Convolutional Neural Networks



Information deducible from Images, Video, Audio is increasingly available digitally. Their analysis can support humans in contexts such as medicine, robotics, control systems, security, etc.

The market demand is for more and more precise and efficient AI tools for real-time analysis to accompany e.g. medical image analysis, artificial vision for industrial robotics, quality control in production, automotive traffic safety, etc..

Humanativa – Tools and Expertise

CNN Framework (Convolutional Neural Network)

Convolutional Neural Networks are constantly evolving. Humanativa has a framework that uses the most effective and fastest CNN libraries, offering:

  • an Object Detection/Classification model
  • a pipeline in which, in addition to the first stage of Object Detection in inference mode, it is possible to insert other stages that enrich the Object Detection analysis depending on the context in which they have to be applied.
  • For example, in the automotive context of risk event control, Humanativa has developed a Tracking library for counting vehicles in the lanes of Routine Driving, Overtaking and Fast Overtaking in a motorway context.


  • Improve safety supervision capabilities
    E.g. in the automotive traffic field
  • Provide diagnostic support
    E.g. in the medical field

Use Case

  • Industry: Automotive
    Use case: Highway Control
    Automatic Incident Detection (AID), such as the detection of stopped vehicles, wrong-way vehicles, pedestrians and traffic congestion.