Mathieu Cocheteux- Master of Science
- PhD Student at University of Technology of Compiègne
Mathieu Cocheteux
- Master of Science
- PhD Student at University of Technology of Compiègne
Currently focusing on deep learning-based sensor calibration for autonomous driving.
About
5
Publications
159
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
7
Citations
Introduction
I'm Mathieu Cocheteux, a PhD candidate in Computer Science at Université de technologie de Compiègne, focusing on sensor calibration and autonomous systems. My research has led to publications in top conferences like WACV and CVPR, and an international patent. I've gained experience through roles at Motional, Toyota Motor Europe, and as a researcher at my university.
Current institution
Additional affiliations
June 2022 - December 2022
Motional
Position
- Research Engineer
April 2021 - September 2021
July 2020 - January 2021
Education
October 2021 - April 2025
Field of study
- Computer vision, Artificial intelligence, Intelligent vehicles
February 2016 - March 2021
Publications
Publications (5)
Accurate sensor calibration is crucial for autonomous systems, yet its uncertainty quantification remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration, combining Monte Carlo Dropout with Conformal Prediction to generate prediction intervals with a guaranteed level of coverage. Our...
Despite the increasing interest in enhancing perception systems for autonomous vehicles, the online calibration between event cameras and LiDAR - two sensors pivotal in capturing comprehensive environmental information - remains unexplored. We introduce MULi-Ev, the first online, deep learning-based framework tailored for the extrinsic calibration...
Camera-LiDAR extrinsic calibration is a critical task for multi-sensor fusion in autonomous systems, such as self-driving vehicles and mobile robots. Traditional techniques often require manual intervention or specific environments, making them labour-intensive and error-prone. Existing deep learning-based self-calibration methods focus on small re...
We introduce a novel architecture, UniCal, for Camera-to-LiDAR (C2L) extrinsic calibration which leverages self-attention mechanisms through a Transformer-based backbone network to infer the 6-degree of freedom (DoF) relative transformation between the sensors. Unlike previous methods, UniCal performs an early fusion of the input camera and LiDAR d...
