Single player tracking in multiple sports videos

Added Title

Mechatronics and Machine Vision in Practice (21st : 2015)
Annual International Conference on Mechatronics and Machine Vision in Practice (22nd : 2015)

College

College of Computer Studies

Department/Unit

Computer Technology

Document Type

Book

Source Title

Mechatronics and Machine Vision in Practice 3

First Page

73

Last Page

89

Publication Date

4-4-2018

Abstract

Performance analysis for basketball development programs are based on the athletes' movement patterns, playing position on an area, and ball acquisition. The objective of the system is to automate the performance analysis by providing raw statistical data based on the player's behaviors produced through tracking the player inside the basketball court. Using visual features described by SURF, unoccluded players are localized using a tracking by detection approach with an observed accuracy of 40%. Player positions are also adjusted to compensate for distortions, which improves player localization by 0.11%, on average. © Springer International Publishing AG, part of Springer Nature 2018.

html

Digitial Object Identifier (DOI)

10.1007/978-3-319-76947-9_6

Disciplines

Graphics and Human Computer Interfaces

Note

Presented at the 21st Mechatronics and Machine Vision in Practice, M2VIP 2015 and the 22nd Annual International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2015

Keywords

Pattern recognition systems; Human activity recognition

Upload File

wf_yes

This document is currently not available here.

Share

COinS