Tracking Fast Moving Objects by Segmentation Network

Tracking Fast Moving Objects (FMO), which appear as blurred streaks in video sequences, is a difficult task for standard trackers, as the object position does not overlap in consecutive video frames and texture information of the objects is blurred. Up-to-date approaches tuned for this task are base...

Full description

Saved in:
Bibliographic Details
Published in2020 25th International Conference on Pattern Recognition (ICPR) pp. 10312 - 10319
Main Authors Zita, Ales, Sroubek, Filip
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.01.2021
Subjects
Generators
Pattern recognition
Pipelines
Real-time systems
Streaming media
Training
Video sequences
Online AccessGet full text

Cover

More Information
Summary:Tracking Fast Moving Objects (FMO), which appear as blurred streaks in video sequences, is a difficult task for standard trackers, as the object position does not overlap in consecutive video frames and texture information of the objects is blurred. Up-to-date approaches tuned for this task are based on background subtraction with a static background and slow deblurring algorithms. In this article, we present a tracking-by-segmentation approach implemented using modern deep learning methods that perform near real-time tracking on real-world video sequences. We have developed a physically plausible FMO sequence generator to be a robust foundation for our training pipeline and demonstrate straightforward network adaptation for different FMO scenarios with varying foreground.
DOI:10.1109/ICPR48806.2021.9413129