Development of a Transfer Function for Weight Prediction of Live Broiler Chicken Using Machine Vision

Abstract

The objective of this study was to process digital images to investigate the possibility of broilers body weight estimation based on the dynamic model. For this experiment, 2440 images were recorded by a top-view camera from 30 birds. An ellipse fitting algorithm was applied to localize chickens within the pen, by using a generalized Hough transform. Chickens' head and tail were removed efficiently using the Chan-Vese method. After that, using image processing, six body measures were calculated. Next, they were used to design a Transform Function (TF) model with weight measurements as output. Secondorder dynamic models were used to predict the weight of life broiler chicken, without delay, stable and with the highest R 2 were predominantly selected according to the Young Identification Criterion (YIC) criterion chosen models. It was observed that predicted values rigorously follow the real values. Moreover, the relative body weight errors of chickens in the early days of grow-out was much more than last days. The accuracy of TF for body weight prediction from a comparison between measured (absolute) and predicted total life body weights were estimated for all studied broiler chicken (R 2 =0.98).

A Review on Computer Vision Technology for Monitoring Poultry Farm—Application, Hardware, and Software

“…Computer vision has been widely used in various processes of different poultry production systems. It includes automation of the house management, behavior, and welfare [11,[29][30][31][32][33][34][35][36][37][38][39][40], disease detection [28,[41][42][43][44][45][46][47], weight measurement [27,[48][49], slaughtering process [50][51], carcass quality [52][53][54][55], and egg examination [56][57][58][59][60][61][62][63][64][65]. On the other hand, computer vision also popular on other livestock monitoring, such as pig [73][74][75][76][77][78][79][80], sheep or cattle …”

“…Image segmentation is the most difficult task mentioned by some of the researchers [42,[47][48]. It is a process of forming connected objects with relatively homogeneous properties by grouping related pixels together or partitioning an image into multiple segments with similar attributes [42,70,107].…”

Desenvolvimentos em inteligência artificial na avicultura de frangos de corte

“…Mortensen et al (2016), a partir de dataset rotulado com 13.000 imagens para treinamento de rede neural Bayesiana, utilizaram câmera 3D para capturar o frango sobre uma balança, obtendo 12 descritores de peso diferentes que permitem estimar o peso individual. Amraei et al (2018) propõem um sistema equivalente, com dataset de 2440 imagens e combinação da Transformada de Hough (HT) generalizada e método de Chan-Vese para segmentação. Os 6 descritores obtidos são utilizados para construção de modelo de regressão para predição de peso.…”

Mass detection of walnut based on X‐ray imaging technology

“…The machine vision technology is able to visually acquire the geometric shape and other characteristics of the sample, and provided a noncontact automatic inspection method for grading agricultural products. This technology has the advantages of real‐time, high efficient and objective (Amraei, Mehdizadeh, & Nääs, 2018; Rong, Rao, & Ying, 2017; Saglam & Cetin, 2021; Vidyarthi, Tiwari, & Singh, 2020). Katrin, Marcus, Simone, et al (2019) extracted the geometric dimensions of mangoes using the image processing technology, estimated the fruit mass with the characteristics using length, width and thickness as the input parameters of the ANN, and compared different image processing methods.…”