Representação Postural de Baleias-Jubarte em Imagens Aéreas usando Aprendizado Profundo
Resumo
Este artigo investiga a representação postural de baleias-jubarte (Megaptera novaeangliae) em imagens aéreas obtidas por Veículos Aéreos Não Tripulados, com foco no uso de aprendizado profundo para estimativa de pontos-chave anatômicos. Embora VANTs ampliem a capacidade de monitoramento de cetáceos em ambiente natural, o grande volume de registros visuais e a presença de reflexos, espuma, submersão parcial e variações de postura dificultam a análise manual e a extração sistemática de informações comportamentais. Para enfrentar esse problema, propõe-se um estudo piloto baseado na anotação de 5 pontos anatômicos mínimos e no treinamento de um modelo YOLO para estimativa de pose em imagens de baleias-jubarte. O modelo foi avaliado em um conjunto de teste independente, considerando métricas de detecção, métricas de pose, erro normalizado por ponto e PCK. Os resultados indicam desempenho promissor, com mAP50 de 0,6539 para pose e PCK pareado de 89,26% no limiar de erro normalizado 0,10, embora o resultado end-to-end ainda seja limitado por falhas de detecção e associação. Os achados sustentam a viabilidade da representação postural por pontos-chave como etapa inicial para análises futuras de orientação corporal, deslocamento e interações sociais de jubartes em cenários reais de monitoramento aéreo.
Referências
Alsaidi, M., Al-Jassani, M. G., Bang, C., O’Corry-Crowe, G., Watt, C., Ghazal, M., and Zhuang, H. (2024). Localization and tracking of beluga whales in aerial video using deep learning. Frontiers in Marine Science, 11:1445698.
Andriluka, M., Pishchulin, L., Gehler, P., and Schiele, B. (2014). 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 3686–3693, Columbus, OH, USA. IEEE.
Bagchi, C., Medina, J., Irschick, D. J., Maji, S., and Christiansen, F. (2025). Automated extraction of right whale morphometric data from drone aerial photographs. Remote Sensing in Ecology and Conservation, 11(4):438–453.
Bierlich, K. C., Karki, S., Bird, C. N., Fern, A., and Torres, L. G. (2024). Automated body length and body condition measurements of whales from drone videos for rapid assessment of population health. Marine Mammal Science, 40(4):e13137.
Blázquez, M., Massett, N., O’Callaghan, S., Hogan, M., López-Suárez, P., Lopes, K., Whooley, P., O’Brien, J. M., Wenzel, F. W., O’Connor, I., and Berrow, S. D. (2025). Humpback whale (Megaptera novaeangliae) maturity and body condition in Ireland, Norway and Cabo Verde based on UAS photogrammetry data. Frontiers in Marine Science, 12:1604106.
Boulent, J., Charry, B., Kennedy, M. M., Tissier, E., Fan, R., Marcoux, M., Watt, C. A., and Gagné-Turcotte, A. (2023). Scaling whale monitoring using deep learning: A human-in-the-loop solution for analyzing aerial datasets. Frontiers in Marine Science, 10:1099479.
Castrillon, J. and Bengtson Nash, S. (2020). Evaluating cetacean body condition; a review of traditional approaches and new developments. Ecology and Evolution, 10(12):6144–6162.
Christiansen, F., Dujon, A. M., Sprogis, K. R., Arnould, J. P. Y., and Bejder, L. (2016). Noninvasive unmanned aerial vehicle provides estimates of the energetic cost of reproduction in humpback whales. Ecosphere, 7(10):e01468.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2010). The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2):303–338.
Graving, J. M., Chae, D., Naik, H., Li, L., Koger, B., Costelloe, B. R., and Couzin, I. D. (2019). DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning. eLife, 8:e47994.
Guirado, E., Tabik, S., Rivas, M. L., Alcaraz-Segura, D., and Herrera, F. (2019). Whale counting in satellite and aerial images with deep learning. Scientific Reports, 9(1):14259.
Hodgson, A., Peel, D., and Kelly, N. (2017). Unmanned aerial vehicles for surveying marine fauna: assessing detection probability. Ecological Applications, 27(4):1253–1267.
Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83–97.
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., and Dollár, P. (2014). Microsoft COCO: Common Objects in Context.
Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022). YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss.
Martins, C., Morete, M., H.Engel, M., Freitas, A., Secchi, E., and Kinas, P. (2001). Aspects of habitat use patterns of humpback whales in the Abrolhos Bank, Brazil, breeding ground. Memoirs of the Queensland Museum, 47:563–570.
Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, V. N., Mathis, M. W., and Bethge, M. (2018). DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9):1281–1289.
Napoli, C., Hirtle, N., Stepanuk, J., Christiansen, F., Heywood, E. I., Grove, T. J., Stoller, A., Dodds, F., Glarou, M., Rasmussen, M. H., Lonati, G. L., Davies, K. T., Videsen, S., Simon, M. J., Boye, T. K., Zoidis, A., Todd, S. K., and Thorne, L. H. (2024). Drone-based photogrammetry reveals differences in humpback whale body condition and mass across North Atlantic foraging grounds. Frontiers in Marine Science, 11:1336455.
Pereira, T. D., Tabris, N., Matsliah, A., Turner, D. M., Li, J., Ravindranath, S., Papadoyannis, E. S., Normand, E., Deutsch, D. S., Wang, Z. Y., McKenzie-Smith, G. C., Mitelut, C. C., Castro, M. D., D’Uva, J., Kislin, M., Sanes, D. H., Kocher, S. D., Wang, S. S.-H., Falkner, A. L., Shaevitz, J. W., and Murthy, M. (2022). SLEAP: A deep learning system for multi-animal pose tracking. Nature Methods, 19(4):486–495.
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., Van Langevelde, F., Burghardt, T., Kays, R., Klinck, H., Wikelski, M., Couzin, I. D., Van Horn, G., Crofoot, M. C., Stewart, C. V., and Berger-Wolf, T. (2022). Perspectives in machine learning for wildlife conservation. Nature Communications, 13(1):792.
Weinstein, B. G. (2018). A computer vision for animal ecology. Journal of Animal Ecology, 87(3):533–545.
Yang, Y. and Ramanan, D. (2011). Articulated pose estimation with flexible mixtures-of-parts. In CVPR 2011, pages 1385–1392, Colorado Springs, CO, USA. IEEE.
Andriluka, M., Pishchulin, L., Gehler, P., and Schiele, B. (2014). 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 3686–3693, Columbus, OH, USA. IEEE.
Bagchi, C., Medina, J., Irschick, D. J., Maji, S., and Christiansen, F. (2025). Automated extraction of right whale morphometric data from drone aerial photographs. Remote Sensing in Ecology and Conservation, 11(4):438–453.
Bierlich, K. C., Karki, S., Bird, C. N., Fern, A., and Torres, L. G. (2024). Automated body length and body condition measurements of whales from drone videos for rapid assessment of population health. Marine Mammal Science, 40(4):e13137.
Blázquez, M., Massett, N., O’Callaghan, S., Hogan, M., López-Suárez, P., Lopes, K., Whooley, P., O’Brien, J. M., Wenzel, F. W., O’Connor, I., and Berrow, S. D. (2025). Humpback whale (Megaptera novaeangliae) maturity and body condition in Ireland, Norway and Cabo Verde based on UAS photogrammetry data. Frontiers in Marine Science, 12:1604106.
Boulent, J., Charry, B., Kennedy, M. M., Tissier, E., Fan, R., Marcoux, M., Watt, C. A., and Gagné-Turcotte, A. (2023). Scaling whale monitoring using deep learning: A human-in-the-loop solution for analyzing aerial datasets. Frontiers in Marine Science, 10:1099479.
Castrillon, J. and Bengtson Nash, S. (2020). Evaluating cetacean body condition; a review of traditional approaches and new developments. Ecology and Evolution, 10(12):6144–6162.
Christiansen, F., Dujon, A. M., Sprogis, K. R., Arnould, J. P. Y., and Bejder, L. (2016). Noninvasive unmanned aerial vehicle provides estimates of the energetic cost of reproduction in humpback whales. Ecosphere, 7(10):e01468.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2010). The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2):303–338.
Graving, J. M., Chae, D., Naik, H., Li, L., Koger, B., Costelloe, B. R., and Couzin, I. D. (2019). DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning. eLife, 8:e47994.
Guirado, E., Tabik, S., Rivas, M. L., Alcaraz-Segura, D., and Herrera, F. (2019). Whale counting in satellite and aerial images with deep learning. Scientific Reports, 9(1):14259.
Hodgson, A., Peel, D., and Kelly, N. (2017). Unmanned aerial vehicles for surveying marine fauna: assessing detection probability. Ecological Applications, 27(4):1253–1267.
Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83–97.
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., and Dollár, P. (2014). Microsoft COCO: Common Objects in Context.
Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022). YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss.
Martins, C., Morete, M., H.Engel, M., Freitas, A., Secchi, E., and Kinas, P. (2001). Aspects of habitat use patterns of humpback whales in the Abrolhos Bank, Brazil, breeding ground. Memoirs of the Queensland Museum, 47:563–570.
Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, V. N., Mathis, M. W., and Bethge, M. (2018). DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9):1281–1289.
Napoli, C., Hirtle, N., Stepanuk, J., Christiansen, F., Heywood, E. I., Grove, T. J., Stoller, A., Dodds, F., Glarou, M., Rasmussen, M. H., Lonati, G. L., Davies, K. T., Videsen, S., Simon, M. J., Boye, T. K., Zoidis, A., Todd, S. K., and Thorne, L. H. (2024). Drone-based photogrammetry reveals differences in humpback whale body condition and mass across North Atlantic foraging grounds. Frontiers in Marine Science, 11:1336455.
Pereira, T. D., Tabris, N., Matsliah, A., Turner, D. M., Li, J., Ravindranath, S., Papadoyannis, E. S., Normand, E., Deutsch, D. S., Wang, Z. Y., McKenzie-Smith, G. C., Mitelut, C. C., Castro, M. D., D’Uva, J., Kislin, M., Sanes, D. H., Kocher, S. D., Wang, S. S.-H., Falkner, A. L., Shaevitz, J. W., and Murthy, M. (2022). SLEAP: A deep learning system for multi-animal pose tracking. Nature Methods, 19(4):486–495.
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., Van Langevelde, F., Burghardt, T., Kays, R., Klinck, H., Wikelski, M., Couzin, I. D., Van Horn, G., Crofoot, M. C., Stewart, C. V., and Berger-Wolf, T. (2022). Perspectives in machine learning for wildlife conservation. Nature Communications, 13(1):792.
Weinstein, B. G. (2018). A computer vision for animal ecology. Journal of Animal Ecology, 87(3):533–545.
Yang, Y. and Ramanan, D. (2011). Articulated pose estimation with flexible mixtures-of-parts. In CVPR 2011, pages 1385–1392, Colorado Springs, CO, USA. IEEE.
Publicado
23/09/2026
Como Citar
ARGOLO, Reinan L.; OLIVEIRA, Alexandre E. C.; SANTOS, Lucas S. C.; IGLESIAS, Susana M.; AMBRÓSIO, Paulo E.; RIGHI, Bianca M.; PENDU, Yvonnick Le.
Representação Postural de Baleias-Jubarte em Imagens Aéreas usando Aprendizado Profundo. In: ESCOLA REGIONAL DE COMPUTAÇÃO BAHIA, ALAGOAS E SERGIPE (ERBASE), 26. , 2026, Maragogi/AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 289-298.
DOI: https://doi.org/10.5753/erbase.2026.31997.
