One of the main use cases of Fyma is gathering live movement data from video streams.
Model is a neural network responsible for detecting object from video frames.
Creating a one-size-fits-all model is nearly impossible. That's why we have different types of models such as
- outdoor (detects light and heavy traffic, people etc)
- people (specifically optimised for detecting people)
- top-down (optimised for detecting people in retail)
- age (tries to predict whether a person is a child or adult)
- gender (tries to predict wheter a person is male/female)
Counter lines and polygons
What really makes Fyma useful is the ability to add counter lines and polygons which give detailed data about specific areas of interest.