American Society of Agricultural and Biological Engineers



Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Methodology for determination of body mass gain of broilers in commercial aviaries via digital image analysis

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  131620477,  2013 Kansas City, Missouri, July 21 - July 24, 2013. (doi: http://dx.doi.org/10.13031/aim.20131620477) @2013
Authors:   Cecília de Fátima Souza, Cristina Akemi Mogami, Ilda de Fátima Ferreira Tinôco, Francisco de Assis Carvalho Pinto, Keles Regina Antony Inoue, HOLMER Savastano Júnior
Keywords:   Binary count; precision aviculture image processing

Abstract. The objective of this work was to develop and test an algorithm for determination of the daily weight gain of broilers in commercial aviaries, using image analysis. The study was carried out in two commercial production facilities belonging to the Perdigao agroindustrial Company S/A, in the city of Rio Verde, Goias state, Brazil, during growth phase of the broilers. Both facilities were equipped with tunnel ventilation and sprinkling systems, and one of them had a water sprinkling system over the roof. In each building, a color video camera was installed and connected to a computer. From the data of average daily weight of the animals, the Gompertz and Expolinear models were adjusted to estimate the average weight as a function of the age. For the image processing, it was applied the SciLab programming language, being used 36 images per day, referring to nine days, which totalized 324 images. The images of the standard matrix were submitted to the binarization process, which intended to separate the object of interest, the broiler, from the background. It was verified that the models fit well with the experimental data, resulting in determination coefficients greater than 0.99. It was observed that the binary pixel count increased through the time, in the same way was verified for the weight of the broilers.Thus, it was verified that on average, a daily weight gain of 59 grams represented an increase of 33 pixels. The determination coefficient (R2=0.96) showed that it was adequate the model for determining broiler weight as a function of the number of pixels.

(Download PDF)    (Export to EndNotes)