Lecture Notes in Computer Science vol:8192 pages:555-563
Advanced Concepts for Intelligent Vision Systems location:Poznan, Poland date:October 28-31 2013
The purpose of this study is to investigate the feasibility and validity of an automated image processing method to detect the active pigs housed under experimental conditions. Top-view video images were captured for forty piglets, housed ten per pen. On average, piglets had a weight of 27 kg (SD = 4.4 kg) kilograms at the start of experiments and 40kg (SD=6.5) at the end. Each pen was monitored by a top-view CCD camera. The image analysis protocol to automatically quantify activity consisted of several steps. First, in order to localise the pigs, ellipse fitting algorithms were employed. Subsequently, activity was calculated by subtracting image background and comparing binarised images. To validate the results, they were compared to manually labelled behavioural data ('active' versus 'inactive'). This is the first study to show that active pigs in a group can be detected using image analysis with an accuracy of 89.8 %. Since being active is known to be associated with the behavioural status, careful monitoring can give an indication of the health and welfare of pigs.