Using augmented reality to improve meat grading
An American study of meat grading found that 50% of meat samples were mis-graded in some way.
This is not unreasonable as grading requires humans to repeatedly make objective and subjective judgements — something we are not particularly good at. Particularly when you consider all of the criteria addressed in grading carcases.
The Meat and Livestock Australia (MLA) website gives the following criteria for grading carcases:
- Body number and lot number — cattle from individual vendors will be kept in separate lots.
- Carcase weight — important in determining weight for maturity.
- Sex — male or female.
- Tropical breed content — the hump height is also measured to guarantee the most accurate eating quality grade.
- Hanging method — determined as being either Achilles hang or tenderstretch.
- Hormonal growth promotants — will affect MSA score obtained for different muscles.
- Ossification — measured to determine carcase maturity.
- Marbling — using both the MSA and AUS-MEAT measurement systems.
- Rib fat — a minimum of 3 mm is required, measured at the AUS-MEAT standard site. Overall fat cover is also assessed including any hide puller damage.
- pH and temperature — pH is measured using a pH meter and must be below 5.71. Temperature should be below 12°C according to AUS-MEAT standards.
- Meat colour — recorded using AUS-MEAT standard meat colour chips.
Other measurements that do not impact on eating quality can be taken at the customer’s request, including:
- Eye muscle area (EMA) — measured in square cm using an AUS-MEAT grid.
- Fat colour — recorded using AUS-MEAT chips from 0 (white) to 9 (yellow).
MLA reports that producers and feedlot operators are regularly concerned about the precision of meat grading in Australia and this contributes to trust issues between producers and processors. With so many criteria to be considered it is no wonder that accuracy and consistency can be difficult to maintain.
To overcome this, MLA and Wiley have collaborated to explore how augmented reality (AR) technology can improve meat grading.
The collaborators have developed an AR platform, named ARGA (Augmented Reality Grading App), which facilitates faster, more consistent and more precise meat grading while taking full advantage of the experience and capabilities of the industry’s meat graders.
The system uses computer vision to provide objective measurement and decision support for grading staff. ARGA is designed to distinguish the colour of a meat sample accurately and determine the area of the latissimus dorsi muscle and introduce hands-free scanning of meat sample tickets. These features have been demonstrated on a Vuzix m300 augmented reality headset as well as on various handheld devices.
This project consisted of two phases:
- A research phase reviewing and cataloguing relevant augmented reality projects, case studies and technology.
- A proof of concept phase in which a prototype of an augmented reality application was developed for an AR head-mounted display and tasked with reducing the subjectivity in MSA grading in a processing environment.
Wiley R&D and Innovation Director Brett Wiskar said, “We are really excited to be working with MLA in research and innovation projects that will move the red meat industry forward into the digital era. We congratulate MLA on their foresight to investigate and invest in this technology.”
Wiskar explained some of the benefits of the meat grading AR platform. “Decision assistance for meat graders may lead to improved transparency and consistent outcomes for the meat industry. Increased precision has obvious benefits such as accuracy on a carcase-by-carcase basis and broader labour efficiencies but there are also subtle flow-on positive impacts to the industry and processors. Decision support is likely to bring about greater speed and decreased training periods for meat graders. In addition, such a solution has the potential to normalise grading performance across shift duration, between graders, between facilities and across processor groups.”
Both the augmented reality market and the platform developed through this research show substantial potential. The successful demonstration of a meat grading application in conjunction with the continuing development of augmented reality solutions make it reasonable to expect augmented reality to play a substantial role in the meat industry in years to come. This platform will have much further potential as the technology advances. Watch this space!
MLA and Wiley are now working together to prepare a submission on an augmented and virtual reality program for all of Australian agriculture.
A new learning system developed by MIT researchers improves robots' abilities to mould...
A US study measured nitrogen in wastewater from local cheesemaking and vegetable processing with...
The introduction of the new FSMA Act and the tightening of industry standards is forcing food...