R&D Engineer - Improving Long-Term Multi-Object Tracking for Sports Analysis

The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regional economic players.

With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur  is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.

Inria, the French National Institute for Computer Science and Applied Mathematics, promotes “scientific excellence for technology transfer and society”. Graduates from the world’s top universities, Inria's 2,700 employees rise to the challenges of digital sciences. With its open, agile model, Inria can explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of digital transformation. Inria is the source of many innovations that add value and create jobs.

Team

The STARS research team combines advanced theory with cutting-edge practice focusing on cognitive vision systems.

Team web site : https://team.inria.fr/stars/

Scientific context

This project aims to develop advanced methods for long-term multi-object tracking (MOT), an essential task for sports analysis and video surveillance. Multi-object tracking involves locating targets while maintaining unique identities, enabling precise analysis of the movements and interactions of players or other subjects of interest in high-density environments.

The approach developed focuses on improving target association accuracy, by integrating a cost matrix into Hungarian-style association procedures. This matrix will take into account various attributes inherent to the targets, such as jersey color or player numbers, in order to optimize target matching on each image. In addition, the project focuses on reducing processing time, while adapting to the complexity introduced by a high density of people in the video sequences.

Detection-based tracking, currently divided into two independent stages (detection and association), will be enhanced by the following proposals:

    Local association: In this first stage, we will establish local associations between the current image and the objects in memory, to enhance tracking continuity.
    Long-term association: In the second stage, we'll apply a Hungarian approach to linking tracklets over an extended period. This method will reduce the calculation of re-identification functionalities and decrease the total number of tracklets created, thus ensuring better identification management.

Validation data: This project will be based on a large-scale multi-object tracking dataset, named SportsMOT, consisting of 240 video clips classified into three categories (basketball, soccer, volleyball). The characteristics of this dataset are ideally suited to the needs of the project:

    Large scale
    Detailed annotations
    Consistent player identification
    No shot changes
    High, fixed resolution (1080P)
    Varied and complex movement patterns
    Re-identification challenges

Expected result: At the end of the project, the aim is to reduce the number of “unaffected tracklets” during the 90-minute match. A key performance indicator (KPI) will be established to measure the number of tracklets generated at the end of the match, taking into account substitutes entering the field. This result will guarantee reliable and continuous player identification, which is essential for accurate sports analysis.

The Inria STARS team is seeking an engineer with a strong background in computer vision, deep learning, and machine learning.

Candidates must hold a Master's or Engineering degree or equivalent in Computer Science or a closely related discipline by the start date.

The candidate must be grounded in computer vision basics and have solid mathematical and programming skills.

With theoretical knowledge in Computer Vision, OpenCV, Mathematics, Deep Learning (PyTorch, TensorFlow), and technical background in C++ and Python programming, and Linux.

The candidate must be committed to scientific research and substantial publications.

In order to protect its scientific and technological assets, Inria is a restricted-access establishment. Consequently, it follows special regulations for welcoming any person who wishes to work with the institute. The final acceptance of each candidate thus depends on applying this security and defense procedure.

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Contribution to mutual insurance (subject to conditions)

From 2692 € gross monthly (according to degree and experience)