Low-cost fibre optic matting for direct live-mapping of livestock weight to improve feed efficiency. Development, demonstration & imaging integration.

点击翻译按钮获取中文摘要

This project exploits prior art and know-how in sensor systems design at the University of Manchester (UoM), which has previously been utilised for mapping human gait and tested for the ability to estimate weight. This will be translated into a reference pig unit, at SRUC, to prove that the technology can be made suitably robust for weighing pigs on a mat and that the subsequent data may then be integrated with commercial and prototype pig imaging hardware, as developed by SRUC and commercial partners, including estimation of pig weight. The Bristol Robotics Laboratory (BRL) contributes the capability to determine if vision-based biometrics, combined with the tomographic footfall 'signatures' or imaging system, could feasibly be developed to autonomously identify individual pigs and assign weights to each of them, without using Radio Frequency Identification (RFID) tags, which requires a separate scanner unit. Furthermore, surface tags are prone to damage by the animals, whereas subcutaneous tags are not viable due to migration under the skin, rendering them both unreadable and acting as a source of meat contamination.We aim to demonstrate the feasibility of one or more pig weighing methods suitable for the pig farm environment. To achieve that, we'll design and test for robustness a smart mat system enclosure and electronics; we'll deploy and test an optical weighing system; we'll also demonstrate non-contact technology to identify and assign the estimated weight to individual pigs.