Autonomous vehicles and Advanced Driver-Assistance Systems (ADAS) have shown outstanding improvements these past few years thanks to a more accurate and reliable road scene analysis. These enhancements are mostly due to the emergence of deep learning, enabling a very accurate road abject detection. However, even if nowadays autonomous vehicles can be found in several countries, they show limits when then visibility is altered. Non-conventional modalities are the best solution to overcome this limitation, thanks to their ability to see beyond human vision, yet without being robust to any test. In this thesis, we aim to address this challenge by using polarimetric imaging, describing abjects by their physical properties invariant to visibilit...
National audienceThe notion of autonomous vehicle has been deep-rooted in the collective imagination...
This paper focuses on exploring ways to improve the performance of LiDAR imagers through fog. One of...
The surveillance industry has traditionally focused on the use of colour intensity images and then u...
Autonomous vehicles and Advanced Driver-Assistance Systems (ADAS) have shown outstanding improvement...
Advance Driver Assistance Systems (ADAS) aim to automate/adapt/enhance trans-portation systems for s...
International audienceRoad scene analysis is a fundamental task for both autonomous vehicles and ADA...
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to m...
International audienceObject detection in road scenes is necessary to develop both autonomous vehicl...
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to m...
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks i...
International audienceObject detection in road scenes is an unavoidable task to develop autonomous v...
Autonomous cars are an emergent technology which has the capacity to change human lives. The current...
National audienceThe notion of autonomous vehicle has been deep-rooted in the collective imagination...
This paper focuses on exploring ways to improve the performance of LiDAR imagers through fog. One of...
The surveillance industry has traditionally focused on the use of colour intensity images and then u...
Autonomous vehicles and Advanced Driver-Assistance Systems (ADAS) have shown outstanding improvement...
Advance Driver Assistance Systems (ADAS) aim to automate/adapt/enhance trans-portation systems for s...
International audienceRoad scene analysis is a fundamental task for both autonomous vehicles and ADA...
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to m...
International audienceObject detection in road scenes is necessary to develop both autonomous vehicl...
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to m...
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks i...
International audienceObject detection in road scenes is an unavoidable task to develop autonomous v...
Autonomous cars are an emergent technology which has the capacity to change human lives. The current...
National audienceThe notion of autonomous vehicle has been deep-rooted in the collective imagination...
This paper focuses on exploring ways to improve the performance of LiDAR imagers through fog. One of...
The surveillance industry has traditionally focused on the use of colour intensity images and then u...