Using artificial intelligence to solve concrete problems
The Imaging, Vision and Artificial Intelligence Laboratory (LIVIA) is a research unit at ÉTS that focuses on the visual perception of 2D and 3D scenes and the static and dynamic modelling of environments using artificial intelligence (AI).
LIVIA’s activities are oriented around machine learning, computer vision, pattern recognition, adaptive and intelligent systems, information fusion and optimization of complex systems. LIVIA excels in the field of AI engineering, and more specifically, in the development of complex models for deep learning using massive amounts of data with limited annotations.
Main fields of application
- Medical and satellite imaging
- Video analysis and surveillance
- Biometrics (face, voice, etc.)
- Affective computing in healthcare
- Analysis of digitized documents
For close to 30 years, the laboratory has been developing innovations at ÉTS, with accomplishments that have been of invaluable benefit to numerous academic and industrial collaborations, focusing on the training of highly skilled personnel and the dissemination of scientific findings via internationally recognized conferences and journals. In addition, members of the LIVIA team have been responsible for hundreds of publications while supervising numerous graduate and post-graduate students and postdoctoral fellows. Its work also contributes to the enviable reputation that ÉTS has acquired in the research sector. In fact, ÉTS is ranked 6th in the CSRankings for computer vision in Canada.
Research Chairs associated with LIVIA
- Creating synergy that is conducive to the development of machine learning solutions for control of connected buildings.
- Developing more intelligent building management solutions.
- Developing AI-based artificial vision algorithms that are better adapted to industry.
- Developing advanced methods for inspection in manufacturing, estimating the positioning of objects, optical character recognition and bar-code reading.
- Assessing non-verbal cues with a view to personalizing online healthcare interventions (eHealth) within a context of behavioural change.
- Designing deep networks for automated recognition of facial and vocal expressions associated with ambivalence, motivation, commitment, etc.