| Texto completo | |
| Autor(es): |
Arnal Barbedo, Jayme Garcia
[1]
;
Koenigkan, Luciano Vieira
[1]
;
Santos, Patricia Menezes
[2]
;
Bueno Ribeiro, Andrea Roberto
[3]
Número total de Autores: 4
|
| Afiliação do(s) autor(es): | [1] Embrapa Agr Informat, BR-13083886 Campinas - Brazil
[2] Embrapa Southeast Livestock, BR-13560970 Sao Carlos - Brazil
[3] Univ Santo Amaro, UNIP, UNISA, BR-04743030 Sao Paulo - Brazil
Número total de Afiliações: 3
|
| Tipo de documento: | Artigo Científico |
| Fonte: | SENSORS; v. 20, n. 7 APR 2020. |
| Citações Web of Science: | 1 |
| Resumo | |
The management of livestock in extensive production systems may be challenging, especially in large areas. Using Unmanned Aerial Vehicles (UAVs) to collect images from the area of interest is quickly becoming a viable alternative, but suitable algorithms for extraction of relevant information from the images are still rare. This article proposes a method for counting cattle which combines a deep learning model for rough animal location, color space manipulation to increase contrast between animals and background, mathematical morphology to isolate the animals and infer the number of individuals in clustered groups, and image matching to take into account image overlap. Using Nelore and Canchim breeds as a case study, the proposed approach yields accuracies over 90% under a wide variety of conditions and backgrounds. (AU) | |
| Processo FAPESP: | 18/12845-9 - Detecção e contagem de gado usando veículos aéreos não tripulados |
| Beneficiário: | Jayme Garcia Arnal Barbedo |
| Modalidade de apoio: | Auxílio à Pesquisa - Programa eScience e Data Science - Regular |