Realtime flicker removal for fast video streaming and detection of moving objects

High-speed cameras are used in computer vision systems to track balls, shuttlecocks, or players in many different sports. Collected information is used for statistics, as coaches’ and players’ aids to improve technique and tactics or as referees’ aids to verify their decisions or to enrich televisio...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2021-04, Vol.80 (10), p.14941-14960
Main Authors: Nowisz, Jarosław, Kopania, Michał, Przelaskowski, Artur
Format: Article
Language:English
Subjects:
Adaptive algorithms
Algorithms
Computer Communication Networks
Computer Science
Computer vision
Data Structures and Information Theory
Flicker
Frames (data processing)
Frames per second
High speed cameras
Light sources
Motion perception
Moving object recognition
Multimedia Information Systems
Shuttlecocks
Special Purpose and Application-Based Systems
Sports
Tactics
Tracking
Video transmission
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:High-speed cameras are used in computer vision systems to track balls, shuttlecocks, or players in many different sports. Collected information is used for statistics, as coaches’ and players’ aids to improve technique and tactics or as referees’ aids to verify their decisions or to enrich television broadcasts. Sports arenas in which games are played are often equipped with lights generating flickering effects in captured movies. A fast and yet effective enough algorithm is necessary to remove flickering so movement detection and object tracking algorithms could be used. In this paper, we propose a fast flicker removal algorithm working as an online filter on frame streams at speeds exceeding 200 frames per second. Most of the solutions found in literature concentrate on effectiveness and accuracy and not on the speed of operation. In contrast, our original solution is designed with speed in mind with sufficient accuracy to be used before calculating differential frames to detect movement in streams. Our algorithm is adaptive and works when lighting conditions are changing (new light sources) and performs well with various light sources that are causing flickering. The results of the experiments carried out show the high effectiveness of the method implemented on CPU and GPU, allowing effective tracking of objects of interest in preliminary applications of a commercially offered instant review system for badminton.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-020-10385-8