Embrapa develops technology to monitor herd with drone



The activity of monitoring the livestock population is essential in the management of livestock farms. However, in the large estates that adopt the extensive cattle ranching, very common in Brazil, this count requires advanced technology and methods. But the Brazilian Agricultural Research Corporation (Embrapa) will coordinate a survey for detection and counting using an unmanned aerial vehicle (Vant), also popularized as a drone.

The project, led by researcher Jayme Garcia Arnal Barbedo of Embrapa Informática Agropecuária (SP), was approved for funding by the Foundation for Research Support of the State of São Paulo (Fapesp). "Aerial surveys appear as a potential solution," explains Barbedo. There are already some initiatives being implemented on farms, but still with several disadvantages, such as high operating costs, high noise levels and risk of accidents. Therefore, the researchers want to employ techniques of image processing and machine learning, combined with the development of software and drone use, seeking to generate more adequate solutions for the monitoring of animals in the pasture.

Among the objectives are the development of a methodology for cattle ranching using drones equipped with cameras with visible spectrum and the creation of an algorithm to automatically recognize and count the cattle in the captured images.

Two different approaches will be investigated: the first is with the use of a conventional camera and the other with a 360 degree. The main difference between the two methodologies is that the first one usually requires multiple flights to cover large areas, while the second may be able to view much larger regions with a single flight, although losing resolution, since the animals are further from the camera, according to the researcher.

The project seeks to advance in the field of computer science, producing new algorithms based on images for animal detection and for its management, with innovative approach for counting cattle. "This methodology can also be used in the future to work on other aspects of cattle monitoring such as animal health, body measurements, among others," says Barbedo. Read more.

Source: Canal Rural

CAMPUS II Samambaia - Post Office Box: 131 - Goiânia - GO - Brazil / Zip code: 74001-970
Phone: +55 62 3521-1360 / +55 62 3521-1096
E-mail: contato@pastagem.org
Twitter: @pastagem_org