Abstract
The main objective of this study was to develop and evaluate a model for estimating pigs weight using computer vision for improving the management in Korean swine farms in Korea. This research was carried out in two steps: 1) to find a model that relates the projection area with the weight of a pig; 2) to implement the model in a computer vision system mainly consisted of a monochrome CCD camera, a frame grabber and a computer system for estimating the weight of pigs in a non-contact, real-time manner. The model was developed under an important assumption there were no observable genetic differences among the pigs. The main results were: 1) The relationship between the projection area and the weight of pigs was W = 0.0569 <TEX>${\times}$</TEX> A - 32.585(<TEX>$R^2$</TEX> = 0.953), where W is the weight in kg; A is the projection area of a pig in <TEX>$\textrm{cm}^2$</TEX>; 2) The model could estimate the weight of pigs with an error less than 3.5%.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
