| dc.identifier.citation | COW DETECTION IDENTIFIER. Cow Behavior Tracking Dataset, 2024. Disponível em: https://universe.roboflow.com/cow-detection-identifier/cow-behavior-tracking. Acesso em: 17 fev. 2025. DA SILVA, D. L.; SEIJAS, L. M.; BASTOS-FILHO, C. J. A. Artificial Bee Colony Optimization for Feature Selection of Traffic Sign Recognition. International Journal of Swarm Intelligence Research, v. 8, n. 2, p. 50–66, abr. 2017. DENG, Jia et al. ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, Miami, FL. Anais [...]. IEEE, 2009. p. 248–255. DOI: 10.1109/CVPR.2009.5206848. EVERINGHAM, M. et al. The PASCAL Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, v. 88, n. 2, p. 303-338, 2010. DOI: https://doi.org/10.1007/s11263-009-0275-4. GUARNIDO-LOPEZ, P.; RAMIREZ-AGUDELO, J. F.; DENIMAL, E.; BENAOAUDA, M. Programming and Setting Up the Object Detection Algorithm YOLO to Determine Feeding Activities of Beef Cattle: A Comparison between YOLOv8m and YOLOv10m. Animals, v. 14, n. 19, p. 2821, 2024. Disponível em: https://doi.org/10.3390/ani14192821. HE, K.; ZHANG, X.; REN, S.; SUN, J. Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, 2016, Las Vegas. Anais [...]. IEEE, 2016. p. 770–778. HONG, Y.; GAO, L.; CHEN, J.; SHI, M. Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. arXiv preprint, arXiv:2101.06085, 2021. Disponível em: https://arxiv.org/abs/2101.06085. KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, v. 25, p. 1097–1105, 2012. KOHAVI, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE. Proceedings… San Mateo: Morgan Kaufmann, 1995. p. 1137–1145. LIN, Tsung-Yi et al. Microsoft COCO: Common Objects in Context. In: European Conference on Computer Vision, 2014, Zurich. Anais [...]. Cham: Springer, 2014. p. 740–755. DOI: 10.1007/978-3-319-10602-1_48. LIU, Kang; WANG, Shengli; WU, Chao. Application of YOLOv4 and DeepSort in real-time poultry behavior detection and tracking. Computers and Electronics in Agriculture, v. 186, p. 106171, 2021. Disponível em: https://doi.org/10.1016/j.compag.2021.106171. MARCIA DEL CAMPO, M.; MONTOSSI, F.; SOARES DE LIMA, J. M.; BRITO, G. Future cattle production: Animal welfare as a critical component of sustainability and beef quality, a South American perspective. Meat Science, v. 219, p. 109672, 2024. Disponível em: https://doi.org/10.1016/j.meatsci.2024.109672. MICHAEL, S.; COCKRAM, M. Cattle handling stress and transportation. In: GRANDIN, T. (org.). Livestock Handling and Transport. 5. ed. Cambridge: Elsevier, 2024. p. 666–674. DOI: 10.1016/B978-0-323-85125-1.00033-8. REDMON, J.; DIVVALA, S.; GIRSHICK, R.; FARHADI, A. You Only Look Once: Unified, real-time object detection. arXiv preprint, 2015. Disponível em: https://arxiv.org/abs/1506.02640. TONG, L.; FANG, J.; WANG, X.; ZHAO, Y. Research on Cattle Behavior Recognition and Multi-Object Tracking Algorithm Based on YOLO-BoT. Animals, v. 14, n. 20, p. 2993, 2024. Disponível em: https://doi.org/10.3390/ani14202993. | pt_BR |
| dc.description.abstract | Livestock farming plays a crucial role in the Brazilian economy, particularly in beef production and exportation. However, beef cattle farming faces challenges related to efficient resource management and animal welfare. The prolonged production cycle and high nutritional demands of beef cattle result in delayed financial returns, necessitating strategies to optimize management and ensure animal health. In this context, monitoring cattle behavior emerges as a strategic tool. This study proposes the development of an automated monitoring system utilizing deep learning to identify and classify cattle behavioral activities, such as drinking, feeding, lying down, and standing, from images obtained in the herd's resting and confinement environment. The solution aims to continuously monitor the animals, identifying behavioral patterns
and irregularities that may indicate the need for interventions to ensure welfare and increase productivity. The system, aimed at precision agriculture, provides relevant information for strategic decisions, promoting more sustainable and efficient management in contemporary livestock farming. | pt_BR |
