Image & Video Machine Learning

Big data and machine learning are taking over almost every industry right now, and the drone industry is no exception. Event 38 is able to do AI integration for your drone, or take your existing AI and incorporate it into one of our drones.

Using image and video related machine learning we are able to train a machine learning model to detect any object of interest. Event 38 is then able to deploy that model on an embedded computer on board the drone itself, so you don’t need to transmit the data to a ground station if link bandwidth is limited.

How it works: The two main processes are machine learning and computer vision. We gather a set of images or video frames and mark the target object in the image that you are trying to detect and label it. Then we run it through cloud processing and that will output a model. The model is then loaded onto an embedded computer and integrated with the on board payload.

Strengths – Simplifies training/setup, Can perform otherwise very difficult image processing tasks

Weaknesses – Only as good as your data set, Can produce false positives

The image to the right is of semantic segmentation of aerial imagery. Red is buildings, green is foliage, gray is pavement/dirt/etc, pink is vehicles.

Applications

  • Identify and track any item of interest (E.g. car, person, structure, boat, or broken solar panels)
  • Disaster Relief
  • Perimeter Security
  • Agriculture
  • Infrastructure Inspections (E.g. pipeline, bridge, runway, utility)
  • Safe Landing/Obstacle Avoidance