New Zealand agritech startup Scanabull has developed a world-first system capable of estimating cattle weight instantly using a 3D camera on a phone or a custom hardware device, with AI processing running directly on the device (edge computing). Promising to weigh cattle in one second without the crush or guesswork, the technology provides meat processors and farmers with accurate real-time data about on-farm production.
Founded in April 2024 by Dan Bull who is now joined by Co-founders combining expertise in farming, veterinary science and artificial intelligence, Scanabull has built a computer-vision platform that allows meat processors and farmers to determine the live weight of cattle in a second using the LiDAR sensor on an iPhone. The technology captures a 3D scan of the animal and processes it using proprietary neural networks run directly on the device.
The company has announced a NZ$1.1 million raise led by Sprout Agritech, with support from Enterprise Angels and Callaghan Innovation’s Deep Tech Incubator programme.
Scanabull is already working with industry partners, including Silver Fern Farms, with trials and demonstrations underway across New Zealand. Scanabull will actively explore opportunities in Australia and other major beef-producing regions by year-end.
Bringing objective data to the beef supply chain
Unlike dairy farming, where real-time data is widely used to manage production, much of the beef industry still relies on estimation when assessing livestock weight.
Traditionally, cattle must be mustered into yards and processed through weigh platforms - a process that can be time-consuming, labour-intensive and stressful for animals. What’s more, weighing systems can cost tens of thousands of dollars and require purpose-built yards and handling facilities. In some cases, the stress of yarding can even result in short-term weight loss, making frequent weighing counterproductive.
Co-Founder and CEO Dan Bull, who grew up on a farm and spent several years actively managing livestock, says this lack of accurate data can create costly inefficiencies across the supply chain. “Many animals are bought and sold based on visual estimates rather than objective measurements. When those estimates are wrong, it can result in significant financial differences for farmers, traders and processors,” explains Bull.
“Our goal is to give the beef industry a fast, reliable way to understand what’s actually happening with their animals in real time.”
How Scanabull works
Scanabull has two systems: a phone app that works on an iPhone Pro and a custom camera called the Scanabull Weigh Point that weighs animals automatically in the paddock. The phone app allows a quick measure of animal weight, whereas the Weigh Point allows better measurement of growth trends. The technology generates a detailed 3D point cloud of an animal and processes the data using a deep neural network which analyses the animal’s shape and structure to accurately estimate its live weight.
The model processes spatial data around 30 times per second, allowing the system to deliver a weight estimate in roughly one second. The system is currently over 93% accurate on individuals, but much more accurate at the mob level. Accuracy is improving as Scanabull gathers more data.
The technology has been trained using over 100,000 animal data points, enabling it to continuously improve as more livestock scans are captured.
Running this level of machine learning directly on a mobile device required significant technical innovation. Because farms often operate in remote areas without reliable connectivity, the system was designed to run entirely on-device using edge computing rather than relying on cloud infrastructure.
“No one is running neural networks at this speed on edge devices for livestock applications. Scanabull has developed our own proprietary architecture and training models to make it possible,” explains Bull.
A practical tool for farmers and industry
Scanabull’s first product is the WeighApp, which enables farmers, stock agents and veterinarians to scan animals directly in yards, pens or near farm gates using their smartphone. The goal is to provide farmers with a quick and low-stress way to monitor livestock performance without needing expensive weight platforms or specialised infrastructure, and ultimately give meat processors access to valuable supply chain data to improve the efficiency of their operations.
Future versions of the technology will extend beyond live weight measurement to include additional livestock metrics such as carcass weight prediction and body condition scoring.
Championing industry transparency
Co-founder and Chief Commercial Officer Dr Ursula Haywood, a veterinarian who spent a decade working in rural practice before moving into agritech, says the technology has the potential to introduce a new level of transparency to livestock management.
“The beef sector is still heavily reliant on estimation and manual processes. By introducing objective measurements that can be captured quickly in the field, we can help farmers manage their animals more effectively and make more informed decisions about when to sell,” Haywood says.
Beyond farmers, the technology also has applications for livestock traders, veterinarians and meat processors seeking greater visibility into their upstream livestock supply. “Processors often have very little reliable data about animals before they arrive at the plant,” says Bull. “Improving weight visibility earlier in the supply chain can help reduce inefficiencies and even improve relationships between farmers and buyers.”
Investment to accelerate development
Crispin Dye, Investment Manager at Sprout Agritech, says Scanabull is a powerful example of how deep technology can transform traditional industries. “Technologies that bring reliable data into agricultural supply chains have enormous potential. Scanabull’s use of computer vision and on-device AI opens up new possibilities for livestock management and supply chain transparency,” Dye says. The startup is a Sprout Accelerator Alumni.
The newly secured funding will support further development of Scanabull’s AI models, additional data collection and international expansion as the company prepares for broader commercial rollout.
Bull and Haywood believe the opportunity extends far beyond simple weight estimation.
“Our ambition is to help bring data-driven decision making into the beef industry from birth through to processing. Once farmers have accurate, real-time data about their animals, everything from farm management to market pricing becomes more efficient,” concludes Haywood.
(ENDS)