AI/ML COMPUTER VISION FOR THE NEXT GENERATION POULTRY FARMS
Researchers from consortium engaged poultry farms to understand their business challenges and propose an IoT-based management solution. They used HPC and deep learning AI to create prediction models for edge devices with camera sensors, enabling the use of IoT/AI solutions in the poultry sector.
Start date: 01/06/2021
Duration in months: 18
Problem Description
Raising chickens means closely monitoring environmental conditions, e.g. measuring air temperature and humidity, CO2 and ammonia levels, and having insights into chicken health. DunavNET addressed this issue with a modern digital farming platform based on IoT technology.
Goals
New services
Challenges
DigitalSmart and DunavNET gathered around the question of how to utilize artificial intelligence (AI) and machine learning (ML) to develop computer vision sensors that can monitor the number of chickens, assess their weight, detect dead chickens.
Innovation results
DigitalSmart and DunavNET utilised HPC to efficiently apply deep learning to train and later calibrate prediction models. This process led to the creation of a new type of precision agriculture sensor to support the next generation of poultry farms.
Business impact
The smart agriculture solution developed within this experiment could boost the productivity of poultry farms by potentially reducing both manual labor costs and chicken mortality rates by about 10% each. For SME farms these savings could exceed hundreds of thousands of euros annually.