Remote monitoring of cattle body condition through various imaging technologies has the potential to improve the efficiency and cost effectiveness of livestock production systems.
Improving livestock management decisions
Australia's livestock industries are valued at over $23 billion in 2013-14, including $11 billion in exports. Farmers' management of their livestock and pastures is a key factor in the success of their business.
Tools to automatically and remotely measure and monitor the liveweight and condition of livestock, and be able to predict future condition would allow producers to make more accurate, informed and timely decisions.
The information these tools could provide is critical for making better management decisions about feed supply, animal management and when to muster to achieve the optimal selling date for profitability. The end goals are to increase the percentage of animals meeting market specifications and optimal reproductive performance of the livestock.
LiDAR and stereo vision reveal the whole picture
We are currently leading research and development of applications for real-time liveweight monitoring. Integration of automatic monitoring of body condition is a significant opportunity to build a more holistic solution.
One of the technologies currently being tested to estimate body condition is LiDAR – "Light Detection And Ranging". LiDAR is a laser imaging technology that measures three-dimensional structural data with millimetre to centimetre accuracy. LiDAR sends non-invasive rapid pulses of invisible light (laser pulses) at the target (in this case an animal) and a sensor mounted on the instrument measures the amount of time taken for each light pulse to bounce back. In this way it can generate a detailed 3D 'picture' of the animals shape and surface characteristics.
The other technology on trial is 3D imaging using stereo vision. Similar in concept to human binocular vision, stereo vision uses two cameras to obtain two images from which 3D shape information can be obtained. The way that machine stereo vision generates the third dimension is achieved by finding the same features in each of the two images, and then measuring the distances of objects containing these features by triangulation.
A team of researchers is testing LiDAR and stereo vision technologies to see how accurately they can objectively measure body condition score of beef cattle. It is important that these technologies can operate reliably in very harsh and remote conditions so that regular measurements can be obtained on individual animals. That way producers can know at any given time the exact weight and condition of their livestock.
In association with the Digital Homestead project, the technology could be integrated with the 'walk-over-weighing' system for remotely determining animal liveweight, with data sent over a sensor network so that individual animal information is readily available to the producer in real-time.
Building a robust and reliable technology
The project team has commenced the initial testing of the technologies in cattle yards, comparing the outputs to visual assessment of cattle condition. The next step will be a larger scale assessment capturing more variation in cattle breed, colour, size and condition.
If proof-of-concept is successful, the most promising technologies can be deployed in field conditions with the possibility of integrating them into a sensor network for real-time data capture. At the same time, forward-prediction models are being evaluated to enable a forecast of animal liveweight and condition.
This project is one of a suite of Precision Livestock Management innovations, and is connected to the Digital Homestead project which brings together new technology and information streams from both within the farm and external to it, in order to make better beef farm management decisions.
Do business with us to help your organisation thrive
We partner with small and large companies, government and industry in Australia and around the world.