Search
Menu
Lumencor Inc. - Power of Light 4-24 LB

Thermal Imaging Takes the Guesswork Out of Feeder Cattle Sizing

Facebook X LinkedIn Email
Stanley Kummer

In the feeder cattle industry, sizing considerations are extremely important. Sending animals to slaughter that are not the correct size can be a costly mistake for a producer, yielding lower-quality meat that consequently demands a lower price on the market. Until recently, sizing processes have been limited in their ability to gauge size effectively, but thermal imaging technology offers a means to overcome these limitations.

More than an animal's weight is necessary to predict whether it will merit a grade of "Choice" -- the most popular at retail meat counters -- from the US Department of Agriculture (USDA). Feeder cattle also must be evaluated according to the size of their physical frame. According to the Training Manual for USDA Standards for Grading Slaughter Animals, feeder cattle grades are determined by differences in frame size and muscle thickness. With three recognized grades of frame size and four of muscle thickness, producers must determine which of the 12 combinations describes a given animal before they can deduce that it has reached the optimal weight for slaughter.

Apps1.jpg
Thermal imaging enables a producer of feeder cattle to perform automated "slaughterability" assessments that are not subject to the edge-definition errors caused by dust and variation in animal color that can affect visible-light systems in this application.

A technologically sophisticated feeder cattle producer may conduct the "slaughterability" assessment process by sending animals through a chute and photographing them from above with a CCTV or visible-light camera that is connected to a computer system. The system's machine vision software examines the image of the animal to determine its edge definition. By measuring the area inside the defined edges, the software can help measure the animal's mass and determine whether it will meet USDA standards.

Trioptics GmbH - Worldwide Benchmark 4-24 LB

There are, however, practical problems with such a setup. Because much of the sizing is performed in an outdoor environment, the dust that is kicked up by the cattle interferes with the visible-light camera system's ability to perform the edge definition effectively. In addition, the different colors on the cattle, some of which are similar to that of the ground, can make it difficult for visible-light systems to determine where an animal begins and the background ends. Some producers have tried to fix these problems by increasing the illumination on the cattle while they are being photographed. However, the extra light can make the animals more nervous, causing them to move about all the more and to stir up additional dust.

One producer solved the problems by using thermal imaging cameras. Thermal imaging technology operates in the 7- to 14-µm wavelength range, so it is able to "see" through the dust. In addition, by measuring and displaying thermal characteristics, it is easy for the software to distinguish an animal from the background -- no matter the color of the animal or ground. Using a thermal camera, the system designer acquired consistent, reliable images, enabling the machine vision software to perform more accurate edge-definition measurements.

Although thermal systems may cost more than those that incorporate visible-light cameras, they can help producers avoid the expense of inaccurate sizing and grading. This means that the thermal imaging camera systems give a high return on investment.

Published: January 2005
Glossary
machine vision
Machine vision, also known as computer vision or computer sight, refers to the technology that enables machines, typically computers, to interpret and understand visual information from the world, much like the human visual system. It involves the development and application of algorithms and systems that allow machines to acquire, process, analyze, and make decisions based on visual data. Key aspects of machine vision include: Image acquisition: Machine vision systems use various...
Accent on ApplicationsApplicationsmachine visionmachine vision softwarethermal imaging technologyvisible-light cameras

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.