada Amapaense de Botânica, pages 254–258.

Freitas, M. A., Magalhães, J. L., Carmona, C. P., Arroyo-Rodríguez, V., Vieira, I. C., and Tabarelli, M. (2021). Intensification of açaípalm management largely impoverishes tree assemblages in the amazon estuarine forest. Biological Conservation, 261:109251.

IBGE (2019). Produção da extração vegetal e da silvicultura. Instituto Brasileiro de Geografia e Estatística.

INPE (2021). Monitoramento do desmatamento na amazônia legal por satélite. Instituto Nacional de Pesquisas Espaciais.

Junos, M. H. and Thannirmalai, S. (2021). Performance evaluation of improved yolo models for fruit detection. In Editor, A., editor, Smart Agriculture Technologies, pages 123–134. Springer.

Mendonça, A. U. and Guedes, E. B. (2024). Classificacao e deteccao inteligentes de graos para agricultura digital na cultura do milho. In Laboratório de Sistemas Inteligentes, Escola Superior de Tecnologia, Universidade do Estado do Amazonas, pages 1–10. Universidade do Estado do Amazonas.

Neto, J. T. F., de Carvalho, J. E. U., do Socorro Padilha de Oliveira, M., and do Nascimento, W. M. O. (2021). Estimativas de produtividade. Content fully migrated on: 12/20/2021.

Osco, L. P., dos Santos de Arruda, M., Junior, J. M., da Silva, N. B., Ramos, A. P. M., Érika Akemi Saito Moryia, Imai, N. N., Pereira, D. R., Creste, J. E., Matsubara, E. T., Li, J., and Gonçalves, W. N. (2020). A convolutional neural network approach for counting and geolocating citrus trees in uav multispectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 160:97–106.

Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A survey on performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 237–242.

Sohan, M., Sai Ram, T., and Rami Reddy, C. V. (2024). A review on yolov8 and its advancements. In Jacob, I. J., Piramuthu, S., and Falkowski-Gilski, P., editors, Data Intelligence and Cognitive Informatics, pages 529–545. Springer Nature Singapore, Singapore.

Tan, X. J., Cheor, W. L., Yeo, K. S., and Leow, W. Z. (2022). Expert systems in oil palm precision agriculture: A decade systematic review. Journal of King Saud University - Computer and Information Sciences, 34(2):1321–1334.

Ultralytics (2023). Yolov8 documentation. Accessed: 2024-10-01.