Master Thesis Proposal - Data Augmentation of Naturalistic Two-Wheeler Data Using Video Processing and Sensor Fusion
Are you a Master student with a passion for saving lives? Then this might be the role for you!
Background
According to the Global status report on road safety 2023, around 1.19 million persons died on the roads in 2021. People riding two-wheelers (e.g., motorcycles and bicycles) shared a significant part of those road fatalities. Autoliv has increased its focus in developing countermeasures to improve the safety of two-wheelers. Some of its activities led Autoliv to collect naturalistic riding data that can describe real-life riding situations and inform researchers on the actual risks that riders face. However, the naturalistic riding raw data are usually insufficient to have a detailed picture of the traffic situation and data augmentation must be done to estimate metrics that could be used to draw this detailed picture. Data augmentation is already something that can be done using data processing algorithms such as visual simultaneous localization and mapping (VSLAM) algorithms. The majority of the publicly available VSLAM algorithms are not adapted out-of-the-box to two-wheeler applications and this thesis aims to address this gap.
Aim
The aim of this thesis work will be to develop a data augmentation software (e.g., VSLAM algorithm) fitted to two-wheeler riding data.
Work Packages
1. Calibrate the sensors of the two-wheeler data logging systems and collect ground-truth data
2. Benchmark different data augmentation techniques (e.g., VSLAM algorithms) that are publicly available
3. Develop a data augmentation software that is fitted to Autoliv’s data logging systems
4. Disseminate the results internally and externally
Literature reviews are expected during each work package.
Suitability
- 1-2 Master students with a background in Automation and Mechatronics or Computer Science
- Programming skills (Python and/or C/C++) required
- Competences in sensor fusion and nonlinear filtering
- Competences in computer vision
- Previous experience with ROS2 is desirable
Application
If you find this opportunity interesting and in line with your profile, do not wait with your application! We will start the recruitment process immediately and the positions could be filled before the final application date, 2024-12-01.
If you have any questions, you are welcome to contact the supervisor:
Christian-Nils Boda, christian-nils.boda@autoliv.com
- Function
- Students & Graduates
- Locations
- Autoliv Research - Vårgårda - ADS
- Remote status
- Hybrid
Autoliv Research - Vårgårda - ADS
Workplace & Culture
We strive to save more lives and prevent serious injuries, and we continuously focus on quality, confidence and security for our customers, stability and growth for our shareholders and employees, as well as being sustainable and earning trust within our communities.
About Autoliv Sweden
Autoliv is the world's largest automitive safety supplier, with sales to all major car manufacturers in the World. Our more than 67,000 Associates in 27 countries are passionate about our vision of Saving More Lives.
Master Thesis Proposal - Data Augmentation of Naturalistic Two-Wheeler Data Using Video Processing and Sensor Fusion
Are you a Master student with a passion for saving lives? Then this might be the role for you!
Loading application form