Using machine learning we are able to process vast amounts of imagery into meaningful information. Together with our clients, we develop custom object recognition algorithms tailored to their specific needs.


Automated Vine Row Detection

Digital Falcon has developed a new method to automatically segment crops with distinct row and canopy configurations (e.g. vineyard, fruit orchards and vegetable crops) in aerial imagery. By simplifying the skill set required to collect and analyse remotely sensed data, we can start to realise the potential unmanned aerial systems (UAS) has in precision agriculture and environmental monitoring.


Apple Sunburn Risk and Fruit Diameter Estimation

The horticultural industry required a quick, reliable and accurate tool to help estimate final fruit size and assess sunburn risk. Digital Falcon used machine learning to train a model to automatically detect apples to calculate their diameter and average temperature for the estimation of sunburn risk. The project was funded to The University of Melbourne (UoM) and The Department of Economic Development, Jobs, Transport and Resources (DEDJTR) from The Innovation Seed Fund for Horticulture Development.

Emotion Recognition Software

We’re improving food and beverage sensory studies analysis by quantifying changes in consumer physiological responses including:

  • Emotions
  • Heart rate
  • Pupil dilation
  • Face micro-movement patterns