Transformer-Based Multi-Object Tracking of Football Players Using Pseudo-Labeling

dc.contributor.authorHedén, Anton
dc.contributor.authorOdengard, Anthon
dc.contributor.departmentChalmers tekniska högskola / Institutionen för elektrotekniksv
dc.contributor.examinerMcKelvey, Tomas
dc.contributor.supervisorSjöberg, Anders
dc.contributor.supervisorSvensson, Lennart
dc.date.accessioned2025-06-30T11:38:19Z
dc.date.issued2025
dc.date.submitted
dc.description.abstractThis thesis investigates the problem of tracking football players in video sequences, with a focus on adapting modern multi-object tracking (MOT) methods to the specific challenges of football environments. The work is part of a broader effort to develop tools for analyzing football games using automated visual data. In this context, we utilize MOTRv2, a transformer-based tracking model originally designed for general-purpose MOT tasks, and apply it to the football domain, where challenges such as frequent occlusions, tight formations, and rapid movement are prevalent. To address the lack of annotated football-specific tracking data, we implement a pseudo-labeling framework that allows the model to be trained on unlabelled domain data in a semi-supervised fashion. This approach enables progressive refinement of the model through multiple training cycles on domain-specific content. Our results show that MOTRv2 can be adapted to the football setting and performs well in many scenarios, particularly in open-play segments with clear player separation. However, limitations remain, including decreased tracking stability in crowded scenes and occasional ID-switches due to overlapping motion patterns. Overall, this work demonstrates the potential of transformer-based trackers in sports applications and highlights the benefits of self-supervised training when domainspecific data is scarce. The findings offer insights for future improvements in automated sports tracking systems.
dc.identifier.coursecodeEENX30
dc.identifier.urihttp://hdl.handle.net/20.500.12380/309777
dc.language.isoeng
dc.setspec.uppsokTechnology
dc.subjectComputer Vision
dc.subjectMultiple Object Tracking
dc.subjectTransformer
dc.subjectFootball
dc.subjectPseudo-Labeling
dc.subjectRe-ID
dc.titleTransformer-Based Multi-Object Tracking of Football Players Using Pseudo-Labeling
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeComplex adaptive systems (MPCAS), MSc

Ladda ner

Original bundle

Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
Transformer_Based_Multi_Object_Tracking_of_Football_Players_Using_Pseudo_Labeling.pdf
Storlek:
36.27 MB
Format:
Adobe Portable Document Format

License bundle

Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: