Multimodal detection of emotions and stress in drone operators using deep learning
Operators of drones and remotely piloted aircraft have a demanding job, with many challenges.
As UAVs ( unmanned aerial vehicles) become increasingly autonomous, the number of personnel at the controls during missions is reduced. But this also poses safety challenges, as control and supervision periods become increasingly long.
CRIM’s project, carried out via the National Defense IDEeS program, aims to assess the state of operators non-intrusively using AI and computer vision. The new technique uses facial emotion analysis to assess a person’s emotional state using a deep learning model.
The development of a reliable, non-intrusive technique would make it easy to monitor the psychological state of individual operators, and avoid mental overload that could lead to incidents.
Additional information: AI detects emotional state of drone operators – CScience.ca – March 3, 2021
Mohamed Dahmane, a computer vision researcher at CRIM, will offer a master class on the subject:
Human factors in autonomous system operators: AI in the loop.
As part of CRIAQ’s RDV Forum on February 19, 2021 at 1:30pm. Register here
