International audienceThree-dimensional (3D) real-time object detection and tracking is an important task in the case of autonomous vehicles and road and railway smart mobility in order to allow them to analyze their environment for navigation and obstacle avoidance purposes. In this paper, we try to improve the efficiency of 3D monocular object detection by using dataset combination, knowledge distillation, and creating a lightweight model. Firstly, we combine real and synthetic datasets to increase the diversity and richness of the training data. Then, we use knowledge distillation to transfer the knowledge from a large, pre-trained model to a smaller, lightweight model. Finally, we created a lightweight model by selecting the combination...
An environment perception system is one of the most critical components of an automated vehicle, whi...
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. ...
International audienceThis paper shows how to improve the real-time object detection in complex robo...
International audienceFor smart mobility, and autonomous vehicles (AV), it is necessary to have a ve...
International audienceFor smart mobility, autonomous vehicles, and advanced driver-assistance system...
To improve transportation safety and make driving more autonomous, vehicles must have a better perce...
International audienceA robust visual understanding of complex urban environments using passive opti...
In recent years, we have seen an incredible increase in deep learning. With increasing interest, we...
In this thesis, we first tackle the monocular 3D object detection task. The main challenge in monocu...
Afin d'améliorer la sécurité des transports et rendre la conduite plus autonome, les véhicules doive...
International audienceIn core computer vision tasks, we have witnessed significant advances in objec...
This PhD work is to be seen within the context of autonomous vehicle perception, in which the detect...
In this thesis, we are interested in fine-grained analysis of vehicle from an image. We define fine-...
International audienceIn this paper, we will introduce our object detection, localization and tracki...
This thesis addresses the problem of obstacle avoidance for semi- and autonomous terrestrial platfor...
An environment perception system is one of the most critical components of an automated vehicle, whi...
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. ...
International audienceThis paper shows how to improve the real-time object detection in complex robo...
International audienceFor smart mobility, and autonomous vehicles (AV), it is necessary to have a ve...
International audienceFor smart mobility, autonomous vehicles, and advanced driver-assistance system...
To improve transportation safety and make driving more autonomous, vehicles must have a better perce...
International audienceA robust visual understanding of complex urban environments using passive opti...
In recent years, we have seen an incredible increase in deep learning. With increasing interest, we...
In this thesis, we first tackle the monocular 3D object detection task. The main challenge in monocu...
Afin d'améliorer la sécurité des transports et rendre la conduite plus autonome, les véhicules doive...
International audienceIn core computer vision tasks, we have witnessed significant advances in objec...
This PhD work is to be seen within the context of autonomous vehicle perception, in which the detect...
In this thesis, we are interested in fine-grained analysis of vehicle from an image. We define fine-...
International audienceIn this paper, we will introduce our object detection, localization and tracki...
This thesis addresses the problem of obstacle avoidance for semi- and autonomous terrestrial platfor...
An environment perception system is one of the most critical components of an automated vehicle, whi...
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. ...
International audienceThis paper shows how to improve the real-time object detection in complex robo...