| Full text | |
| Author(s): |
Arnal Barbedo, Jayme Garcia
[1]
;
Koenigkan, Luciano Vieira
[1]
;
Santos, Patricia Menezes
[2]
;
Bueno Ribeiro, Andrea Roberto
[3]
Total Authors: 4
|
| Affiliation: | [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
Total Affiliations: 3
|
| Document type: | Journal article |
| Source: | SENSORS; v. 20, n. 7 APR 2020. |
| Web of Science Citations: | 1 |
| Abstract | |
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) | |
| FAPESP's process: | 18/12845-9 - Cattle detection and counting using unmanned aerial vehicles |
| Grantee: | Jayme Garcia Arnal Barbedo |
| Support Opportunities: | Research Grants - eScience and Data Science Program - Regular Program Grants |