Tracking fast moving objects, 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 static background and slow deblurring algorithms. In this paper, we present a tracking-bysegmentation approach implemented using state-of-the-art deep learning methods that performs near-realtime tracking on realworld video sequences. We implemented a physically plausible FMO sequence generator to be a robust foundation for our training pipeline and demonstrate the ease of fast generator and network adaptation for different FMO scenarios in terms of foreground variations
© Copyright 2020 arXiv e-print repository. All rights reserved.
|Subjects:||video mathematic-logical model real-time processing software table tennis tennis badminton volleyball beach-volley baseball|
|Notations:||technical and natural sciences sport games|
|Tagging:||deep learning künstliche Intelligenz motion tracking|
|Published in:||arXiv e-print repository|