Needs & Requirements
Digitalisation of sport activities and specifi cally collective indoor sports such as handball, volleyball and basketball is a trendy research topic at Icam. A platform – called Digisport – has already been developed that makes it possible to collect data from IMU devices and analyse these data in order to predict the activities done by athletes that wore the corresponding IMU devices. IMU-based Sport Activity Recognition is the ground of indicators of athletic performance such as numbers, distances, durations and intensities of runnings, counts, heights of jumpings, etc. However, such indicators lack accuracy from IMU measurements only. In fact, IMU provide 3-axis acceleration speeds and 3-axis angular velocities that are well known to lead to estimation drifts of speeds, distances or heights.
This MSR aims, fi rstly, at strengthening such indicators accuracy by data fusion i.e. by simultaneously analysing both IMU and LPS data in order to provide better estimations of speeds, distances and heights. It also aims, secondly, at doing data fusion as well with camera-based data and CV analysis.
Icam major partner of such studies is the Neptunes de Nantes, a professional women’s club in both handball and volleyball in Nantes. It is planned to equip their main sports hall – complexe sportif de Mangin-Beaulieu – with a complete system made of IMU and LPS fi xed devices and to provide IMU and LPS wearable devices to their coaching staff and athletes. This sports hall is already equipped with 2 IP cameras very well located which video streams are retrievable.
Hypothesis & Objectives
The main objectives of this MSR from the platform point-of-view then consist of:
1. upgrading the platform for collecting IMU and LPS data
2. upgrading the platform for strengthening sport activity analysis such as jumping height estimation, running distance and running speed measurement by data fusion
3. upgrading the platform for collecting videos alongside IMU and LPS data
4. upgrading the platform for data fusion of CV-based analysis and IMU-based and LPS-based analysis
The main objectives of this MSR from the scientific point-of-view consist of:
5. investigating scientific literature about data fusion, IMU, LPS and CV
6. running a scientific study about athlete activities in handball and volleyball
7. writing a scientific report and submitting it to an international conference or revue such as the International Journal of Computer Science in Sport
Work Packages
This MSR is planned to fi t within 5 months starting at the M0 milestone and ending at the M5 milestone. Each milestone corresponds to a 1-month boundary. It can be then organised according to the following 5 work packages:
- WP-1 LPS system (M0 – M3) developing and integrating LPS system into the Digisport platform
- WP-2 LPS data fusion (M1 – M4) inserting or upgrading IMU data analysis with LPS data
- WP-3 CV-based data fusion (M3 – M5) integrating an existing CV system into the Digisport platform and upgrading IMU and LPS data analysis with CV analysis
- WP-4 State-of-the-Art (M0 – M4) building a scientific literature review
- WP-5 Writing (M4 – M5) writing a technical report and a scientific article
The scientific study about handball and volleyball is conducted during the first 4 work packages, as well as the platform updates and enhancements. Deliverables consist both of programming codes for the platform updates and of documents for the technical report and scientific article.
Download further details
-
Compétences requises :
-
Candidates should have skills in programming, databases, data analysis, data mining, and artifi cial intelligence. Interests in sports and in basketball would also be appreciated. It is strongly suggested to include CV and motivation letter to the application. The latter must be sent via email to the supervisor. Shortlisted candidates will be invited for a (video) interview.
- Application 10th, June 2025
- Interview 17th, June 2025
- Notification 24th, June 2025
