Detection of Cacao Trees in Orthomosaic Images Using YOLOv8 and SAHI
Resumo
This study explores the application of drone-based orthomosaic imagery combined with the YOLOv8x segmentation model and the Slicing Aided Hyper Inference (SAHI) method for detecting cacao trees. High-resolution orthomosaic images were processed by slicing them into smaller tiles to facilitate object segmentation. Although the YOLOv8x model was trained for segmentation, the evaluation was conducted using bounding boxes for ease of comparison. The model achieved a precision of 93.49% and an accuracy of 81.10%, demonstrating its potential for monitoring large-scale plantations. However, the system is best suited for estimation purposes rather than precise, real-time decision-making.
Palavras-chave:
Cacao trees, orthomosaic images, drone survey, computer vision, segmentation, precision agriculture
Referências
KOBLITZ, M. G. B. Café, cacau e chá. In: KOBLITZ, M. G. B. (Ed.). Matérias-primas alimentícias: composição e controle de qualidade. Rio de Janeiro: Guanabara Koogan, 2011. p. 122-146.
SEQUEIRA, Andreia Filipa Caeiro. CACAU: DO FRUTO AO CHOCOLATE. 2016. 27 f. Tese (Doutorado) - Curso de Biologia, Escola Secundária Rainha Santa Isabel, Estremoz, 2016.
SENAR, Serviço Nacional de Aprendizagem Rural. Cacau: produção, manejo e colheita, 2018.
BRAINER, M. S. C. P. Produção de Cacau, Caderno Setorial ETENE. Banco do Nordeste do Brasil, ano 6, nº 149, 2021.
SANTOS FILHO, L. P. et al. Cacauicultura baiana: considerações econômicas e tecnológicas, anos agrícolas de 1975/76 a 2011/12. Ilhéus, BA: CEPLAC/CEPEC, 2021. Boletim Técnico, nº 220, 23p.
IBGE - Instituto Brasileiro de Geografia e Estatística. Produção Agrícola Municipal - PAM. Disponível em: [link]. Acesso em: 2023.
BAHIA DE AGUIAR, P. C.; PIRES, M. M. A região cacaueira do sul do estado da Bahia (Brasil): crise e transformação. Cuadernos de Geografía: Revista Colombiana de Geografía, vol. 28, núm. 1:192, 2019. DOI: 10.15446/rcdg.v28n1.67437. Relatório Anual de Produção de Cacau, 2021.
International Cocoa Organization. Cocoa Market Report. April 2024.
SCHROTH, G., et al. Cocoa in a Changing Climate: Vulnerability and Adaptation. Climatic Change, 2016.
LÄDERACH, P., et al. Predicting the Impact of Climate Change on Cocoa Production. Agricultural Systems, 2013.
Ayubi, A., Faiz, M., Situmorang, G. B., Ramadhani, K. N., Utama, N. P., A Cocoa Ripeness Detection and Classification Model Based on Improved YOLOv5s, 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), 2023, pp. 1-6, DOI: 10.1109/ICAICTA59291.2023.10390119.
Bastidas-Alva, R. A., Paitan Cardenas, J. A., Bazan Espinoza, K. S., Povez Nu˜nez, V. K., Quincho Rivera, M. E., Huaytalla, J., Recognition and classification system for trinitario cocoa fruits according to their ripening stage based on the Yolo v5 algorithm, 2022 Asia Conference on Advanced Robotics, Automation, and Control Engineering (ARACE), 2022, pp. 138-142, DOI: 10.1109/ARACE56528.2022.00032.
Justam, Indrabayu, Zainuddin, Z., Basri, Detection and Counting of the Number of Cocoa Fruits on Trees Using UAV, 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), 2023, pp. 257-263, DOI: 10.1109/IAICT59002.2023.10205752.
Akyon, F. C., Altinuc, S. O., Temizel, A., Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection, 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 966-970, DOI: 10.1109/ICIP46576.2022.9897990.
G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLO, version 8.0.0, Jan. 2023. [Online]. Available: [link]. [Accessed: Sep. 08, 2024].
ALHICHRI, H.; AL-KHUSHI, W.; BOUKERCH, I.; et al. Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images. In: IEEE Access, 2021, p. 1-16.
SEQUEIRA, Andreia Filipa Caeiro. CACAU: DO FRUTO AO CHOCOLATE. 2016. 27 f. Tese (Doutorado) - Curso de Biologia, Escola Secundária Rainha Santa Isabel, Estremoz, 2016.
SENAR, Serviço Nacional de Aprendizagem Rural. Cacau: produção, manejo e colheita, 2018.
BRAINER, M. S. C. P. Produção de Cacau, Caderno Setorial ETENE. Banco do Nordeste do Brasil, ano 6, nº 149, 2021.
SANTOS FILHO, L. P. et al. Cacauicultura baiana: considerações econômicas e tecnológicas, anos agrícolas de 1975/76 a 2011/12. Ilhéus, BA: CEPLAC/CEPEC, 2021. Boletim Técnico, nº 220, 23p.
IBGE - Instituto Brasileiro de Geografia e Estatística. Produção Agrícola Municipal - PAM. Disponível em: [link]. Acesso em: 2023.
BAHIA DE AGUIAR, P. C.; PIRES, M. M. A região cacaueira do sul do estado da Bahia (Brasil): crise e transformação. Cuadernos de Geografía: Revista Colombiana de Geografía, vol. 28, núm. 1:192, 2019. DOI: 10.15446/rcdg.v28n1.67437. Relatório Anual de Produção de Cacau, 2021.
International Cocoa Organization. Cocoa Market Report. April 2024.
SCHROTH, G., et al. Cocoa in a Changing Climate: Vulnerability and Adaptation. Climatic Change, 2016.
LÄDERACH, P., et al. Predicting the Impact of Climate Change on Cocoa Production. Agricultural Systems, 2013.
Ayubi, A., Faiz, M., Situmorang, G. B., Ramadhani, K. N., Utama, N. P., A Cocoa Ripeness Detection and Classification Model Based on Improved YOLOv5s, 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), 2023, pp. 1-6, DOI: 10.1109/ICAICTA59291.2023.10390119.
Bastidas-Alva, R. A., Paitan Cardenas, J. A., Bazan Espinoza, K. S., Povez Nu˜nez, V. K., Quincho Rivera, M. E., Huaytalla, J., Recognition and classification system for trinitario cocoa fruits according to their ripening stage based on the Yolo v5 algorithm, 2022 Asia Conference on Advanced Robotics, Automation, and Control Engineering (ARACE), 2022, pp. 138-142, DOI: 10.1109/ARACE56528.2022.00032.
Justam, Indrabayu, Zainuddin, Z., Basri, Detection and Counting of the Number of Cocoa Fruits on Trees Using UAV, 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), 2023, pp. 257-263, DOI: 10.1109/IAICT59002.2023.10205752.
Akyon, F. C., Altinuc, S. O., Temizel, A., Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection, 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 966-970, DOI: 10.1109/ICIP46576.2022.9897990.
G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLO, version 8.0.0, Jan. 2023. [Online]. Available: [link]. [Accessed: Sep. 08, 2024].
ALHICHRI, H.; AL-KHUSHI, W.; BOUKERCH, I.; et al. Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images. In: IEEE Access, 2021, p. 1-16.
Publicado
06/11/2024
Como Citar
MARTINS, Thiago Mantovani; LIMA, Matheus Arroyo de; JUNQUEIRA, Henrique Montemor; FERREIRA, Victor Hugo Campos; SANTOS, David Barral; PAPA, Giovanni Bruno.
Detection of Cacao Trees in Orthomosaic Images Using YOLOv8 and SAHI. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 19. , 2024, Rio Paranaíba/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 37-41.
DOI: https://doi.org/10.5753/wvc.2024.34010.
