Technologies

Discover, Connect & Collaborate at TECHINNOVATION 2021

Animal Weight Estimation Utilizing Computer Vision

Technology Overview

  • This solution is one among numerous AI and Machine Learning solutions Crayon has developed at our Data & AI Center of Excellence. Our solution automates the current manual process of weight measurement of animals. This process currently involves significant resources and accuracy is difficult due to animal movement. It also increases the animals stress for each weighing, which affects their eating habits and can affect the quality of the end-product. By removing the animal’s exposure to humans as part of this process the risk of contamination and increased stress of the animal is reduced, providing a higher quality end-product.
  • This solution utilizes proprietary developed Computer Vision and Machine Learning algorithms to identify animals and accurately predict their weight, removing the need of human intervention until the final stage. The solution can predict the weight of multiple animals utilizing one single camera.
  • The target user of our solution includes the animal husbandry industry, precision livestock farming market, livestock monitoring solutions providers. We are looking for industry partners and/or technology partners to collaborate to prove the feasibility of the solution in the region.

Technology Features, Specifications and Advantages

  • Our solution enables organizations to reduce its dependency on the tacit knowledge of their employees and take a data driven approach as to which animals have reached the desired weight during the growth stage. Additionally, our solution allows the organization to gather valuable data points on their animals over time, providing further prediction and insights that was previously not possible.
  • The main advantages our solution provides include; Improved efficiency of staff by providing them with the right information at the right time to provide more accurate decision making as well as automating a traditionally human resource heavy process, significantly decreasing risk of contagion due to reduced interaction between humans and animals, and capability to identify sick animals and other anomalies by identifying under-weight or over-weight animals.
  • Currently, the process either utilizes cameras and tacit knowledge of their employees to estimate the animal weight. IoT devices could potentially provide estimates, but scaling would be cost prohibitive. Other state of the art weight estimators are utilizing expensive and complex sensors and scanners and may not work in crowded areas, making them difficult to scale. Our solution, however, is highly scalable due to the nature of Computer Vision and Machine Learning technologies, which is a novel approach in the animal husbandry industry, but one we have successfully proven to be efficient, allows for increase productivity and easily scalable solution.

Potential Applications

  • The solution primary application is to identify an animal and predict its weight without human interaction. It can be applied in any areas where humans are monitoring animals utilizing vision to track the growth stages of an animal, or where counting of animals is currently done manually.
  • Potential product areas include Machine Learning powered animal husbandry management platform utilizing computer vision to track, count and measure animals and their behavior. With the data gather further analysis can be done to provide organizations with data driven predictions and insights to improve their operations.
  • With the current Precision Livestock Market in APAC being estimated at US$3.1 billion in 2020, and is expected to reach US$4.8 billion by 2025, at a CAGR of 9.0%, there is a significant opportunity for our solution in the region.

Customer Benefit

  • Improve efficiency and productivity of pig farms by automating the pig weight estimation during the growth stage.
  • Reduced animal stress, maintained eating habits towards target growth rate.
  • Efficient meat production.
  • Increase staff efficiency and increasing profit.
  • Identifying sick animals and anomalies by finding under-weight or over-weight ones.
OVERVIEW
Contact Person

David Bergendahl

Organisation

Crayon Pte. Ltd.

Technology Category

  • Foods
  • Processes

Technology Readiness Level

Keywords

Computer Vision, AI, Machine Learning, Animal, Wellbeing