Real-Time Head Pose Estimation in Low-Resolution Football Footage
Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesisAlternative title
Realtidsestimering av huvudets vridning i lågupplösta videosekvenser från fotbollsmatcher (Swedish)
This report examines the problem of real-time head pose estimation in low-resolution football footage. A method is presented for inferring the head pose using a combination of footage and knowledge of the locations of the football and players. An ensemble of randomized ferns is compared with a support vector machine for processing the footage, while a support vector machine performs pattern recognition on the location data. Combining the two sources of information outperforms either in isolation. The location of the football turns out to be an important piece of information.
Place, publisher, year, edition, pages
2009. , 61 p.
, TRITA-CSC-E, ISSN ISSN-1653-5715 ; 2009:130
head pose estimation, football, real-time, coarse head pose estimation, machine learning, computer vision, svm, randomized ferns
Computer Science Computer Vision and Robotics (Autonomous Systems) Computer Engineering
IdentifiersURN: urn:nbn:se:kth:diva-12061OAI: oai:DiVA.org:kth-12061DiVA: diva2:300808
Sullivan, Josephine, Assistant Professor
Carlsson, Stefan, Professor
ProjectsCapturing and Visualizing Large scale Human Action (ACTVIS)
QC 201007072010-07-072010-03-012010-07-07Bibliographically approved