COUNTING NELORE CATTLE USING COMPUTER VISION IN AERIAL IMAGES
DOI:
https://doi.org/10.61164/rsv.v8i1.2047Keywords:
Nelore, visão computacional e pecuária.Abstract
The article proposes an innovative approach for the automated identification and counting of Nelore cattle, using advanced computer vision techniques. Initially, the economic and food importance of livestock farming, especially the Nelore breed, stands out. The literature review covers computer vision techniques and livestock counting computer systems, allowing the comparison of characteristics, functionalities, algorithms and machine learning used. Furthermore, accuracy and efficiency metrics are proposed to evaluate the performance of automated systems, comparing them with traditional methods. The study not only aims to improve the management of the Nelore herd, but also contributes to scientific advancement in the practical application of computer vision in livestock farming. By offering practical support to rural producers in the selection and implementation of efficient systems, the aim is to promote the modernization and improvement of herd management practices, in line with the current demands of the agricultural sector.
References
Kellenberger B., Marcos D., TUIA D.(2018). Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning. Remote Sensing of Environment. Link: https://www.sciencedirect.com/science/article/abs/pii/S0034425718303067 DOI: https://doi.org/10.1016/j.rse.2018.06.028
Andrew W., Greatwood C., Burghardt T. (2017). Visual localisation and individual identification of holstein friesian cattle via deep learning. Proceedings of the IEEE international conference on computer vision workshops. Link: https://openaccess.thecvf.com/content_ICCV_2017_workshops/w41/html/Andrew_Visual_Localisation_and_ICCV_2017_paper.html DOI: https://doi.org/10.1109/ICCVW.2017.336
Alexandre Brito (2021). Reconhecimento Facial Bovino: uma alternativa aos Métodos Tradicionais de Rastreio. Engenharia de Controle e Automação — Universidade de Caxias do Sul, Área do conhecimento de ciências exatas e engenharias – Caxias do Sul/RS, Brasil. Link:https://repositorio.ucs.br/xmlui/handle/11338/9364;jsessionid=CBD94A22C706225268DE7F1C212170E7
Garcia J. A. B., Vieira L. K., Teixeira T. S., Menezes P. S. (2019). A Study on the Detection of Cattle in UAV Images Using Deep Learning. Embrapa Informática Agropecuária, Campinas, São Paulo e Embrapa Pecuária Sudeste, São Carlos, São Paulo, Brasil. Link: https://www.mdpi.com/1424-8220/19/24/5436
Midlej J. E. S., Lima J. O. F. (2020). Detecção e Contagem de Bovinos em Imagens Aereas utilizando Visão Computacional. Departamento de Ciências Exatas e Tecnológicas, Universidade Estatual de Santa Cruz (UESC) – Ilhéus, BA – Brasil. Link: https://sol.sbc.org.br/index.php/erbase/article/view/15462
Ribeiro, N. G. Vi., Guedes, G. B. e Bardieri, T. T. (2019). Aplicação de algoritmos de visão computacional na contagem de gado por meio de processamento de imagens aéreas. Instituto Federal de Educação, Ciências e Tecnologia de São Paulo, Campus Hortolândia, São Paulo – Brasil. Link: https://revistas.setrem.com.br/index.php/reabtic/article/view/343]
Secretário J. H. A., Pires R. (2018). Uso de visão computacional para contagem automática de células em imagens obtidas por microscópios. IFSP – Campus de São Paulo - Brasil. Link: https://regrasp.spo.ifsp.edu.br/index.php/regrasp/article/view/234
Silva E. J., Minadeo R. (2018). Sistema RFID: Vantagens e Desvantagens Observadas na Implementação em Estudos de Casos.
Universidade de Brasilia – UNB, Brasil. Link: https://www.researchgate.net/profile/Roberto-Minadeo/publication/329921526_SISTEMA_RFID_VANTAGENS_E_DESVANTAGENS_OBSERVADAS_NA_IMPLEMENTACAO_EM_ESTUDOS_DE_CASOS/links/5c2381d7a6fdccfc706a2556/SISTEMA-RFID-VANTAGENS-E-DESVANTAGENS-OBSERVADAS-NA-IMPLEMENTACAO-EM-ESTUDOS-DE-CASOS.pdf
David L. R. (2008). Sistema de controle de animais de corte através da tecnologia RFID. Faculdade de Tecnologia e Ciências Sociais Aplicada (FATECS). UNICEUB. Brasilia – Distrito Federal, Brasil. Link: https://repositorio.ucs.br/xmlui/handle/11338/9364;jsessionid=CBD94A22C706225268DE7F1C212170E7w
Valadão L., Dopcke G. (2022). Além de gigantes como IBM, Intel e Microsoft, empresas do agronegócio, sobretudo as agtechs, têm despertado para o potencial da visão computacional para identificar padrões em escala, Revista EY, Campinas – São Paulo, Brasil. Link: https://www.ey.com/pt_br/agencia-ey/noticias/a-visao-computacional-na-transformacao-para-a-agropecuaria-4-0
